logo

Blog


You can expect to read a post here every Sunday or Monday, mostly about Techtonique. Want to get notified? Subscribe via RSS.

A list of previous posts can be found below, and a list of categories here. Use the search bar appearing before this paragraph if you're looking for a more specific keyword.

You can also me on GitHub or Hire me on LinkedIn or Hire me on Malt or Hire me on Fiverr or Hire me on Upwork

Having any other inquiry related to the content published here? Easiest/fastest/safest way is to send an email to: thierry dot moudiki at gmail dot com.



Blogroll | Top

List of posts by date of publication | Top

  1. 'Zero-Shot Probabilistic Stock Returns Forecasting with Pretrained RVFL Networks' accepted at COPA 2026 (and to appear in the Proceedings of Machine Learning Research) Aug 15, 2026
  2. 'PCARVFLSimulator': a GAN-like tabular data synthesizer built from PCA scores, a Random Vector Functional-Link network, and residuals bootstrapping Aug 10, 2026
  3. 'garchf': GARCH probabilistic forecasting with package 'forecast'-style interface (and 'rugarch' under the hood) Aug 1, 2026
  4. GPopt for R: Bayesian and conformal optimization of black-box functions and hyperparameter tuning Jul 26, 2026
  5. My last R posts: How conformalization helps weak models, fast conformal prediction with jackknife+ (and no refitting), and sklearn in R Jul 13, 2026
  6. Natively Interpretable Boosting Jul 12, 2026
  7. Fast conformal prediction (no refitting) for some Machine Learning models via closed-form jackknife plus Jun 27, 2026
  8. Using scikit-learn models in R easily with the tisthemachinelearner package Jun 21, 2026
  9. No-Code Machine Learning in Excel with the Techtonique API Jun 14, 2026
  10. How Conformal Prediction Makes Linear Models Good Enough — An Example Using R Package mlS3 Jun 7, 2026
  11. Techtonique dot net, the Machine Learning web API, is back online (but more like a passion project for now) May 31, 2026
  12. Conformalized TabICL: Prediction Intervals for a State-Of-The-Art Tabular Foundation Model in Python and R May 21, 2026
  13. Conformalized TabPFN: Prediction Intervals for a Pretrained Transformer for Tabular Data in Python and R May 17, 2026
  14. Probabilistic Time Series Cross-Validation with R package crossvalidation May 16, 2026
  15. One interface, (Almost) Every Classifier (and Regressor): unifiedml v0.3.0 May 9, 2026
  16. You Don't Need to Learn All the Weights on tabular data: The Case for rvflnet (a nonlinear expressive glmnet) on regression, classification and survival analysis May 2, 2026
  17. Survival analysis with sklearn, glmnet, keras, pytorch, lightgbm, xgboost, nnetsauce, mlsauce Part 2 Apr 28, 2026
  18. Any Sklearn Regressor as a Survival Model — Does It Actually Work? Benchmarking vs Established Packages Apr 26, 2026
  19. Conformal Optimization Beats Bayesian Optimization, Optuna and Random Search on 72 classification Datasets Apr 19, 2026
  20. `mlS3` — A Unified S3 Machine Learning Interface in R Apr 12, 2026
  21. One interface, (Almost) Every Classifier: unifiedml v0.2.1 Apr 4, 2026
  22. Techtonique dot net is down until further notice Apr 1, 2026
  23. Explaining Time-Series Forecasts with Sensitivity Analysis (ahead::dynrmf and external regressors) Mar 29, 2026
  24. Python version of 'Option pricing using time series models as market price of risk Pt.3' Mar 22, 2026
  25. Option pricing using time series models as market price of risk Pt.3 Mar 16, 2026
  26. Explaining Time-Series Forecasts with Exact Shapley Values (ahead::dynrmf with external regressors applied to scenarios) Mar 8, 2026
  27. My Presentation at Risk 2026: Lightweight Transfer Learning for Financial Forecasting Mar 1, 2026
  28. nnetsauce with and without jax for GPU acceleration Feb 23, 2026
  29. Understanding Boosted Configuration Networks (combined neural networks and boosting): An Intuitive Guide Through Their Hyperparameters Feb 16, 2026
  30. R version of Python package survivalist, for model-agnostic survival analysis Feb 9, 2026
  31. Presenting Lightweight Transfer Learning for Financial Forecasting (Risk 2026) Feb 4, 2026
  32. Option pricing using time series models as market price of risk Feb 1, 2026
  33. Enhancing Time Series Forecasting (ahead::ridge2f) with Attention-Based Context Vectors (ahead::contextridge2f) Jan 31, 2026
  34. Overfitting and scaling (on GPU T4) tests on nnetsauce.CustomRegressor Jan 29, 2026
  35. Beyond Cross-validation: Hyperparameter Optimization via Generalization Gap Modeling Jan 25, 2026
  36. GPopt for Machine Learning (hyperparameters' tuning) Jan 21, 2026
  37. rtopy: an R to Python bridge -- novelties Jan 8, 2026
  38. Python examples for 'Beyond Nelson-Siegel and splines: A model- agnostic Machine Learning framework for discount curve calibration, interpolation and extrapolation' Jan 3, 2026
  39. Forecasting benchmark: Dynrmf (a new serious competitor in town) vs Theta Method on M-Competitions and Tourism competitition Jan 1, 2026
  40. Finally figured out a way to port python packages to R using uv and reticulate: example with nnetsauce Dec 17, 2025
  41. Overfitting Random Fourier Features: Universal Approximation Property Dec 13, 2025
  42. Counterfactual Scenario Analysis with ahead::ridge2f Dec 11, 2025
  43. Zero-Shot Probabilistic Time Series Forecasting with TabPFN 2.5 and nnetsauce Dec 10, 2025
  44. ARIMA Pricing: Semi-Parametric Market price of risk for Risk-Neutral Pricing (code + preprint) Dec 7, 2025
  45. Analyzing Paper Reviews with LLMs: I Used ChatGPT, DeepSeek, Qwen, Mistral, Gemini, and Claude (and you should too + publish the analysis) Dec 3, 2025
  46. tisthemachinelearner: New Workflow with uv for R Integration of scikit-learn Dec 1, 2025
  47. (ICYMI) RPweave: Unified R + Python + LaTeX System using uv Nov 21, 2025
  48. unifiedml: A Unified Machine Learning Interface for R, is now on CRAN + Discussion about AI replacing humans Nov 16, 2025
  49. Context-aware Theta forecasting Method: Extending Classical Time Series Forecasting with Machine Learning Nov 13, 2025
  50. unifiedml in R: A Unified Machine Learning Interface Nov 5, 2025
  51. Deterministic Shift Adjustment in Arbitrage-Free Pricing (historical to risk-neutral short rates) Oct 28, 2025
  52. New instantaneous short rates models with their deterministic shift adjustment, for historical and risk-neutral simulation Oct 27, 2025
  53. RPweave: Unified R + Python + LaTeX System using uv Oct 19, 2025
  54. GAN-like Synthetic Data Generation Examples (on univariate, multivariate distributions, digits recognition, Fashion-MNIST, stock returns, and Olivetti faces) with DistroSimulator Oct 19, 2025
  55. R port of llama2.c Oct 9, 2025
  56. Native uncertainty quantification for time series with NGBoost Oct 8, 2025
  57. NGBoost (Natural Gradient Boosting) for Regression, Classification, Time Series forecasting and Reserving Oct 6, 2025
  58. Real-time pricing with a pretrained probabilistic stock return model Oct 1, 2025
  59. Combining any model with GARCH(1,1) for probabilistic stock forecasting Sep 23, 2025
  60. Generating Synthetic Data with R-vine Copulas using esgtoolkit in R Sep 21, 2025
  61. Reimagining Equity Solvency Capital Requirement Approximation (one of my Master's Thesis subjects): From Bilinear Interpolation to Probabilistic Machine Learning Sep 16, 2025
  62. Transfer Learning using ahead::ridge2f on synthetic stocks returns Pt.2: synthetic data generation Sep 9, 2025
  63. Transfer Learning using ahead::ridge2f on synthetic stocks returns Sep 8, 2025
  64. I'm supposed to present 'Conformal Predictive Simulations for Univariate Time Series' at COPA CONFERENCE 2025 in London... Sep 4, 2025
  65. external regressors in ahead::dynrmf's interface for Machine learning forecasting Sep 1, 2025
  66. Another interesting decision, now for 'Beyond Nelson-Siegel and splines: A model-agnostic Machine Learning framework for discount curve calibration, interpolation and extrapolation' Aug 20, 2025
  67. Boosting any randomized based learner for regression, classification and univariate/multivariate time series forcasting Jul 26, 2025
  68. New nnetsauce version with CustomBackPropRegressor (CustomRegressor with Backpropagation) and ElasticNet2Regressor (Ridge2 with ElasticNet regularization) Jul 15, 2025
  69. mlsauce (home to a model-agnostic gradient boosting algorithm) can now be installed from PyPI. Jul 10, 2025
  70. A user-friendly graphical interface to techtonique dot net's API (will eventually contain graphics). Jul 8, 2025
  71. Calling =TECHTO_MLCLASSIFICATION for Machine Learning supervised CLASSIFICATION in Excel is just a matter of copying and pasting Jul 7, 2025
  72. Calling =TECHTO_MLREGRESSION for Machine Learning supervised regression in Excel is just a matter of copying and pasting Jul 6, 2025
  73. Calling =TECHTO_RESERVING and =TECHTO_MLRESERVING for claims triangle reserving in Excel is just a matter of copying and pasting Jul 5, 2025
  74. Calling =TECHTO_SURVIVAL for Survival Analysis in Excel is just a matter of copying and pasting Jul 4, 2025
  75. Calling =TECHTO_SIMULATION for Stochastic Simulation in Excel is just a matter of copying and pasting Jul 3, 2025
  76. Calling =TECHTO_FORECAST for forecasting in Excel is just a matter of copying and pasting Jul 2, 2025
  77. Random Vector Functional Link (RVFL) artificial neural network with 2 regularization parameters successfully used for forecasting/synthetic simulation in professional settings: Extensions (including Bayesian) Jul 1, 2025
  78. R version of 'Backpropagating quasi-randomized neural networks' Jun 24, 2025
  79. Backpropagating quasi-randomized neural networks Jun 23, 2025
  80. Beyond ARMA-GARCH: leveraging any statistical model for volatility forecasting Jun 21, 2025
  81. Stacked generalization (Machine Learning model stacking) + conformal prediction for forecasting with ahead::mlf Jun 18, 2025
  82. An Overfitting dilemma: XGBoost Default Hyperparameters vs GenericBooster + LinearRegression Default Hyperparameters Jun 14, 2025
  83. Programming language-agnostic reserving using RidgeCV, LightGBM, XGBoost, and ExtraTrees Machine Learning models Jun 13, 2025
  84. Free R, Python and SQL editors in techtonique dot net Jun 9, 2025
  85. Beyond Nelson-Siegel and splines: A model-agnostic Machine Learning framework for discount curve calibration, interpolation and extrapolation Jun 7, 2025
  86. scikit-learn, glmnet, xgboost, lightgbm, pytorch, keras, nnetsauce in probabilistic Machine Learning (for longitudinal data) Reserving (work in progress) Jun 6, 2025
  87. R version of Probabilistic Machine Learning (for longitudinal data) Reserving (work in progress) Jun 5, 2025
  88. Probabilistic Machine Learning (for longitudinal data) Reserving (work in progress) Jun 4, 2025
  89. Python version of Beyond ARMA-GARCH: leveraging model-agnostic Quasi-Randomized networks and conformal prediction for nonparametric probabilistic stock forecasting (ML-ARCH) Jun 3, 2025
  90. Beyond ARMA-GARCH: leveraging model-agnostic Machine Learning and conformal prediction for nonparametric probabilistic stock forecasting (ML-ARCH) Jun 2, 2025
  91. Permutations and SHAPley values for feature importance in techtonique dot net's API (with R + Python + the command line) Jun 1, 2025
  92. Which patient is going to survive longer? Another guide to using techtonique dot net's API (with R + Python + the command line) for survival analysis May 31, 2025
  93. A Guide to Using techtonique.net's API and rush for simulating and plotting Stochastic Scenarios May 30, 2025
  94. Simulating Stochastic Scenarios with Diffusion Models: A Guide to Using techtonique.net's API for the purpose May 29, 2025
  95. Will my apartment in 5th avenue be overpriced or not? Harnessing the power of www.techtonique.net (+ xgboost, lightgbm, catboost) to find out May 28, 2025
  96. How long must I wait until something happens: A Comprehensive Guide to Survival Analysis via an API May 27, 2025
  97. Harnessing the Power of techtonique.net: A Comprehensive Guide to Machine Learning Classification via an API May 26, 2025
  98. Quantile regression with any regressor -- Examples with RandomForestRegressor, RidgeCV, KNeighborsRegressor May 20, 2025
  99. Survival stacking: survival analysis translated as supervised classification in R and Python May 5, 2025
  100. 'Bayesian' optimization of hyperparameters in a R machine learning model using the bayesianrvfl package Apr 25, 2025
  101. A lightweight interface to scikit-learn in R: Bayesian and Conformal prediction Apr 21, 2025
  102. A lightweight interface to scikit-learn in R Pt.2: probabilistic time series forecasting in conjunction with ahead::dynrmf Apr 20, 2025
  103. Extending the Theta forecasting method to GLMs, GAMs, GLMBOOST and attention: benchmarking on Tourism, M1, M3 and M4 competition data sets (28000 series) Apr 14, 2025
  104. Extending the Theta forecasting method to GLMs and attention Apr 8, 2025
  105. Nonlinear conformalized Generalized Linear Models (GLMs) with R package 'rvfl' (and other models) Mar 31, 2025
  106. Probabilistic Time Series Forecasting (predictive simulations) in Microsoft Excel using Python, xlwings lite and www.techtonique.net Mar 28, 2025
  107. Conformalize (improved prediction intervals and simulations) any R Machine Learning model with misc::conformalize Mar 25, 2025
  108. My poster for the 18th FINANCIAL RISKS INTERNATIONAL FORUM by Institut Louis Bachelier/Fondation du Risque/Europlace Institute of Finance Mar 19, 2025
  109. Interpretable probabilistic kernel ridge regression using Matérn 3/2 kernels Mar 16, 2025
  110. (News from) Probabilistic Forecasting of univariate and multivariate Time Series using Quasi-Randomized Neural Networks (Ridge2) and Conformal Prediction Mar 9, 2025
  111. Word-Online: re-creating Karpathy's char-RNN (with supervised linear online learning of word embeddings) for text completion Mar 8, 2025
  112. CRAN-like repository for most recent releases of Techtonique's R packages Mar 2, 2025
  113. Presenting 'Online Probabilistic Estimation of Carbon Beta and Carbon Shapley Values for Financial and Climate Risk' at Institut Louis Bachelier Feb 27, 2025
  114. Web app with DeepSeek R1 and Hugging Face API for chatting Feb 23, 2025
  115. tisthemachinelearner: A Lightweight interface to scikit-learn with 2 classes, Classifier and Regressor (in Python and R) Feb 17, 2025
  116. R version of survivalist: Probabilistic model-agnostic survival analysis using scikit-learn, xgboost, lightgbm (and conformal prediction) Feb 12, 2025
  117. Model-agnostic global Survival Prediction of Patients with Myeloid Leukemia in QRT/Gustave Roussy Challenge (challengedata.ens.fr): Python's survivalist Quickstart Feb 10, 2025
  118. A simple test of the martingale hypothesis in esgtoolkit Feb 3, 2025
  119. Command Line Interface (CLI) for techtonique.net's API Jan 31, 2025
  120. Gradient-Boosting and Boostrap aggregating anything (alert: high performance): Part5, easier install and Rust backend Jan 27, 2025
  121. Just got a paper on conformal prediction REJECTED by International Journal of Forecasting despite evidence on 30,000 time series (and more). What's going on? Part2: 1311 time series from the Tourism competition Jan 20, 2025
  122. Techtonique is released! (with a tutorial in various programming languages and formats) Jan 14, 2025
  123. Univariate and Multivariate Probabilistic Forecasting with nnetsauce and TabPFN Jan 14, 2025
  124. Just got a paper on conformal prediction REJECTED by International Journal of Forecasting despite evidence on 30,000 time series (and more). What's going on? Jan 5, 2025
  125. Python and Interactive dashboard version of Stock price forecasting with Deep Learning: throwing power at the problem (and why it won't make you rich) Dec 31, 2024
  126. Stock price forecasting with Deep Learning: throwing power at the problem (and why it won't make you rich) Dec 29, 2024
  127. No-code Machine Learning Cross-validation and Interpretability in techtonique.net Dec 23, 2024
  128. survivalist: Probabilistic model-agnostic survival analysis using scikit-learn, glmnet, xgboost, lightgbm, pytorch, keras, nnetsauce and mlsauce Dec 15, 2024
  129. Model-agnostic 'Bayesian' optimization (for hyperparameter tuning) using conformalized surrogates in GPopt Dec 9, 2024
  130. You can beat Forecasting LLMs (Large Language Models a.k.a foundation models) with nnetsauce.MTS Pt.2: Generic Gradient Boosting Dec 1, 2024
  131. You can beat Forecasting LLMs (Large Language Models a.k.a foundation models) with nnetsauce.MTS Nov 24, 2024
  132. Unified interface and conformal prediction (calibrated prediction intervals) for R package forecast (and 'affiliates') Nov 23, 2024
  133. GLMNet in Python: Generalized Linear Models Nov 18, 2024
  134. Gradient-Boosting anything (alert: high performance): Part4, Time series forecasting Nov 10, 2024
  135. Predictive scenarios simulation in R, Python and Excel using Techtonique API Nov 3, 2024
  136. Chat with your tabular data in www.techtonique.net Oct 30, 2024
  137. Gradient-Boosting anything (alert: high performance): Part3, Histogram-based boosting Oct 28, 2024
  138. R editor and SQL console (in addition to Python editors) in www.techtonique.net Oct 21, 2024
  139. R and Python consoles + JupyterLite in www.techtonique.net Oct 15, 2024
  140. Gradient-Boosting anything (alert: high performance): Part2, R version Oct 14, 2024
  141. Gradient-Boosting anything (alert: high performance) Oct 6, 2024
  142. Benchmarking 30 statistical/Machine Learning models on the VN1 Forecasting -- Accuracy challenge Oct 4, 2024
  143. Automated random variable distribution inference using Kullback-Leibler divergence and simulating best-fitting distribution Oct 2, 2024
  144. Forecasting in Excel using Techtonique's Machine Learning APIs under the hood Sep 30, 2024
  145. Techtonique web app for data-driven decisions using Mathematics, Statistics, Machine Learning, and Data Visualization Sep 25, 2024
  146. Parallel for loops (Map or Reduce) + New versions of nnetsauce and ahead Sep 16, 2024
  147. Adaptive (online/streaming) learning with uncertainty quantification using Polyak averaging in learningmachine Sep 10, 2024
  148. New versions of nnetsauce and ahead Sep 9, 2024
  149. Prediction sets and prediction intervals for conformalized Auto XGBoost, Auto LightGBM, Auto CatBoost, Auto GradientBoosting Sep 2, 2024
  150. Quick/automated R package development workflow (assuming you're using macOS or Linux) Part2 Aug 30, 2024
  151. R package development workflow (assuming you're using macOS or Linux) Aug 27, 2024
  152. A new method for deriving a nonparametric confidence interval for the mean Aug 26, 2024
  153. Conformalized adaptive (online/streaming) learning using learningmachine in Python and R Aug 19, 2024
  154. Bayesian (nonlinear) adaptive learning Aug 12, 2024
  155. Auto XGBoost, Auto LightGBM, Auto CatBoost, Auto GradientBoosting Aug 5, 2024
  156. Copulas for uncertainty quantification in time series forecasting Jul 28, 2024
  157. Forecasting uncertainty: sequential split conformal prediction + Block bootstrap (web app) Jul 22, 2024
  158. learningmachine for Python (new version) Jul 15, 2024
  159. learningmachine v2.0.0: Machine Learning with explanations and uncertainty quantification Jul 8, 2024
  160. My presentation at ISF 2024 conference (slides with nnetsauce probabilistic forecasting news) Jul 3, 2024
  161. 10 uncertainty quantification methods in nnetsauce forecasting Jul 1, 2024
  162. Forecasting with XGBoost embedded in Quasi-Randomized Neural Networks Jun 24, 2024
  163. Forecasting Monthly Airline Passenger Numbers with Quasi-Randomized Neural Networks Jun 17, 2024
  164. Automated hyperparameter tuning using any conformalized surrogate Jun 9, 2024
  165. Recognizing handwritten digits with Ridge2Classifier Jun 3, 2024
  166. Forecasting the Economy May 27, 2024
  167. A detailed introduction to Deep Quasi-Randomized 'neural' networks May 19, 2024
  168. Probability of receiving a loan; using learningmachine May 12, 2024
  169. mlsauce's `v0.18.2`: various examples and benchmarks with dimension reduction May 6, 2024
  170. mlsauce's `v0.17.0`: boosting with Elastic Net, polynomials and heterogeneity in explanatory variables Apr 29, 2024
  171. mlsauce's `v0.13.0`: taking into account inputs heterogeneity through clustering Apr 21, 2024
  172. mlsauce's `v0.12.0`: prediction intervals for LSBoostRegressor Apr 15, 2024
  173. Conformalized predictive simulations for univariate time series on more than 250 data sets Apr 7, 2024
  174. learningmachine v1.1.2: for Python Apr 1, 2024
  175. learningmachine v1.0.0: prediction intervals around the probability of the event 'a tumor being malignant' Mar 25, 2024
  176. Bayesian inference and conformal prediction (prediction intervals) in nnetsauce v0.18.1 Mar 18, 2024
  177. Multiple examples of Machine Learning forecasting with ahead Mar 11, 2024
  178. rtopy (v0.1.1): calling R functions in Python Mar 4, 2024
  179. ahead forecasting (v0.10.0): fast time series model calibration and Python plots Feb 26, 2024
  180. A plethora of datasets at your fingertips Part3: how many times do couples cheat on each other? Feb 19, 2024
  181. nnetsauce's introduction as of 2024-02-11 (new version 0.17.0) Feb 11, 2024
  182. Tuning Machine Learning models with GPopt's new version Part 2 Feb 5, 2024
  183. Tuning Machine Learning models with GPopt's new version Jan 29, 2024
  184. Subsampling continuous and discrete response variables Jan 22, 2024
  185. DeepMTS, a Deep Learning Model for Multivariate Time Series Jan 15, 2024
  186. A classifier that's very accurate (and deep) Pt.2: there are > 90 classifiers in nnetsauce Jan 8, 2024
  187. learningmachine: prediction intervals for conformalized Kernel ridge regression and Random Forest Jan 1, 2024
  188. A plethora of datasets at your fingertips Part2: how many times do couples cheat on each other? Descriptive analytics, interpretability and prediction intervals using conformal prediction Dec 25, 2023
  189. Diffusion models in Python with esgtoolkit (Part2) Dec 18, 2023
  190. Diffusion models in Python with esgtoolkit Dec 11, 2023
  191. Julia packaging at the command line Dec 4, 2023
  192. Quasi-randomized nnetworks in Julia, Python and R Nov 27, 2023
  193. A plethora of datasets at your fingertips Nov 20, 2023
  194. A classifier that's very accurate (and deep) Nov 12, 2023
  195. mlsauce version 0.8.10: Statistical/Machine Learning with Python and R Nov 5, 2023
  196. AutoML in nnetsauce (randomized and quasi-randomized nnetworks) Pt.2: multivariate time series forecasting Oct 29, 2023
  197. AutoML in nnetsauce (randomized and quasi-randomized nnetworks) Oct 22, 2023
  198. Version v0.14.0 of nnetsauce for R and Python Oct 16, 2023
  199. A diffusion model: G2++ Oct 9, 2023
  200. Diffusion models in ESGtoolkit + announcements Oct 2, 2023
  201. An infinity of time series forecasting models in nnetsauce (Part 2 with uncertainty quantification) Sep 25, 2023
  202. (News from) forecasting in Python with ahead (progress bars and plots) Sep 18, 2023
  203. Forecasting in Python with ahead Sep 11, 2023
  204. Risk-neutralize simulations Sep 4, 2023
  205. Comparing cross-validation results using crossval_ml and boxplots Aug 27, 2023
  206. Reminder Apr 30, 2023
  207. Did you ask ChatGPT about who you are? Apr 16, 2023
  208. A new version of nnetsauce (randomized and quasi-randomized 'neural' networks) Apr 2, 2023
  209. Simple interfaces to the forecasting API Nov 23, 2022
  210. A web application for forecasting in Python, R, Ruby, C#, JavaScript, PHP, Go, Rust, Java, MATLAB, etc. Nov 2, 2022
  211. Prediction intervals (not only) for Boosted Configuration Networks in Python Oct 5, 2022
  212. Boosted Configuration (neural) Networks Pt. 2 Sep 3, 2022
  213. Boosted Configuration (_neural_) Networks for classification Jul 21, 2022
  214. A Machine Learning workflow using Techtonique Jun 6, 2022
  215. Super Mario Bros © in the browser using PyScript May 8, 2022
  216. News from ESGtoolkit, ycinterextra, and nnetsauce Apr 4, 2022
  217. Explaining a Keras _neural_ network predictions with the-teller Mar 11, 2022
  218. New version of nnetsauce -- various quasi-randomized networks Feb 12, 2022
  219. A dashboard illustrating bivariate time series forecasting with `ahead` Jan 14, 2022
  220. Hundreds of Statistical/Machine Learning models for univariate time series, using ahead, ranger, xgboost, and caret Dec 20, 2021
  221. Forecasting with `ahead` (Python version) Dec 13, 2021
  222. Tuning and interpreting LSBoost Nov 15, 2021
  223. Time series cross-validation using `crossvalidation` (Part 2) Nov 7, 2021
  224. Fast and scalable forecasting with ahead::ridge2f Oct 31, 2021
  225. Automatic Forecasting with `ahead::dynrmf` and Ridge regression Oct 22, 2021
  226. Forecasting with `ahead` Oct 15, 2021
  227. Classification using linear regression Sep 26, 2021
  228. `crossvalidation` and random search for calibrating support vector machines Aug 6, 2021
  229. parallel grid search cross-validation using `crossvalidation` Jul 31, 2021
  230. `crossvalidation` on R-universe, plus a classification example Jul 23, 2021
  231. Documentation and source code for GPopt, a package for Bayesian optimization Jul 2, 2021
  232. Hyperparameters tuning with GPopt Jun 11, 2021
  233. A forecasting tool (API) with examples in curl, R, Python May 28, 2021
  234. Bayesian Optimization with GPopt Part 2 (save and resume) Apr 30, 2021
  235. Bayesian Optimization with GPopt Apr 16, 2021
  236. Compatibility of nnetsauce and mlsauce with scikit-learn Mar 26, 2021
  237. Explaining xgboost predictions with the teller Mar 12, 2021
  238. An infinity of time series models in nnetsauce Mar 6, 2021
  239. New activation functions in mlsauce's LSBoost Feb 12, 2021
  240. 2020 recap, Gradient Boosting, Generalized Linear Models, AdaOpt with nnetsauce and mlsauce Dec 29, 2020
  241. A deeper learning architecture in nnetsauce Dec 18, 2020
  242. Classify penguins with nnetsauce's MultitaskClassifier Dec 11, 2020
  243. Bayesian forecasting for uni/multivariate time series Dec 4, 2020
  244. Generalized nonlinear models in nnetsauce Nov 28, 2020
  245. Boosting nonlinear penalized least squares Nov 21, 2020
  246. Statistical/Machine Learning explainability using Kernel Ridge Regression surrogates Nov 6, 2020
  247. NEWS Oct 30, 2020
  248. A glimpse into my PhD journey Oct 23, 2020
  249. Submitting R package to CRAN Oct 16, 2020
  250. Simulation of dependent variables in ESGtoolkit Oct 9, 2020
  251. Forecasting lung disease progression Oct 2, 2020
  252. New nnetsauce Sep 25, 2020
  253. Technical documentation Sep 18, 2020
  254. A new version of nnetsauce, and a new Techtonique website Sep 11, 2020
  255. Back next week, and a few announcements Sep 4, 2020
  256. Explainable 'AI' using Gradient Boosted randomized networks Pt2 (the Lasso) Jul 31, 2020
  257. LSBoost: Explainable 'AI' using Gradient Boosted randomized networks (with examples in R and Python) Jul 24, 2020
  258. nnetsauce version 0.5.0, randomized neural networks on GPU Jul 17, 2020
  259. Maximizing your tip as a waiter (Part 2) Jul 10, 2020
  260. New version of mlsauce, with Gradient Boosted randomized networks and stump decision trees Jul 3, 2020
  261. Announcements Jun 26, 2020
  262. Parallel AdaOpt classification Jun 19, 2020
  263. Comments section and other news Jun 12, 2020
  264. Maximizing your tip as a waiter Jun 5, 2020
  265. AdaOpt classification on MNIST handwritten digits (without preprocessing) May 29, 2020
  266. AdaOpt (a probabilistic classifier based on a mix of multivariable optimization and nearest neighbors) for R May 22, 2020
  267. AdaOpt May 15, 2020
  268. Custom errors for cross-validation using crossval::crossval_ml May 8, 2020
  269. Documentation+Pypi for the `teller`, a model-agnostic tool for Machine Learning explainability May 1, 2020
  270. Encoding your categorical variables based on the response variable and correlations Apr 24, 2020
  271. Linear model, xgboost and randomForest cross-validation using crossval::crossval_ml Apr 17, 2020
  272. Grid search cross-validation using crossval Apr 10, 2020
  273. Documentation for the querier, a query language for Data Frames Apr 3, 2020
  274. Time series cross-validation using crossval Mar 27, 2020
  275. On model specification, identification, degrees of freedom and regularization Mar 20, 2020
  276. Import data into the querier (now on Pypi), a query language for Data Frames Mar 13, 2020
  277. R notebooks for nnetsauce Mar 6, 2020
  278. Version 0.4.0 of nnetsauce, with fruits and breast cancer classification Feb 28, 2020
  279. Create a specific feed in your Jekyll blog Feb 21, 2020
  280. Git/Github for contributing to package development Feb 14, 2020
  281. Feedback forms for contributing Feb 7, 2020
  282. nnetsauce for R Jan 31, 2020
  283. A new version of nnetsauce (v0.3.1) Jan 24, 2020
  284. ESGtoolkit, a tool for Monte Carlo simulation (v0.2.0) Jan 17, 2020
  285. Search bar, new year 2020 Jan 10, 2020
  286. 2019 Recap, the nnetsauce, the teller and the querier Dec 20, 2019
  287. Understanding model interactions with the `teller` Dec 13, 2019
  288. Using the `teller` on a classifier Dec 6, 2019
  289. Benchmarking the querier's verbs Nov 29, 2019
  290. Composing the querier's verbs for data wrangling Nov 22, 2019
  291. Comparing and explaining model predictions with the teller Nov 15, 2019
  292. Tests for the significance of marginal effects in the teller Nov 8, 2019
  293. Introducing the teller Nov 1, 2019
  294. Introducing the querier Oct 25, 2019
  295. Prediction intervals for nnetsauce models Oct 18, 2019
  296. Using R in Python for statistical learning/data science Oct 11, 2019
  297. Model calibration with `crossval` Oct 4, 2019
  298. Bagging in the nnetsauce Sep 25, 2019
  299. Adaboost learning with nnetsauce Sep 18, 2019
  300. Change in blog's presentation Sep 4, 2019
  301. nnetsauce on Pypi Jun 5, 2019
  302. More nnetsauce (examples of use) May 9, 2019
  303. nnetsauce Mar 13, 2019
  304. crossval Mar 13, 2019
  305. test Mar 10, 2019

Categories | Top

Forecasting

  1. ARIMA Pricing: Semi-Parametric Market price of risk for Risk-Neutral Pricing (code + preprint)
  2. My poster for the 18th FINANCIAL RISKS INTERNATIONAL FORUM by Institut Louis Bachelier/Fondation du Risque/Europlace Institute of Finance
  3. Presenting 'Online Probabilistic Estimation of Carbon Beta and Carbon Shapley Values for Financial and Climate Risk' at Institut Louis Bachelier
  4. Just got a paper on conformal prediction REJECTED by International Journal of Forecasting despite evidence on 30,000 time series (and more). What's going on? Part2: 1311 time series from the Tourism competition
  5. Techtonique is released! (with a tutorial in various programming languages and formats)
  6. Just got a paper on conformal prediction REJECTED by International Journal of Forecasting despite evidence on 30,000 time series (and more). What's going on?
  7. You can beat Forecasting LLMs (Large Language Models a.k.a foundation models) with nnetsauce.MTS
  8. My presentation at ISF 2024 conference (slides with nnetsauce probabilistic forecasting news)
  9. 10 uncertainty quantification methods in nnetsauce forecasting
  10. Forecasting with XGBoost embedded in Quasi-Randomized Neural Networks
  11. Forecasting Monthly Airline Passenger Numbers with Quasi-Randomized Neural Networks
  12. DeepMTS, a Deep Learning Model for Multivariate Time Series
  13. Version v0.14.0 of nnetsauce for R and Python
  14. An infinity of time series forecasting models in nnetsauce (Part 2 with uncertainty quantification)
  15. (News from) forecasting in Python with ahead (progress bars and plots)
  16. Forecasting in Python with ahead
  17. Simple interfaces to the forecasting API
  18. A web application for forecasting in Python, R, Ruby, C#, JavaScript, PHP, Go, Rust, Java, MATLAB, etc.
  19. A dashboard illustrating bivariate time series forecasting with `ahead`
  20. Hundreds of Statistical/Machine Learning models for univariate time series, using ahead, ranger, xgboost, and caret

Misc

  1. Analyzing Paper Reviews with LLMs: I Used ChatGPT, DeepSeek, Qwen, Mistral, Gemini, and Claude (and you should too + publish the analysis)
  2. A plethora of datasets at your fingertips Part2: how many times do couples cheat on each other? Descriptive analytics, interpretability and prediction intervals using conformal prediction
  3. Julia packaging at the command line
  4. A plethora of datasets at your fingertips
  5. Risk-neutralize simulations
  6. Comparing cross-validation results using crossval_ml and boxplots
  7. Reminder
  8. Did you ask ChatGPT about who you are?
  9. A web application for forecasting in Python, R, Ruby, C#, JavaScript, PHP, Go, Rust, Java, MATLAB, etc.
  10. Boosted Configuration (_neural_) Networks for classification
  11. Super Mario Bros © in the browser using PyScript
  12. News from ESGtoolkit, ycinterextra, and nnetsauce
  13. Time series cross-validation using `crossvalidation` (Part 2)
  14. Fast and scalable forecasting with ahead::ridge2f
  15. Automatic Forecasting with `ahead::dynrmf` and Ridge regression
  16. Forecasting with `ahead`
  17. Documentation and source code for GPopt, a package for Bayesian optimization
  18. Hyperparameters tuning with GPopt
  19. A forecasting tool (API) with examples in curl, R, Python
  20. Bayesian Optimization with GPopt Part 2 (save and resume)
  21. Bayesian Optimization with GPopt
  22. 2020 recap, Gradient Boosting, Generalized Linear Models, AdaOpt with nnetsauce and mlsauce
  23. Statistical/Machine Learning explainability using Kernel Ridge Regression surrogates
  24. NEWS
  25. A glimpse into my PhD journey
  26. Forecasting lung disease progression
  27. New nnetsauce
  28. Technical documentation
  29. A new version of nnetsauce, and a new Techtonique website
  30. Back next week, and a few announcements
  31. Maximizing your tip as a waiter (Part 2)
  32. New version of mlsauce, with Gradient Boosted randomized networks and stump decision trees
  33. Announcements
  34. Comments section and other news
  35. Maximizing your tip as a waiter
  36. Custom errors for cross-validation using crossval::crossval_ml
  37. Encoding your categorical variables based on the response variable and correlations
  38. Linear model, xgboost and randomForest cross-validation using crossval::crossval_ml
  39. Grid search cross-validation using crossval
  40. Time series cross-validation using crossval
  41. On model specification, identification, degrees of freedom and regularization
  42. Create a specific feed in your Jekyll blog
  43. Git/Github for contributing to package development
  44. Feedback forms for contributing
  45. Change in blog's presentation
  46. test

Python

  1. 'PCARVFLSimulator': a GAN-like tabular data synthesizer built from PCA scores, a Random Vector Functional-Link network, and residuals bootstrapping
  2. Natively Interpretable Boosting
  3. Fast conformal prediction (no refitting) for some Machine Learning models via closed-form jackknife plus
  4. Techtonique dot net, the Machine Learning web API, is back online (but more like a passion project for now)
  5. Conformalized TabICL: Prediction Intervals for a State-Of-The-Art Tabular Foundation Model in Python and R
  6. Conformalized TabPFN: Prediction Intervals for a Pretrained Transformer for Tabular Data in Python and R
  7. Survival analysis with sklearn, glmnet, keras, pytorch, lightgbm, xgboost, nnetsauce, mlsauce Part 2
  8. Any Sklearn Regressor as a Survival Model — Does It Actually Work? Benchmarking vs Established Packages
  9. Conformal Optimization Beats Bayesian Optimization, Optuna and Random Search on 72 classification Datasets
  10. Techtonique dot net is down until further notice
  11. Python version of 'Option pricing using time series models as market price of risk Pt.3'
  12. nnetsauce with and without jax for GPU acceleration
  13. Understanding Boosted Configuration Networks (combined neural networks and boosting): An Intuitive Guide Through Their Hyperparameters
  14. R version of Python package survivalist, for model-agnostic survival analysis
  15. Overfitting and scaling (on GPU T4) tests on nnetsauce.CustomRegressor
  16. GPopt for Machine Learning (hyperparameters' tuning)
  17. rtopy: an R to Python bridge -- novelties
  18. Python examples for 'Beyond Nelson-Siegel and splines: A model- agnostic Machine Learning framework for discount curve calibration, interpolation and extrapolation'
  19. Finally figured out a way to port python packages to R using uv and reticulate: example with nnetsauce
  20. Overfitting Random Fourier Features: Universal Approximation Property
  21. Zero-Shot Probabilistic Time Series Forecasting with TabPFN 2.5 and nnetsauce
  22. Analyzing Paper Reviews with LLMs: I Used ChatGPT, DeepSeek, Qwen, Mistral, Gemini, and Claude (and you should too + publish the analysis)
  23. tisthemachinelearner: New Workflow with uv for R Integration of scikit-learn
  24. (ICYMI) RPweave: Unified R + Python + LaTeX System using uv
  25. New instantaneous short rates models with their deterministic shift adjustment, for historical and risk-neutral simulation
  26. RPweave: Unified R + Python + LaTeX System using uv
  27. GAN-like Synthetic Data Generation Examples (on univariate, multivariate distributions, digits recognition, Fashion-MNIST, stock returns, and Olivetti faces) with DistroSimulator
  28. Native uncertainty quantification for time series with NGBoost
  29. NGBoost (Natural Gradient Boosting) for Regression, Classification, Time Series forecasting and Reserving
  30. Real-time pricing with a pretrained probabilistic stock return model
  31. Reimagining Equity Solvency Capital Requirement Approximation (one of my Master's Thesis subjects): From Bilinear Interpolation to Probabilistic Machine Learning
  32. Transfer Learning using ahead::ridge2f on synthetic stocks returns Pt.2: synthetic data generation
  33. Transfer Learning using ahead::ridge2f on synthetic stocks returns
  34. I'm supposed to present 'Conformal Predictive Simulations for Univariate Time Series' at COPA CONFERENCE 2025 in London...
  35. Another interesting decision, now for 'Beyond Nelson-Siegel and splines: A model-agnostic Machine Learning framework for discount curve calibration, interpolation and extrapolation'
  36. Boosting any randomized based learner for regression, classification and univariate/multivariate time series forcasting
  37. New nnetsauce version with CustomBackPropRegressor (CustomRegressor with Backpropagation) and ElasticNet2Regressor (Ridge2 with ElasticNet regularization)
  38. mlsauce (home to a model-agnostic gradient boosting algorithm) can now be installed from PyPI.
  39. A user-friendly graphical interface to techtonique dot net's API (will eventually contain graphics).
  40. Calling =TECHTO_MLCLASSIFICATION for Machine Learning supervised CLASSIFICATION in Excel is just a matter of copying and pasting
  41. Calling =TECHTO_MLREGRESSION for Machine Learning supervised regression in Excel is just a matter of copying and pasting
  42. Calling =TECHTO_RESERVING and =TECHTO_MLRESERVING for claims triangle reserving in Excel is just a matter of copying and pasting
  43. Calling =TECHTO_SURVIVAL for Survival Analysis in Excel is just a matter of copying and pasting
  44. Calling =TECHTO_SIMULATION for Stochastic Simulation in Excel is just a matter of copying and pasting
  45. Calling =TECHTO_FORECAST for forecasting in Excel is just a matter of copying and pasting
  46. Random Vector Functional Link (RVFL) artificial neural network with 2 regularization parameters successfully used for forecasting/synthetic simulation in professional settings: Extensions (including Bayesian)
  47. Backpropagating quasi-randomized neural networks
  48. Beyond ARMA-GARCH: leveraging any statistical model for volatility forecasting
  49. An Overfitting dilemma: XGBoost Default Hyperparameters vs GenericBooster + LinearRegression Default Hyperparameters
  50. Free R, Python and SQL editors in techtonique dot net
  51. Beyond Nelson-Siegel and splines: A model-agnostic Machine Learning framework for discount curve calibration, interpolation and extrapolation
  52. scikit-learn, glmnet, xgboost, lightgbm, pytorch, keras, nnetsauce in probabilistic Machine Learning (for longitudinal data) Reserving (work in progress)
  53. Probabilistic Machine Learning (for longitudinal data) Reserving (work in progress)
  54. Python version of Beyond ARMA-GARCH: leveraging model-agnostic Quasi-Randomized networks and conformal prediction for nonparametric probabilistic stock forecasting (ML-ARCH)
  55. Permutations and SHAPley values for feature importance in techtonique dot net's API (with R + Python + the command line)
  56. Which patient is going to survive longer? Another guide to using techtonique dot net's API (with R + Python + the command line) for survival analysis
  57. A Guide to Using techtonique.net's API and rush for simulating and plotting Stochastic Scenarios
  58. Simulating Stochastic Scenarios with Diffusion Models: A Guide to Using techtonique.net's API for the purpose
  59. Will my apartment in 5th avenue be overpriced or not? Harnessing the power of www.techtonique.net (+ xgboost, lightgbm, catboost) to find out
  60. How long must I wait until something happens: A Comprehensive Guide to Survival Analysis via an API
  61. Harnessing the Power of techtonique.net: A Comprehensive Guide to Machine Learning Classification via an API
  62. Quantile regression with any regressor -- Examples with RandomForestRegressor, RidgeCV, KNeighborsRegressor
  63. Survival stacking: survival analysis translated as supervised classification in R and Python
  64. Extending the Theta forecasting method to GLMs and attention
  65. Probabilistic Time Series Forecasting (predictive simulations) in Microsoft Excel using Python, xlwings lite and www.techtonique.net
  66. My poster for the 18th FINANCIAL RISKS INTERNATIONAL FORUM by Institut Louis Bachelier/Fondation du Risque/Europlace Institute of Finance
  67. Word-Online: re-creating Karpathy's char-RNN (with supervised linear online learning of word embeddings) for text completion
  68. Presenting 'Online Probabilistic Estimation of Carbon Beta and Carbon Shapley Values for Financial and Climate Risk' at Institut Louis Bachelier
  69. Web app with DeepSeek R1 and Hugging Face API for chatting
  70. tisthemachinelearner: A Lightweight interface to scikit-learn with 2 classes, Classifier and Regressor (in Python and R)
  71. Model-agnostic global Survival Prediction of Patients with Myeloid Leukemia in QRT/Gustave Roussy Challenge (challengedata.ens.fr): Python's survivalist Quickstart
  72. Command Line Interface (CLI) for techtonique.net's API
  73. Gradient-Boosting and Boostrap aggregating anything (alert: high performance): Part5, easier install and Rust backend
  74. Just got a paper on conformal prediction REJECTED by International Journal of Forecasting despite evidence on 30,000 time series (and more). What's going on? Part2: 1311 time series from the Tourism competition
  75. Techtonique is released! (with a tutorial in various programming languages and formats)
  76. Univariate and Multivariate Probabilistic Forecasting with nnetsauce and TabPFN
  77. Just got a paper on conformal prediction REJECTED by International Journal of Forecasting despite evidence on 30,000 time series (and more). What's going on?
  78. Python and Interactive dashboard version of Stock price forecasting with Deep Learning: throwing power at the problem (and why it won't make you rich)
  79. No-code Machine Learning Cross-validation and Interpretability in techtonique.net
  80. survivalist: Probabilistic model-agnostic survival analysis using scikit-learn, glmnet, xgboost, lightgbm, pytorch, keras, nnetsauce and mlsauce
  81. Model-agnostic 'Bayesian' optimization (for hyperparameter tuning) using conformalized surrogates in GPopt
  82. You can beat Forecasting LLMs (Large Language Models a.k.a foundation models) with nnetsauce.MTS Pt.2: Generic Gradient Boosting
  83. You can beat Forecasting LLMs (Large Language Models a.k.a foundation models) with nnetsauce.MTS
  84. GLMNet in Python: Generalized Linear Models
  85. Gradient-Boosting anything (alert: high performance): Part4, Time series forecasting
  86. Predictive scenarios simulation in R, Python and Excel using Techtonique API
  87. Chat with your tabular data in www.techtonique.net
  88. Gradient-Boosting anything (alert: high performance): Part3, Histogram-based boosting
  89. R editor and SQL console (in addition to Python editors) in www.techtonique.net
  90. R and Python consoles + JupyterLite in www.techtonique.net
  91. Gradient-Boosting anything (alert: high performance)
  92. Benchmarking 30 statistical/Machine Learning models on the VN1 Forecasting -- Accuracy challenge
  93. Forecasting in Excel using Techtonique's Machine Learning APIs under the hood
  94. Techtonique web app for data-driven decisions using Mathematics, Statistics, Machine Learning, and Data Visualization
  95. Parallel for loops (Map or Reduce) + New versions of nnetsauce and ahead
  96. Adaptive (online/streaming) learning with uncertainty quantification using Polyak averaging in learningmachine
  97. New versions of nnetsauce and ahead
  98. Prediction sets and prediction intervals for conformalized Auto XGBoost, Auto LightGBM, Auto CatBoost, Auto GradientBoosting
  99. Conformalized adaptive (online/streaming) learning using learningmachine in Python and R
  100. Auto XGBoost, Auto LightGBM, Auto CatBoost, Auto GradientBoosting
  101. Copulas for uncertainty quantification in time series forecasting
  102. Forecasting uncertainty: sequential split conformal prediction + Block bootstrap (web app)
  103. learningmachine for Python (new version)
  104. My presentation at ISF 2024 conference (slides with nnetsauce probabilistic forecasting news)
  105. 10 uncertainty quantification methods in nnetsauce forecasting
  106. Forecasting with XGBoost embedded in Quasi-Randomized Neural Networks
  107. Forecasting Monthly Airline Passenger Numbers with Quasi-Randomized Neural Networks
  108. Automated hyperparameter tuning using any conformalized surrogate
  109. Recognizing handwritten digits with Ridge2Classifier
  110. A detailed introduction to Deep Quasi-Randomized 'neural' networks
  111. Probability of receiving a loan; using learningmachine
  112. mlsauce's `v0.18.2`: various examples and benchmarks with dimension reduction
  113. mlsauce's `v0.17.0`: boosting with Elastic Net, polynomials and heterogeneity in explanatory variables
  114. mlsauce's `v0.13.0`: taking into account inputs heterogeneity through clustering
  115. mlsauce's `v0.12.0`: prediction intervals for LSBoostRegressor
  116. learningmachine v1.1.2: for Python
  117. Bayesian inference and conformal prediction (prediction intervals) in nnetsauce v0.18.1
  118. rtopy (v0.1.1): calling R functions in Python
  119. ahead forecasting (v0.10.0): fast time series model calibration and Python plots
  120. A plethora of datasets at your fingertips Part3: how many times do couples cheat on each other?
  121. nnetsauce's introduction as of 2024-02-11 (new version 0.17.0)
  122. Tuning Machine Learning models with GPopt's new version Part 2
  123. Tuning Machine Learning models with GPopt's new version
  124. Subsampling continuous and discrete response variables
  125. DeepMTS, a Deep Learning Model for Multivariate Time Series
  126. A classifier that's very accurate (and deep) Pt.2: there are > 90 classifiers in nnetsauce
  127. A plethora of datasets at your fingertips Part2: how many times do couples cheat on each other? Descriptive analytics, interpretability and prediction intervals using conformal prediction
  128. Diffusion models in Python with esgtoolkit (Part2)
  129. Diffusion models in Python with esgtoolkit
  130. Quasi-randomized nnetworks in Julia, Python and R
  131. A plethora of datasets at your fingertips
  132. A classifier that's very accurate (and deep)
  133. mlsauce version 0.8.10: Statistical/Machine Learning with Python and R
  134. AutoML in nnetsauce (randomized and quasi-randomized nnetworks) Pt.2: multivariate time series forecasting
  135. AutoML in nnetsauce (randomized and quasi-randomized nnetworks)
  136. Version v0.14.0 of nnetsauce for R and Python
  137. An infinity of time series forecasting models in nnetsauce (Part 2 with uncertainty quantification)
  138. (News from) forecasting in Python with ahead (progress bars and plots)
  139. Forecasting in Python with ahead
  140. Did you ask ChatGPT about who you are?
  141. A new version of nnetsauce (randomized and quasi-randomized 'neural' networks)
  142. Simple interfaces to the forecasting API
  143. A web application for forecasting in Python, R, Ruby, C#, JavaScript, PHP, Go, Rust, Java, MATLAB, etc.
  144. Prediction intervals (not only) for Boosted Configuration Networks in Python
  145. A Machine Learning workflow using Techtonique
  146. Super Mario Bros © in the browser using PyScript
  147. News from ESGtoolkit, ycinterextra, and nnetsauce
  148. Explaining a Keras _neural_ network predictions with the-teller
  149. New version of nnetsauce -- various quasi-randomized networks
  150. A dashboard illustrating bivariate time series forecasting with `ahead`
  151. Forecasting with `ahead` (Python version)
  152. Tuning and interpreting LSBoost
  153. Classification using linear regression
  154. Documentation and source code for GPopt, a package for Bayesian optimization
  155. Hyperparameters tuning with GPopt
  156. A forecasting tool (API) with examples in curl, R, Python
  157. Bayesian Optimization with GPopt Part 2 (save and resume)
  158. Bayesian Optimization with GPopt
  159. Compatibility of nnetsauce and mlsauce with scikit-learn
  160. Explaining xgboost predictions with the teller
  161. An infinity of time series models in nnetsauce
  162. 2020 recap, Gradient Boosting, Generalized Linear Models, AdaOpt with nnetsauce and mlsauce
  163. A deeper learning architecture in nnetsauce
  164. Generalized nonlinear models in nnetsauce
  165. Boosting nonlinear penalized least squares
  166. Technical documentation
  167. A new version of nnetsauce, and a new Techtonique website
  168. Back next week, and a few announcements
  169. Explainable 'AI' using Gradient Boosted randomized networks Pt2 (the Lasso)
  170. LSBoost: Explainable 'AI' using Gradient Boosted randomized networks (with examples in R and Python)
  171. nnetsauce version 0.5.0, randomized neural networks on GPU
  172. Maximizing your tip as a waiter (Part 2)
  173. Parallel AdaOpt classification
  174. Maximizing your tip as a waiter
  175. AdaOpt classification on MNIST handwritten digits (without preprocessing)
  176. AdaOpt
  177. Documentation+Pypi for the `teller`, a model-agnostic tool for Machine Learning explainability
  178. Encoding your categorical variables based on the response variable and correlations
  179. Documentation for the querier, a query language for Data Frames
  180. Import data into the querier (now on Pypi), a query language for Data Frames
  181. Version 0.4.0 of nnetsauce, with fruits and breast cancer classification
  182. A new version of nnetsauce (v0.3.1)
  183. Using R in Python for statistical learning/data science
  184. nnetsauce on Pypi

QuasiRandomizedNN

  1. Gradient-Boosting anything (alert: high performance): Part4, Time series forecasting
  2. Gradient-Boosting anything (alert: high performance): Part3, Histogram-based boosting
  3. My presentation at ISF 2024 conference (slides with nnetsauce probabilistic forecasting news)
  4. 10 uncertainty quantification methods in nnetsauce forecasting
  5. Forecasting with XGBoost embedded in Quasi-Randomized Neural Networks
  6. Forecasting Monthly Airline Passenger Numbers with Quasi-Randomized Neural Networks
  7. Automated hyperparameter tuning using any conformalized surrogate
  8. Recognizing handwritten digits with Ridge2Classifier
  9. A plethora of datasets at your fingertips Part3: how many times do couples cheat on each other?
  10. nnetsauce's introduction as of 2024-02-11 (new version 0.17.0)
  11. DeepMTS, a Deep Learning Model for Multivariate Time Series
  12. A classifier that's very accurate (and deep) Pt.2: there are > 90 classifiers in nnetsauce
  13. Quasi-randomized nnetworks in Julia, Python and R
  14. A classifier that's very accurate (and deep)
  15. AutoML in nnetsauce (randomized and quasi-randomized nnetworks) Pt.2: multivariate time series forecasting
  16. AutoML in nnetsauce (randomized and quasi-randomized nnetworks)
  17. Version v0.14.0 of nnetsauce for R and Python
  18. An infinity of time series forecasting models in nnetsauce (Part 2 with uncertainty quantification)
  19. A new version of nnetsauce (randomized and quasi-randomized 'neural' networks)
  20. New version of nnetsauce -- various quasi-randomized networks
  21. Tuning and interpreting LSBoost
  22. Classification using linear regression
  23. An infinity of time series models in nnetsauce
  24. A deeper learning architecture in nnetsauce
  25. Classify penguins with nnetsauce's MultitaskClassifier
  26. Bayesian forecasting for uni/multivariate time series
  27. New nnetsauce
  28. Technical documentation
  29. A new version of nnetsauce, and a new Techtonique website
  30. Back next week, and a few announcements
  31. nnetsauce version 0.5.0, randomized neural networks on GPU
  32. R notebooks for nnetsauce
  33. Version 0.4.0 of nnetsauce, with fruits and breast cancer classification
  34. Feedback forms for contributing
  35. nnetsauce for R
  36. A new version of nnetsauce (v0.3.1)
  37. 2019 Recap, the nnetsauce, the teller and the querier
  38. Prediction intervals for nnetsauce models
  39. Bagging in the nnetsauce
  40. Adaboost learning with nnetsauce
  41. nnetsauce on Pypi
  42. More nnetsauce (examples of use)
  43. nnetsauce

R

  1. 'Zero-Shot Probabilistic Stock Returns Forecasting with Pretrained RVFL Networks' accepted at COPA 2026 (and to appear in the Proceedings of Machine Learning Research)
  2. 'garchf': GARCH probabilistic forecasting with package 'forecast'-style interface (and 'rugarch' under the hood)
  3. GPopt for R: Bayesian and conformal optimization of black-box functions and hyperparameter tuning
  4. My last R posts: How conformalization helps weak models, fast conformal prediction with jackknife+ (and no refitting), and sklearn in R
  5. Fast conformal prediction (no refitting) for some Machine Learning models via closed-form jackknife plus
  6. Using scikit-learn models in R easily with the tisthemachinelearner package
  7. How Conformal Prediction Makes Linear Models Good Enough — An Example Using R Package mlS3
  8. Techtonique dot net, the Machine Learning web API, is back online (but more like a passion project for now)
  9. Conformalized TabICL: Prediction Intervals for a State-Of-The-Art Tabular Foundation Model in Python and R
  10. Conformalized TabPFN: Prediction Intervals for a Pretrained Transformer for Tabular Data in Python and R
  11. Probabilistic Time Series Cross-Validation with R package crossvalidation
  12. One interface, (Almost) Every Classifier (and Regressor): unifiedml v0.3.0
  13. You Don't Need to Learn All the Weights on tabular data: The Case for rvflnet (a nonlinear expressive glmnet) on regression, classification and survival analysis
  14. `mlS3` — A Unified S3 Machine Learning Interface in R
  15. One interface, (Almost) Every Classifier: unifiedml v0.2.1
  16. Techtonique dot net is down until further notice
  17. Explaining Time-Series Forecasts with Sensitivity Analysis (ahead::dynrmf and external regressors)
  18. Option pricing using time series models as market price of risk Pt.3
  19. Explaining Time-Series Forecasts with Exact Shapley Values (ahead::dynrmf with external regressors applied to scenarios)
  20. My Presentation at Risk 2026: Lightweight Transfer Learning for Financial Forecasting
  21. nnetsauce with and without jax for GPU acceleration
  22. Understanding Boosted Configuration Networks (combined neural networks and boosting): An Intuitive Guide Through Their Hyperparameters
  23. R version of Python package survivalist, for model-agnostic survival analysis
  24. Presenting Lightweight Transfer Learning for Financial Forecasting (Risk 2026)
  25. Option pricing using time series models as market price of risk
  26. Enhancing Time Series Forecasting (ahead::ridge2f) with Attention-Based Context Vectors (ahead::contextridge2f)
  27. Beyond Cross-validation: Hyperparameter Optimization via Generalization Gap Modeling
  28. rtopy: an R to Python bridge -- novelties
  29. Python examples for 'Beyond Nelson-Siegel and splines: A model- agnostic Machine Learning framework for discount curve calibration, interpolation and extrapolation'
  30. Forecasting benchmark: Dynrmf (a new serious competitor in town) vs Theta Method on M-Competitions and Tourism competitition
  31. Finally figured out a way to port python packages to R using uv and reticulate: example with nnetsauce
  32. Overfitting Random Fourier Features: Universal Approximation Property
  33. Counterfactual Scenario Analysis with ahead::ridge2f
  34. ARIMA Pricing: Semi-Parametric Market price of risk for Risk-Neutral Pricing (code + preprint)
  35. Analyzing Paper Reviews with LLMs: I Used ChatGPT, DeepSeek, Qwen, Mistral, Gemini, and Claude (and you should too + publish the analysis)
  36. tisthemachinelearner: New Workflow with uv for R Integration of scikit-learn
  37. (ICYMI) RPweave: Unified R + Python + LaTeX System using uv
  38. unifiedml: A Unified Machine Learning Interface for R, is now on CRAN + Discussion about AI replacing humans
  39. Context-aware Theta forecasting Method: Extending Classical Time Series Forecasting with Machine Learning
  40. unifiedml in R: A Unified Machine Learning Interface
  41. Deterministic Shift Adjustment in Arbitrage-Free Pricing (historical to risk-neutral short rates)
  42. New instantaneous short rates models with their deterministic shift adjustment, for historical and risk-neutral simulation
  43. RPweave: Unified R + Python + LaTeX System using uv
  44. GAN-like Synthetic Data Generation Examples (on univariate, multivariate distributions, digits recognition, Fashion-MNIST, stock returns, and Olivetti faces) with DistroSimulator
  45. R port of llama2.c
  46. Native uncertainty quantification for time series with NGBoost
  47. Real-time pricing with a pretrained probabilistic stock return model
  48. Combining any model with GARCH(1,1) for probabilistic stock forecasting
  49. Generating Synthetic Data with R-vine Copulas using esgtoolkit in R
  50. Reimagining Equity Solvency Capital Requirement Approximation (one of my Master's Thesis subjects): From Bilinear Interpolation to Probabilistic Machine Learning
  51. Transfer Learning using ahead::ridge2f on synthetic stocks returns Pt.2: synthetic data generation
  52. Transfer Learning using ahead::ridge2f on synthetic stocks returns
  53. I'm supposed to present 'Conformal Predictive Simulations for Univariate Time Series' at COPA CONFERENCE 2025 in London...
  54. external regressors in ahead::dynrmf's interface for Machine learning forecasting
  55. Another interesting decision, now for 'Beyond Nelson-Siegel and splines: A model-agnostic Machine Learning framework for discount curve calibration, interpolation and extrapolation'
  56. A user-friendly graphical interface to techtonique dot net's API (will eventually contain graphics).
  57. Calling =TECHTO_MLCLASSIFICATION for Machine Learning supervised CLASSIFICATION in Excel is just a matter of copying and pasting
  58. Calling =TECHTO_MLREGRESSION for Machine Learning supervised regression in Excel is just a matter of copying and pasting
  59. Calling =TECHTO_RESERVING and =TECHTO_MLRESERVING for claims triangle reserving in Excel is just a matter of copying and pasting
  60. Calling =TECHTO_SURVIVAL for Survival Analysis in Excel is just a matter of copying and pasting
  61. Calling =TECHTO_SIMULATION for Stochastic Simulation in Excel is just a matter of copying and pasting
  62. Calling =TECHTO_FORECAST for forecasting in Excel is just a matter of copying and pasting
  63. Random Vector Functional Link (RVFL) artificial neural network with 2 regularization parameters successfully used for forecasting/synthetic simulation in professional settings: Extensions (including Bayesian)
  64. R version of 'Backpropagating quasi-randomized neural networks'
  65. Beyond ARMA-GARCH: leveraging any statistical model for volatility forecasting
  66. Stacked generalization (Machine Learning model stacking) + conformal prediction for forecasting with ahead::mlf
  67. Programming language-agnostic reserving using RidgeCV, LightGBM, XGBoost, and ExtraTrees Machine Learning models
  68. Free R, Python and SQL editors in techtonique dot net
  69. Beyond Nelson-Siegel and splines: A model-agnostic Machine Learning framework for discount curve calibration, interpolation and extrapolation
  70. R version of Probabilistic Machine Learning (for longitudinal data) Reserving (work in progress)
  71. Beyond ARMA-GARCH: leveraging model-agnostic Machine Learning and conformal prediction for nonparametric probabilistic stock forecasting (ML-ARCH)
  72. Permutations and SHAPley values for feature importance in techtonique dot net's API (with R + Python + the command line)
  73. Which patient is going to survive longer? Another guide to using techtonique dot net's API (with R + Python + the command line) for survival analysis
  74. A Guide to Using techtonique.net's API and rush for simulating and plotting Stochastic Scenarios
  75. Simulating Stochastic Scenarios with Diffusion Models: A Guide to Using techtonique.net's API for the purpose
  76. Will my apartment in 5th avenue be overpriced or not? Harnessing the power of www.techtonique.net (+ xgboost, lightgbm, catboost) to find out
  77. How long must I wait until something happens: A Comprehensive Guide to Survival Analysis via an API
  78. Harnessing the Power of techtonique.net: A Comprehensive Guide to Machine Learning Classification via an API
  79. Quantile regression with any regressor -- Examples with RandomForestRegressor, RidgeCV, KNeighborsRegressor
  80. Survival stacking: survival analysis translated as supervised classification in R and Python
  81. 'Bayesian' optimization of hyperparameters in a R machine learning model using the bayesianrvfl package
  82. A lightweight interface to scikit-learn in R: Bayesian and Conformal prediction
  83. A lightweight interface to scikit-learn in R Pt.2: probabilistic time series forecasting in conjunction with ahead::dynrmf
  84. Extending the Theta forecasting method to GLMs, GAMs, GLMBOOST and attention: benchmarking on Tourism, M1, M3 and M4 competition data sets (28000 series)
  85. Extending the Theta forecasting method to GLMs and attention
  86. Nonlinear conformalized Generalized Linear Models (GLMs) with R package 'rvfl' (and other models)
  87. Conformalize (improved prediction intervals and simulations) any R Machine Learning model with misc::conformalize
  88. My poster for the 18th FINANCIAL RISKS INTERNATIONAL FORUM by Institut Louis Bachelier/Fondation du Risque/Europlace Institute of Finance
  89. Interpretable probabilistic kernel ridge regression using Matérn 3/2 kernels
  90. (News from) Probabilistic Forecasting of univariate and multivariate Time Series using Quasi-Randomized Neural Networks (Ridge2) and Conformal Prediction
  91. Word-Online: re-creating Karpathy's char-RNN (with supervised linear online learning of word embeddings) for text completion
  92. CRAN-like repository for most recent releases of Techtonique's R packages
  93. Presenting 'Online Probabilistic Estimation of Carbon Beta and Carbon Shapley Values for Financial and Climate Risk' at Institut Louis Bachelier
  94. Web app with DeepSeek R1 and Hugging Face API for chatting
  95. tisthemachinelearner: A Lightweight interface to scikit-learn with 2 classes, Classifier and Regressor (in Python and R)
  96. R version of survivalist: Probabilistic model-agnostic survival analysis using scikit-learn, xgboost, lightgbm (and conformal prediction)
  97. A simple test of the martingale hypothesis in esgtoolkit
  98. Command Line Interface (CLI) for techtonique.net's API
  99. Gradient-Boosting and Boostrap aggregating anything (alert: high performance): Part5, easier install and Rust backend
  100. Just got a paper on conformal prediction REJECTED by International Journal of Forecasting despite evidence on 30,000 time series (and more). What's going on? Part2: 1311 time series from the Tourism competition
  101. Techtonique is released! (with a tutorial in various programming languages and formats)
  102. Just got a paper on conformal prediction REJECTED by International Journal of Forecasting despite evidence on 30,000 time series (and more). What's going on?
  103. Stock price forecasting with Deep Learning: throwing power at the problem (and why it won't make you rich)
  104. No-code Machine Learning Cross-validation and Interpretability in techtonique.net
  105. You can beat Forecasting LLMs (Large Language Models a.k.a foundation models) with nnetsauce.MTS
  106. Unified interface and conformal prediction (calibrated prediction intervals) for R package forecast (and 'affiliates')
  107. GLMNet in Python: Generalized Linear Models
  108. Gradient-Boosting anything (alert: high performance): Part4, Time series forecasting
  109. Predictive scenarios simulation in R, Python and Excel using Techtonique API
  110. Chat with your tabular data in www.techtonique.net
  111. Gradient-Boosting anything (alert: high performance): Part3, Histogram-based boosting
  112. R editor and SQL console (in addition to Python editors) in www.techtonique.net
  113. R and Python consoles + JupyterLite in www.techtonique.net
  114. Gradient-Boosting anything (alert: high performance): Part2, R version
  115. Gradient-Boosting anything (alert: high performance)
  116. Automated random variable distribution inference using Kullback-Leibler divergence and simulating best-fitting distribution
  117. Techtonique web app for data-driven decisions using Mathematics, Statistics, Machine Learning, and Data Visualization
  118. Parallel for loops (Map or Reduce) + New versions of nnetsauce and ahead
  119. Adaptive (online/streaming) learning with uncertainty quantification using Polyak averaging in learningmachine
  120. New versions of nnetsauce and ahead
  121. Prediction sets and prediction intervals for conformalized Auto XGBoost, Auto LightGBM, Auto CatBoost, Auto GradientBoosting
  122. Quick/automated R package development workflow (assuming you're using macOS or Linux) Part2
  123. R package development workflow (assuming you're using macOS or Linux)
  124. A new method for deriving a nonparametric confidence interval for the mean
  125. Conformalized adaptive (online/streaming) learning using learningmachine in Python and R
  126. Bayesian (nonlinear) adaptive learning
  127. Auto XGBoost, Auto LightGBM, Auto CatBoost, Auto GradientBoosting
  128. Forecasting uncertainty: sequential split conformal prediction + Block bootstrap (web app)
  129. learningmachine v2.0.0: Machine Learning with explanations and uncertainty quantification
  130. Forecasting the Economy
  131. A detailed introduction to Deep Quasi-Randomized 'neural' networks
  132. Probability of receiving a loan; using learningmachine
  133. mlsauce's `v0.18.2`: various examples and benchmarks with dimension reduction
  134. Conformalized predictive simulations for univariate time series on more than 250 data sets
  135. learningmachine v1.0.0: prediction intervals around the probability of the event 'a tumor being malignant'
  136. Multiple examples of Machine Learning forecasting with ahead
  137. rtopy (v0.1.1): calling R functions in Python
  138. ahead forecasting (v0.10.0): fast time series model calibration and Python plots
  139. A classifier that's very accurate (and deep) Pt.2: there are > 90 classifiers in nnetsauce
  140. learningmachine: prediction intervals for conformalized Kernel ridge regression and Random Forest
  141. A plethora of datasets at your fingertips Part2: how many times do couples cheat on each other? Descriptive analytics, interpretability and prediction intervals using conformal prediction
  142. Diffusion models in Python with esgtoolkit (Part2)
  143. Diffusion models in Python with esgtoolkit
  144. Quasi-randomized nnetworks in Julia, Python and R
  145. A plethora of datasets at your fingertips
  146. A classifier that's very accurate (and deep)
  147. mlsauce version 0.8.10: Statistical/Machine Learning with Python and R
  148. Version v0.14.0 of nnetsauce for R and Python
  149. A diffusion model: G2++
  150. Diffusion models in ESGtoolkit + announcements
  151. Risk-neutralize simulations
  152. Comparing cross-validation results using crossval_ml and boxplots
  153. Did you ask ChatGPT about who you are?
  154. A new version of nnetsauce (randomized and quasi-randomized 'neural' networks)
  155. Simple interfaces to the forecasting API
  156. A web application for forecasting in Python, R, Ruby, C#, JavaScript, PHP, Go, Rust, Java, MATLAB, etc.
  157. Boosted Configuration (neural) Networks Pt. 2
  158. Boosted Configuration (_neural_) Networks for classification
  159. News from ESGtoolkit, ycinterextra, and nnetsauce
  160. New version of nnetsauce -- various quasi-randomized networks
  161. A dashboard illustrating bivariate time series forecasting with `ahead`
  162. Hundreds of Statistical/Machine Learning models for univariate time series, using ahead, ranger, xgboost, and caret
  163. Time series cross-validation using `crossvalidation` (Part 2)
  164. Fast and scalable forecasting with ahead::ridge2f
  165. Automatic Forecasting with `ahead::dynrmf` and Ridge regression
  166. Forecasting with `ahead`
  167. `crossvalidation` and random search for calibrating support vector machines
  168. parallel grid search cross-validation using `crossvalidation`
  169. `crossvalidation` on R-universe, plus a classification example
  170. A forecasting tool (API) with examples in curl, R, Python
  171. An infinity of time series models in nnetsauce
  172. New activation functions in mlsauce's LSBoost
  173. 2020 recap, Gradient Boosting, Generalized Linear Models, AdaOpt with nnetsauce and mlsauce
  174. Classify penguins with nnetsauce's MultitaskClassifier
  175. Bayesian forecasting for uni/multivariate time series
  176. Boosting nonlinear penalized least squares
  177. Statistical/Machine Learning explainability using Kernel Ridge Regression surrogates
  178. Submitting R package to CRAN
  179. Simulation of dependent variables in ESGtoolkit
  180. Forecasting lung disease progression
  181. Explainable 'AI' using Gradient Boosted randomized networks Pt2 (the Lasso)
  182. LSBoost: Explainable 'AI' using Gradient Boosted randomized networks (with examples in R and Python)
  183. nnetsauce version 0.5.0, randomized neural networks on GPU
  184. Maximizing your tip as a waiter (Part 2)
  185. Maximizing your tip as a waiter
  186. AdaOpt classification on MNIST handwritten digits (without preprocessing)
  187. AdaOpt (a probabilistic classifier based on a mix of multivariable optimization and nearest neighbors) for R
  188. Custom errors for cross-validation using crossval::crossval_ml
  189. Encoding your categorical variables based on the response variable and correlations
  190. Linear model, xgboost and randomForest cross-validation using crossval::crossval_ml
  191. Grid search cross-validation using crossval
  192. Time series cross-validation using crossval
  193. On model specification, identification, degrees of freedom and regularization
  194. R notebooks for nnetsauce
  195. Version 0.4.0 of nnetsauce, with fruits and breast cancer classification
  196. Feedback forms for contributing
  197. nnetsauce for R
  198. ESGtoolkit, a tool for Monte Carlo simulation (v0.2.0)
  199. Using R in Python for statistical learning/data science
  200. Model calibration with `crossval`
  201. crossval