This article provides an in‑depth overview of regression prediction, covering linear models like OLS, Lasso, Ridge, and Bayesian approaches, as well as non‑linear techniques such as tree ensembles, SVR, KNN, neural networks, and advanced deep learning frameworks for tabular data.
An extensive overview of supervised learning introduces key concepts, model types, loss functions, optimization methods, linear and generalized linear models, support vector machines, generative approaches, tree and ensemble techniques, as well as foundational learning theory, providing a comprehensive foundation for AI practitioners.
This article explains the principles of one‑way, two‑way and multi‑factor ANOVA, demonstrates how to perform them in R using aov(), lm() and anova(), and shows post‑hoc comparisons with TukeyHSD as well as correlation testing with cor() and cor.test().
RuleFit, introduced by Friedman and Popescu in 2008, integrates decision‑tree‑derived rules with linear regression to boost predictive accuracy while maintaining strong interpretability, and this article explains its definition, rule extraction, algorithmic implementation, code example, advantages, limitations, and practical insights.
This article explains ridge regression by defining the estimator, outlining its key properties, discussing methods for choosing the ridge parameter, and demonstrating its application to economic data with Python code and visualizations.
This article introduces the Project Matrix initiative that re‑examines and restructures Spark‑ML linear models, detailing the background of Spark‑ML usage at JD, the performance‑focused optimizations such as blockification and virtual centering, and outlines upcoming work to further improve scalability and accuracy.
