Recommender Systems and Techniques

A hybrid machine learning recommendation system for interior design services balances customization with cost constraints, achieving 83.62% accuracy in predicting user preferences.

AlphaLearn proposes a multi-objective evolutionary framework for adaptive e-learning pathways that integrates fairness as a core optimization criterion alongside learning effectiveness and engagement.

Engineering optimization of MLOps processes for high-load recommendation systems integrating streaming features, parameter servers, and online training for latency and quality under scale.