"Logic-Driven Investment Algorithms: A Modern Quantitative Framework"

This paper contributes to the literature by proposing a logic-driven, machine learning–augmented framework for quantitative investing. It integrates principles from the CFA curriculum and data science to build explainable, backtestable, and risk-optimized portfolio strategies using modern algorithms like XGBoost, Bayesian learning, and Black-Litterman models. The framework emphasizes transparency, alpha decay monitoring, and multi-asset allocation, which are underrepresented in traditional quant research.