TOPICS IN QUANT FINANCE

This graduate-level course provides a rigorous foundation in quantitative portfolio construction, bridging theory with practical implementation. It develops a systematic framework for constructing optimal portfolios, beginning with the classical Markowitz model and enhancing it to address real-world portfolio objectives and constraints.  Students learn how  forecasts of asset returns, risk, and market impact are formulated in the  optimizer objectives and constraints, and how estimation error affects portfolio construction and performance. They also study the robust estimation of key optimizer inputs such as risk models using modern statistical and econometric methods that handle noise and time-varying dynamics. Students gain hands-on experience constructing portfolios using industry-standard datasets, tools, and risk models. The course also provides a brief introduction to advanced topics such as random matrix theory, multiperiod optimization, and the use of modern machine learning methods, which represent emerging directions in quantitative portfolio research.