This project gave students practical experience applying quantitative, data science, and AI techniques to solve real-world problems in global macro investing. Working with live financial and macroeconomic datasets, students operated in team settings that reflected real-world work environments while enhancing their coding practices, model development, and communication skills. The core objective was to use machine learning and advanced quantitative methods to build systematic trading strategies tailored to the global macro landscape—an area of growing interest among investment managers amid economic uncertainty.

Students focused on identifying tradable trend deviations and structural change points in macroeconomic time series, building models to predict and explain movements in macro data and asset returns. They developed and backtested tactical asset allocation frameworks, as well as trend-following and mean-reversion strategies. This project was especially valuable for students pursuing roles as quantitative analysts, researchers, developers, or data scientists in investment management and trading, with skills gained also applicable to broader data science roles in tech and related fields.