This project involved a structured team-based approach to developing and evaluating quantitative models for investment analysis. The project began with a staged literature review process, where teams analyzed a curated list of academic references—first by reviewing abstracts, then conclusions and results sections, and finally assessing model applicability and implementation feasibility. Team members each selected at least one relevant model or method, which they implemented within a shared coding framework that also included common components for data analysis, benchmarking, visualization, and result interpretation.

The project emphasized not only technical implementation but also the ability to effectively communicate the value and utility of selected models through an interactive dashboard. Teams used Python and R tools, including Shiny and Streamlit for dashboard development, along with libraries like Polars, Kedro, and uv to build, test, and present their work. Final deliverables included a written report, fully functional interactive dashboard, and a private GitHub repository housing all code and documentation. Recordings and curated resources supported each stage of development, ensuring a collaborative and rigorous research process.