This is the repository for Columbia Data Science Capstone Project sponsered by Vanguard.
To understand how investment companies are clustered and behave based on their shared holdings.
- Part I: To transform the huge holdings data with billions of records into easily digestible insights through metrics constructions and dashboard visualizations.
- Part II: To identify cohorts of similar investors through clustering analysis.
- Part III: To detect the polarized topics for investment over the past 10 years
- Part IV: To develop a dashboard for visualization of the project results.
Rui Bai (rb3454)
Xinyi Liu (xl2904)
Yichi Liu (yl4327)
Yuchen Pei (yp2533)
Yujing Song (ys3251)