Aditya Maheshwari - Department of Computer Science, Metropolitan College, Boston University, Boston, USA
Vaidehi Shah - Department of Computer Science, Metropolitan College, Boston University, Boston, USA
Aakansha Sawhney - Department of Computer Science, Metropolitan College, Boston University, Boston, USA
Eugene Pinsky - Department of Computer Science, Metropolitan College, Boston University, Boston, USA

This research paper aims to present an extensive analysis of Large-cap class-A mutual funds spanning a period of ۲۵ years. Using this historical data, the study presents the readers with the observed patterns and trends in these mutual funds. The data has been sourced from two major data repositories for mutual fund and finance data - WRDS (Wharton Research Data Services) and YF (Yahoo Finance). The study uses statistical methodologies like Sharpe Ratio and Volatility and analytical methodologies like CUSUM and Clustering. Along with this quantitative analysis, the paper also encompasses qualitative data like Assets Under Management, Turnover Ratio, and Management Information for all the funds used. This helps gain insights into the influence of these factors on the performance of the mutual funds. This paper mainly discusses how all the aforementioned factors influence the mutual fund trajectories with the help of effective visualizations and machine learning-based analysis over ۲۵ years, hence developing an efficient pipeline.This research paper aims to present an extensive analysis of Large-cap class-A mutual funds spanning a period of ۲۵ years. Using this historical data, the study presents the readers with the observed patterns and trends in these mutual funds. The data has been sourced from two major data repositories for mutual fund and finance data - WRDS (Wharton Research Data Services) and YF (Yahoo Finance). The study uses statistical methodologies like Sharpe Ratio and Volatility and analytical methodologies like CUSUM and Clustering. Along with this quantitative analysis, the paper also encompasses qualitative data like Assets Under Management, Turnover Ratio, and Management Information for all the funds used. This helps gain insights into the influence of these factors on the performance of the mutual funds. This paper mainly discusses how all the aforementioned factors influence the mutual fund trajectories with the help of effective visualizations and machine learning-based analysis over ۲۵ years, hence developing an efficient pipeline.

Mutual Fund Performance, CUSUM, Machine Learning, Clustering, Visualization of Mutual Funds