Machine Learning in Morningstar Fund Rating and Management (https://github.com/Howl101/Fund_Ratings)

Project type: Data analysis

Group Members: Yuxuan Wang (yw2592), Xiaoxuan Liu (xl944), Quanyi Li (ql278)

Course code: 5741

Our project aims to promote machine learning and data analysis innovation that aims to develop a predictive model for rating funds based on various attributes and metrics. Investment funds are a crucial part of the global financial ecosystem, offering investors opportunities for wealth growth. However, the vast number of available funds makes it challenging for investors to make informed decisions. Therefore, fund ratings become crucial for guiding investor decisions in the modern investment market.

Traditional analytic methods, such as the Morning Star, while rigorous and professional, take time and can be slow to reflect market changes. Machine learning classification methods, while broadly applied in credit and other financial ratings, are less explored in fund ratings. Our team aims to investigate their potential in fund ratings, broadening their application and offering new insights. The use of machine learning models offers real-time updates and data-driven insights. Through analyzing vast datasets and market trends, the model promises more timely and accurate ratings.

By transitioning to a more data-driven approach, we aim to leverage the fund rating outcome to refine our investment strategies, ensuring they are responsive and informed. This advancement aligns with our core objective: optimizing fund performance through investment intelligence, elevating our investment acumen, and adding substantial value to our business operations.