Decoding Financial Data: Machine Learning Approach to Predict Trading Actions

This paper presents a study on predicting stock trends using a dataset consisting of key financial indicators from 300 S&P 500 companies over a decade. Each company is characterized by 58 financial indicators along with their 1-year changes, offering valuable insights into potential trends. The objective is to develop predictive models to accurately forecast trading actions (buy, sell, hold) based on fundamental financial data. Three machine learning models---Random Forest, CatBoost, and XGBoost classifiers---were trained, employing two distinct voting mechanisms. The first voting mechanism was utilized in the competition, while the second was developed post-competition after the test labels were released. Notably, the second model was trained solely on the training data. The results demonstrate that both voting mechanisms effectively capture trends, as reflected by the average error cost measure, evaluated using the provided error cost matrix.

---

Track: Data Mining Competition