Predicting Blue-Chip Stock Returns Using Machine Learning Algorithms

Abstract

The aim of the paper is to identify the relationship between blue chip stock returns and market indices using advanced machine learning models. The key objective of the study is to determine an efficient machine learning (ML) model that produces minimum error which gauging the relationship between market volatility indices, i.e., VIX, ISEE, and NASDAQ-100 and stock returns of blue-chip companies like Apple, Amazon, and IBM. In recent studies, machine learning models are generally used for the prediction of stock price movements of the company’s stocks. However, very few studies attempt to explore the relationship between market volatility indices and stock returns of blue chip or large capitalization companies using ML models. Therefore, the current research fills this research gap by analyzing the relationship between market volatility indices and the returns of blue-chip stocks like Amazon, Apple, and IBM. The study employs support vector machine (SVR), regression tree, and random forest model to assess the desired relationships. The findings suggest that the regression tree model predicts the stock returns of Amazon better, while SVR model is comparatively better in predicting the stock returns of Apple and IBM. However, the main limitation of the research is lack of consideration for additional stocks and machine learning which could have improved the generalizability of the research findings. Thus, future research studies should consider different types of stocks from different sectors and estimate the predictive capacity of various machine learning models.