Stock Return Prediction under US Federal Funds Rate Hike Based on Supervised Machine Learning

Abstract

As US Federal Reverse Systems has continued to raise federal funds in the past few years in order to curb inflation, this has had a huge impact on chinese capital market. Investors and financial institude are actively engaged in predicting stock returns to maximize their investment income. This study constructs a model to analyze and predict the financial factor of stock income based on supervised machine learning methods and evaluate the results. The datasample is extracted from wind, for the period half a year before and after the recent federal funds rate hike. Utilizing machine learning packages in R, this paper construct models based on linear discriminant analysis, decision tree and random forest models. After constructing estimation models, this paper visualizes the prediction result by utilizing drawing package in R. It has been found that the random forest algorithm predicting model generates very successful results for the financial factor prediction as the model accuracy reaches 99%. According to the analysis, relevant model to predict financial factors and non-financial factors based on non-linear supervised machine learning algorithm can be built by investors or hedge fund agency to estimate stock performance in the future. This study also investigates the economic result of the Federal Funds Rate hikes, which is instructive for investors to make well-informed decisions.