The Prediction of Stock Index Movements Based on Machine Learning

Abstract

With the rapid development of Artificial Intelligence technology, different methods from other subjects have been used in predicting stock market movement and the stock prices. In this paper, 11 technical indicators were calculated to predict the stock index movements using two machine learning technics. S&P 500 is a stock market index that measures the stock performance in the United States, from Jan 2004 to Dec 2018. The results showed that Random Forest is superior to Support Vector Machine in both training and test sets. Several technical trend indicators we calculated here, such as WILLR, BBANDS, CCI, CMO and MACD, play a significant role in prediction of index movements based on Random Forest. This paper provides a fundamental framework in studying the prediction of stock movements by Artificial Intelligence.