Stock Price Prediction of the TMT Industry Based on Machine-Learning

Abstract

Predicting the TMT stock market enjoys great significance in the financial field and it has been widely researched due to its sophisticated nature and huge potential. Therefore, two machine learning models are trained and tested in this article, i.e., the multi-linear regression model and the random forest model with price information from three stocks, i.e., AAPL, NFLX, and TSLA. Every model used 80% of stock data to train and the rest 20% to test. To evaluate how accurately the models fit the price in reality, the R-squared value and mean absolute percentage error value are used. Firstly, the stationarity had to be checked, which is carried out with the Dicky-Fuller Test. The small p-value showed that the data don’t have a unit root. Then, the data were processed by the two models written by python. According to the analysis, the multi-linear regression and random forest models are relatively accurate. However, with a larger data set or with a relatively small rolling period, the random forest will be able to achieve a better result. However, larger data comes with the price of more computing resources. These results indicate that it is feasible to predict stock market prices with machine learning models and the accuracy could be improved by utilizing better machine learning models.