Research on the Google Stock Price Prediction Based on SVR, Random Forest, and KNN Models

Abstract

The prediction of stock prices is an intriguing and difficult study issue. Due to its frequent offers of quick rewards and low risk of loss, the stock market is currently regarded as a prestigious trading sector. Data mining and business researchers find the stock market to be an ideal environment due to its extensive and dynamic information sources. In this paper, the data of google stock price from 2018-1-2 to 2023-3-31 is imported. As our classification algorithms, the authors independently selected and contrasted super vector regression, random forest, and K-nearest neighbor. Following test, analysis, and comparison of these classifiers and calculate the mean square error of test data, the final result was reached. According to the result, the random forest has the smallest MSE value, so it is the best prediction and uses this method to predict the stock price of next ten days. After using random forest to do the stock price prediction, we find that the close price has the increasing trend for next ten days, which is good for the investors.