Stock price prediction based on optimized random forest model

With the rapid development of Chinese financial industry, people use machine learning to effectively analyze and study the financial market and improve the expected income. The training accuracy in the random forest model is low since the decision tree has the same weight and it is difficult to select the parameters such as the decision tree and the maximum number of use features of the decision tree in the model. In order to solve the problem, a prediction model based on the weighted random forest and ant colony algorithm is proposed in this paper. The prediction error of the weighted random forest model proposed in this paper is obviously lower than the general random forest algorithm and regression algorithm, which is verified through the data of TA-lib and Baidu search index.