An Efficient Prediction Model based on Machine Learning Techniques for Prediction of the Stock Market

Abstract

Nowadays, the stock market's prediction is a topic that attracted researchers in the world. Stock market prediction is a process that requires a comprehensive understanding of the data stock movement and analysis it accurately. Therefore, it needs intelligent methods to deal with this task to ensure that the prediction is as correct as possible, which will return profitable benefits to investors. The main goal of this article is the employment of effective machine learning techniques to build a strong model for stock market prediction. The work involved three stages, the first stage involved preprocessing for the stock market data set, then the second stage which involved employing two from supervised machine learning techniques namely K-Nearest Neighbor (K-NN) and Random Forest (RF), and finally, the evaluation stage of accuracy and efficiency of the prediction for the two proposed models. The results experiments showed that the two proposed models achieved a high accuracy ratio and the RF model was the best of prediction accuracy, where it reached 93.23%, 93.12% and 93.17% respectively according to evaluation measures precision, recall, and F-measure.