AN EXPLORATORY COMPARISON OF STOCK PRICES PREDICTION USING MULTIPLE MACHINE LEARNING APPROACHES BASED ON HONG KONG SHARE MARKET

Abstract

STOCK PRICE PREDICTION HAS ALWAYS BEEN CHALLENGING DUE TO ITS VOLATILITY AND UNPREDICTABILITY. THIS PAPER PERFORMS A PRELIMINARY EXPLORATORY COMPARISON THAT UTILIZES LONG SHORT-TERM MEMORY (LSTM) AND SUPPORT VECTOR MACHINE (SVM) ALGORITHMS TO FORECAST THE STOCK MARKET IN HONG KONG. IT CONSIDERS A PUBLIC DATASET PUBLICLY AVAILABLE AND USES FEATURE ENGINEERING TO EXTRACT RELEVANT FEATURES. THEN, LSTM AND SVM ALGORITHMS ARE APPLIED TO PREDICT STOCK PRICES. OUR RESULTS SHOW THAT THE PROPOSED MACHINE LEARNING TECHNIQUES CAN PREDICT STOCK PRICES IN HONG KONG'S SHARE MARKET WITH THE ERROR METRICS PRESENTED, AND, FOR THIS PURPOSE, LSTM ACHIEVED BETTER RESULTS THAN SVM, WITH MSE = 0.0026, RMSE = 0.0508, MAE = 0.0406, AND MAPE = 1.325.