New Approach for E-Commerce Stock Prices Prediction: Combination of Machine Learning and Technical Analysis

Forecasting stock market is always a challenge task for the investors. This study aimed to develop new approach forecasting price movements of e-commerce stocks. The signals emitted by technical indicators are used as features two machine learning algorithms in predicting stocks movements. this were Moving Average (MA), Convergence Divergence (MACD), Relative Strength Index (RSI) and Stochastic Oscillator (SO). Meanwhile, Random Forest (RF) K-Neighbor Nearest (KNN). findings indicated that inclusion MA rule with 5-days short 20-days long helps reduce error values prediction model. Besides that, also found from MA, MACD, RSI SO fit model well. investors recommended use predict Lastly, consider these four indicators, (5-days & 20 long-MA), reference their investment strategies