Forecasting a Stock Trend Using Genetic Algorithm and Random Forest

This paper addresses the problem of forecasting daily stock trends. The key consideration is to predict whether a given will close on uptrend tomorrow with reference today’s closing price. We propose model that comprises features selection model, based Genetic Algorithm (GA), and Random Forest (RF) classifier. In our study, we consider four international indices follow concept distributed lag analysis. adopted genetic algorithm approach select set helpful among these lags’ indices. Subsequently, employed classifier, unveil hidden relationships between particular stock’s trend. tested by using it trends 15 stocks. Experiments showed had 80% accuracy, significantly outperforming dummy forecast. S&P 500 was most useful index, whereas CAC40 least in prediction study provides evidence usefulness employing