Fuzzy Soft Set Based Stock Prediction Model Integrating Machine Learning with Deep Sentiment Analysis
Mahmut Sami Sivri and Alp Ustundag
In recent years, machine learning and sentiment analysis have been visited by many researchers to predict the stock market where integration different types of information, such as news and financial data, has direct impact. However, it is still unclear how to integrate various of information sources within the prediction process. This study presents a methodology based on fuzzy soft sets to overcome this problem. To determine the fuzzy membership function, the normalized weekly cumulative rate of returns of prediction models were utilized as the criteria. In addition to proposing a new approach, our research varies from previous studies in terms of data coverage and the models that we used in both sentiment analysis and prediction phase. Performance of the proposed methodology was evaluated with the cases where news and financial data are used separately and together. Feature selection methods were also integrated before the prediction phase. The final results show that the proposed methodology outperforms both in terms of rate of return and accuracy.
Keywords: Fuzzy soft sets, stock market prediction, sentiment analysis, machine learning, forecasting, financial data