Application of a Case Base Reasoning Based Support Vector Machine for Financial Time Series Data Forecasting

摘要

This paper establishes a novel financial time series-forecasting model, by clustering and evolving support vector machine for stocks on S&P 500 in the U.S. This forecasting model integrates a data clustering technique with Case Based Reasoning (CBR) weighted clustering and classification with Support Vector Machine (SVM) to construct a decision-making system based on historical data and technical indexes. The future price of the stock is predicted by this proposed model using technical indexes as input and the forecasting accuracy of the model can also be further improved by dividing the historic data into different clusters. Overall, the results support the new stock price predict model by showing that it can accurately react to the current tendency of the stock price movement from these smaller cases. The hit rate of CBR-SVM model is 93.85% the highest performance among others.