Binary gravity search algorithm and support vector machine for forecasting and trading stock indices

A hybrid Support Vector Machine (SVM) model is proposed and applied to the task of forecasting the daily returns of five popular stock indices in the world, including the S&P500, NKY, CAC, FTSE100 and DAX. The originality of this work is that the Binary Gravity Search Algorithm (BGSA) is utilized, in order to optimize the parameters and inputs of SVM. The results show that the forecasts made by this model are significantly better than the Random Walk (RW), SVM, best predictors and Buy-and-Hold. The average accuracy of BGSA-SVM for five stock indices is 52.87%. In general, this study proves that a profitable trading strategy based on BGSA-SVM prediction can be realized in a real stock market.

Automated summary

A hybrid Support Vector Machine (SVM) model is proposed and applied to forecast the daily returns of five popular stock indices. By utilizing the Binary Gravity Search Algorithm (BGSA), the parameters and inputs of SVM are optimized. The results demonstrate that the forecasts made by this model outperform other methods, with an average accuracy of 52.87%. This study proves the profitability of a trading strategy based on BGSA-SVM prediction in a real stock market.