ABSTRACT
Forecasting the weekly change movement of the DAX 30 index using support vector machines (SVMs) is the goal of this work. The inputs of the SVM are traditional technical trading rules commonly used in the analysis of equity markets such as relative strength index (RSI), moving average convergence/divergence (MACD), VDAX and the daily return of the DAX 30. The data cover the period between 3 January 2000 and 30 December 2011.
The outputs of the SVM are the movement of the market and the degree of set membership, from which the best situations to buy or sell the market are extracted. SVM training has found that VDAX indicator influence is quite significant when bearish periods appear. Results presented in this contribution show that including the VDAX indicator in the SVM training reduces the maximum drawdown (MDD) and increases the profit.
