Combining Multiple Kernel Learning and Genetic Algorithm for Forecasting Short Time Foreign Exchange Rate

Shangkun Deng and Akito Sakurai


FX trading, Multiple Kernel Learning, Genetic Algorithm, MKL-GA Hybrid Model


This paper proposes a hybrid model named MKL-GA, which combines Multiple Kernel Learning (MKL) and Genetic Algorithm (GA), for modeling and the prediction of FX (foreign exchange) rate on USDJPY currency pair by extracting features from three main FX pairs with three different short time horizons. Firstly, the MKL regression model predicts the change rate based on MACD indicators, and then GA is applied to fuse all the information from the regression model and overbought/oversold technical indicators. Experiment results and comparisons show that the proposed model outperforms other models in terms of returns and risk-return ratio. In addition, the result of kernel weights for different currency pairs in the step of MKL training should be also advisable for the trading.

Important Links:

Go Back