Integrating High Volume Financial Datasets to Achieve Profitable and Interpretable Short Term Trading with the FTSE100 Index
During the financial crisis of 2009 traditional models have failed to provide satisfactory results. Lately many techniques have been proposed to overcome the deficiencies of traditional models but most of them deal with the examined financial indices as they are cut off from the rest global market. However, many late studies are indicating that such dependencies exist. The enormous number of the potential financial time series which could be integrated to trade a single financial index enables the characterization of this problem as a “big data” problem and raises the need for advanced dimensionality reduction techniques which should additionally be interpretable in order to extract meaningful conclusions. In the present paper, ESVM-Fuzzy Inference Trader is introduced. This technique is based on the hybrid methodology ESVM Fuzzy Inference which combines genetic algorithms and some deterministic methods to extract interpretable fuzzy rules from SVM classification models.
The ESVM-Fuzzy Inference Trader was applied to the task of modeling and trading the FTSE100 index using a plethora of inputs including the closing prices of various European indexes. Its experimental results were compared with a state of the art hybrid technique which combines genetic algorithm with Multilayer Perceptron Neural Networks and indicated the superiority of ESVM-Fuzzy Inference Trader. Moreover, the proposed method extracted a compact set of fuzzy trading rules which among others can be utilized to describe the dependencies between other financial indices and FTSE100 index.
KeywordsTrading Strategies Financial Forecasting FTSE100 Genetic Algorithms Support Vector Machines Fuzzy logic
- 1.Dunis, C., Likothanassis, S., Karathanasopoulos, A., Sermpinis, G., Theofilatos, K.: Computational Intelligent Techniques for Trading and Investment. Advances in Experimental and Computable Economics. Taylor and Francis (2013) ISBN: 978-0-415-63680-3Google Scholar
- 7.Graham, M., Kiviaho, J., Nikkinen, J.: Short term and long-term dependencies of the S&P500 index and commodity prices 13(4), 583–592 (2013)Google Scholar
- 9.Theofilatos, K., Karathanasopoulos, A., Sermpinis, G., Amorgianiotis, T., Georgopoulos, E., Likothanassis, S.: Modelling and Trading the DJIA Financial Index Using Neural Networks Optimized with Adaptive Evolutionary Algorithms. In: Jayne, C., Yue, S., Iliadis, L. (eds.) EANN 2012. CCIS, vol. 311, pp. 453–462. Springer, Heidelberg (2012)CrossRefGoogle Scholar
- 10.Theofilatos, K., Amorgianiotis, T., Karathanasopoulos, A., Sermpinis, G., Geor-gopoulos, E., Likothanassis, S.: Advanced short-term forecasting and trading deploy-ing neural networks optimized with an adaptive evolutionary algorithm. In: Computational Intelligence Techniques for Trading and Investment, pp. 133–145. Routledge (2014)Google Scholar
- 11.Theofilatos, K., Pylarinos, D., Likothanassis, S., Melidis, D., Siderakis, K., Thalassinakis, E., Mavroudi, S.: A Hybrid Sup-port Vector Fuzzy Inference System for the Classification of Leakage Current Waveforms Portraying Discharges. Electric Power Components and Systems 42(2), 180–189 (2014)CrossRefGoogle Scholar
- 12.Papadimitriou, S., Terzidis, K.: Efficient and interpretable fuzzy classifiers from data with support vector learning. Intelligent Data Analysis 9(6), 527–550 (2005)Google Scholar
- 14.Pendaraki, K., Spanoudakis, N.: Constructing Portfolios Using Argumentation Based Decision Making and Performance Persistence of Mutual Funds. In: the 2nd International Symposium & 24th National Conference on Operational Research (EEEE 2013), pp. 24–29 (2013)Google Scholar