Stock market prediction using evolutionary support vector machines: an application to the ASE20 index

Andreas Karathanasopoulos, Konstantinos Athanasios Theofilatos, Georgios Sermpinis, Christian Dunis, Sovan Mitra, Charalampos Stasinakis
2015 European Journal of Finance  
This paper introduces a novel hybrid method for predicting the directional movement of financial assets with an application to the ASE20 Greek stock index. An alternative computational methodology named Evolutionary Support Vector Machine (ESVM) Stock Predictor is used for modeling and trading the ASE20 Greek stock index, extending the pool of the examined inputs to include autoregressive inputs and moving averages of the ASE20 index and other four financial indices. The proposed hybrid method
more » ... osed hybrid method is a combination of Genetic Algorithms (GAs) with Support Vector Machines (SVMs) modified to uncover effective short term trading models and overcome the limitations of existing methods. The trading performance of the ESVM stock predictor is benchmarked with four traditional strategies and a neural network model, namely a Naïve strategy, a Buy and Hold (BH) strategy, a Moving Average Convergence/Divergence (MACD) model, an Autoregressive Moving Average (ARMA) model and a Multi-Layer Perceptron (MLP). As it turns out, the proposed application produces a higher trading performance, even during the financial crisis, in terms of annualized returns and information ratios. Finally, this study provides evidence on the relationship between the ASE20 index and DAX30, NIKKEI225, FTSE100, S&P500 indices.
doi:10.1080/1351847x.2015.1040167 fatcat:dfevrcy3ybhq7a744ismhg23gi