Profit guided or statistical error guided? a study of stock index forecasting using support vector regression
- 87 Downloads
Stock index forecasting has been one of the most widely investigated topics in the field of financial forecasting. Related studies typically advocate for tuning the parameters of forecasting models by minimizing learning errors measured using statistical metrics such as the mean squared error or mean absolute percentage error. The authors argue that statistical metrics used to guide parameter tuning of forecasting models may not be meaningful, given the fact that the ultimate goal of forecasting is to facilitate investment decisions with expected profits in the future. The authors therefore introduce the Sharpe ratio into the process of model building and take it as the profit metric to guide parameter tuning rather than using the commonly adopted statistical metrics. The authors consider three widely used trading strategies, which include a na¨ıve strategy, a filter strategy and a dual moving average strategy, as investment scenarios. To verify the effectiveness of the proposed profit guided approach, the authors carry out simulation experiments using three global mainstream stock market indices. The results show that profit guided forecasting models are competitive, and in many cases produce significantly better performances than statistical error guided models. This implies that profit guided stock index forecasting is a worthwhile alternative over traditional stock index forecasting practices.
KeywordsFinancial market investment trading strategy parameter optimization stock index forecasting support vector regression
Unable to display preview. Download preview PDF.
- Atsalakis G S and Valavanis K P, Surveying stock market forecasting techniques-part I: Conventional methods, Journal of Computational Optimization in Economics and Finance, 2010, 2(1): 45–92.Google Scholar
- Eberhart R C, Shi Y, and Kennedy J, Swarm Intelligence, Elsevier, 2001.Google Scholar
- Chiong R, Neri F, and McKay R I, Nature that breeds solutions. Ed. by Chiong R. Nature-Inspired Informatics for Intelligent Applications and Knowledge Discovery: Implications in Business, Science and Engineering. Chapter 1. Hershey, PA: Information Science Reference, 2009, 1–24.Google Scholar
- Bao Y K, Hu Z Y, and Xiong T, A PSO and pattern search based memetic algorithm for SVMs parameters optimization, Neurocomputing, 2013, 117(14): 98–106.Google Scholar
- Alexander S S, Price movements in speculative markets: Trends or random walks, Industrial Management Review, 1961, 2(2): 7–26.Google Scholar
- Inghelbrecht K, Heyman D, Pauwels S, et al., Technical trading rules in emerging stock markets, World Academy of Science, Engineering and Technology, 2012, 59: 2241–2264.Google Scholar
- Andrada-Félix J, Fernádez-Rodríguez F, García-Artiles M D, et al., An empirical evaluation of non-linear trading rules, Studies in Nonlinear Dynamics & Econometrics, 2003, 7(3): Article 4.Google Scholar
- Hsu C W, Chang C C, and Lin C J, A practical guide to support vector classification, Department of Computer Science, National Taiwan University, 2003. Available at: http://www.csie.ntu. edu.tw/˜cjlin/papers/guide/guide.pdf, 2003.Google Scholar
- Chang C C and Lin C J, LIBSVM: A library for support vector machines, ACM Transactions on Intelligent Systems and Technology, 2001, 2(3): 27.Google Scholar