Tackling Overfitting in Evolutionary-Driven Financial Model Induction
This chapter explores the issue of overfitting in grammar-based Genetic Programming. Tools such as Genetic Programming are well suited to problems in finance where we seek to learn or induce a model from data. Models that overfit the data upon which they are trained prevent model generalisation, which is an important goal of learning algorithms.
Early stopping is a technique that is frequently used to counteract overfitting, but this technique often fails to identify the optimal point at which to stop training. In this chapter, we implement four classes of stopping criteria, which attempt to stop training when the generalisation of the evolved model is maximised.
We show promising results using, in particular, one novel class of criteria, which measured the correlation between the training and validation fitness at each generation. These criteria determined whether or not to stop training depending on the measurement of this correlation - they had a high probability of being the best among a suite of potential criteria to be used during a run. This meant that they often found the lowest validation set error for the entire run faster than other criteria.
KeywordsGenetic Programming Excess Return Generalisation Error Good Criterion Trading Rule
Unable to display preview. Download preview PDF.
- 2.Banzhaf, W., Nordin, P., Keller, R., Francone, F.: Genetic programming: An introduction. Morgan Kaufmann, San Francisco (1999)Google Scholar
- 3.Becker, L.A., Seshadri, M.: Comprehensibility and overfitting avoidance in genetic programming for technical trading rules. Worcester Polytechnic Institute, Computer Science Technical Report (2003)Google Scholar
- 4.Brabazon, A., Dang, J., Dempsey, I., O’Neill, M., Edelman, D.: Natural computing in finance: a review. In: Handbook of Natural Computing: Theory, Springer, Heidelberg (2010)Google Scholar
- 12.Luke, S., Panait, L.: Lexicographic parsimony pressure. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 829–836. Morgan Kaufmann, San Francisco (2002)Google Scholar
- 13.Luke, S., Panait, L.: A comparison of bloat control methods for genetic programming. IEEE Transactions on Evolutionary Computation 14(3), 309–344 (2006)Google Scholar
- 20.Poli, R., Langdon, W.B., McPhee, N.F.: A field guide to genetic programming. Lulu Enterprises, UK (2008)Google Scholar
- 22.Thomas, J.D., Sycara, K.: The importance of simplicity and validation in genetic programming for data mining in financial data. In: Proceedings of the Joint GECCO 1999 and AAAI 1999 Workshop on Data Mining with Evolutionary Algorithms: Research Directions, pp. 7–11 (1999)Google Scholar
- 23.Tuite, C., Agapitos, A., O’Neill, M., Brabazon, A.: A Preliminary Investigation of Overfitting in Evolutionary Driven Model Induction: Implications for Financial Modelling. In: Di Chio, C., Brabazon, A., Di Caro, G.A., Drechsler, R., Farooq, M., Grahl, J., Greenfield, G., Prins, C., Romero, J., Squillero, G., Tarantino, E., Tettamanzi, A.G.B., Urquhart, N., Uyar, A.Ş. (eds.) EvoApplications 2011, Part II. LNCS, vol. 6625, pp. 120–130. Springer, Heidelberg (2011)CrossRefGoogle Scholar
- 24.Tuite, C., Agapitos, A., O’Neill, M., Brabazon, A.: Early Stopping Criteria to Counteract Overfitting in Genetic Programming. In: Proceedings of the 13th Annual Conference on Genetic and Evolutionary Computation. ACM, New York (2011) (forthcoming)Google Scholar