Evolutionary rule-based system for IPO underpricing prediction

Academic literature has documented for a long time the existence of important price gains in the first trading day of initial public offerings (IPOs).Most of the empirical analysis that has been carried out to date to explain underpricing through the offering structure is based on multiple linear regression. The alternative that we suggest is a rule-based system defined by a genetic algorithm using a Michigan approach. The system offers significant advantages in two areas, 1) a higher predictive performance, and 2) robustness to outlier patterns. The importance of the latter should be emphasized since the non-trivial task of selecting the patterns to be excluded from the training sample severely affects the results.We compare the predictions provided by the algorithm to those obtained from linear models frequently used in the IPO literature. The predictions are based on seven classic variables. The results suggest that there is a clear correlation between the selected variables and the initial return, therefore making possible to predict, to a certain extent, the closing price.

[1]  K. De Jong,et al.  Using Genetic Algorithms for Concept Learning , 2004, Machine Learning.

[2]  Martin Casdagli,et al.  Nonlinear Modeling And Forecasting , 1992 .

[3]  Pedro Isasi Viñuela,et al.  Forecasting Time Series by Means of Evolutionary Algorithms , 2004, PPSN.

[4]  William L. Megginson,et al.  Venture Capitalist Certification in Initial Public Offerings , 1991 .

[5]  Hans-Paul Schwefely,et al.  Evolutionary Algorithms: Some Very Old Strategies for Optimization and Adaptation , 1992 .

[6]  Norman H. Packard,et al.  A Genetic Learning Algorithm for the Analysis of Complex Data , 1990, Complex Syst..

[7]  Brian M. Neuberger,et al.  A Study of Underwriters' Experience With Unseasoned New Issues , 1974 .

[8]  Steven Manaster,et al.  Initial Public Offerings and Underwriter Reputation , 1990 .

[9]  Brian M. Neuberger,et al.  Unseasoned New Issue Price Performance on Three Tiers: 1975-1980 , 1983 .

[10]  Kenneth A. De Jong,et al.  Using genetic algorithms for concept learning , 1993, Machine Learning.

[11]  David B. Fogel,et al.  An introduction to simulated evolutionary optimization , 1994, IEEE Trans. Neural Networks.

[12]  Kyung-shik Shin,et al.  A genetic algorithm application in bankruptcy prediction modeling , 2002, Expert Syst. Appl..

[13]  P. Spindt,et al.  How investment bankers determine the offer price and allocation of new issues , 1989 .

[14]  Mark Grinblatt,et al.  Signalling and the Pricing of New Issues , 1989 .

[15]  P. Rousseeuw.  Multivariate estimation with high breakdown point , 1985 .

[16]  John W. Peavy,et al.  Initial Public Offerings: Daily Returns, Offering Types and the Price Effect , 1987 .

[17]  Hayne E. Leland,et al.  INFORMATIONAL ASYMMETRIES, FINANCIAL STRUCTURE, AND FINANCIAL INTERMEDIATION , 1977 .

[18]  Scott Smart,et al.  Control as a Motivation for Underpricing: A Comparison of Dual- and Single-Class Ipos , 2000 .

[19]  Dorothea Heiss-Czedik,et al.  An Introduction to Genetic Algorithms. , 1997, Artificial Life.

[20]  William H. Sackley.  Why Has IPO Underpricing Changed over Time , 2005 .

[21]  K. Hanley,et al.  The underpricing of initial public offerings and the partial adjustment phenomenon , 1993 .

[22]  C. Janikow.  A Knowledge-Intensive Genetic Algorithm for Supervised Learning , 2004, Machine Learning.

[23]  Peter J. Rousseeuw,et al.  Robust Regression and Outlier Detection , 2005, Wiley Series in Probability and Statistics.

[24]  Bharat A. Jain,et al.  On investment banker monitoring in the new issues market , 1999 .

[25]  Robert S. Hansen,et al.  Underwriter Compensation and Corporate Monitoring , 1992 .

[26]  Jerzy J. Korczak,et al.  Evolution Strategy in Portfolio Optimization , 2001, Artificial Evolution.

[27]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[28]  Stephen F. Smith,et al.  A learning system based on genetic adaptive algorithms , 1980 .

[29]  Bharat A. Jain,et al.  Artificial Neural Network Models for Pricing Initial Public Offerings , 1995 .

[30]  Franklin Allen,et al.  Using genetic algorithms to find technical trading rules , 1999 .

[31]  Kent L. Womack,et al.  Strategic IPO Underpricing, Information Momentum, and Lockup Expiration Selling , 2001 .

[32]  P. J. Hughes,et al.  Stock Prices and the Supply of Information , 1991 .

[33]  D.E. Goldberg,et al.  Classifier Systems and Genetic Algorithms , 1989, Artif. Intell..