Evolution Strategies for IPO Underpricing Prediction

David Quintana (), Cristobal Luque (), Jose Maria Valls () and Pedro Isasi ()
Additional contact information
David Quintana: Universidad Carlos III de Madrid
Cristobal Luque: Universidad Carlos III de Madrid
Jose Maria Valls: Universidad Carlos III de Madrid
Pedro Isasi: Universidad Carlos III de Madrid

Chapter Chapter 7 in Financial Decision Making Using Computational Intelligence, 2012, pp 189-208 from Springer

Abstract: Abstract The prediction of first-day returns of initial public offerings is a challenging task due, among other things, to an incomplete theory on the dynamics and the presence of outliers. In this chapter we introduce an evolutionary system based on prototypes adjusted by evolution strategies. The system, set up in two layers, breaks the input space into different regions and fits specialized sets of models. These models are then combined to offer predictions. The structure of the model is such that it is able to handle the extreme values that hinder prediction in this domain. The system is benchmarked against a set of well-known machine learning algorithms, and the results show competitive performance.

Keywords: Initial Public Offering (IPO); Underpricing; Waikato Environment For Knowledge Analysis (WEKA); Voronoi Region; Alternative Machine Learning (search for similar items in EconPapers)
Date: 2012
References: Add references at CitEc
Citations: View citations in EconPapers (1)

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:spochp:978-1-4614-3773-4_7

Ordering information: This item can be ordered from
http://www.springer.com/9781461437734

DOI: 10.1007/978-1-4614-3773-4_7

Access Statistics for this chapter

More chapters in Springer Optimization and Its Applications from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().