Accurate software effort estimation is an important part of the software process. Originally, estimation was performed using only human expertise, but more recently, attention has turned to a variety of machine learning (ML) methods. This paper attempts to evaluate critically the potential of genetic programming (GP) in software effort estimation when compared with previously published approaches, in terms of accuracy and ease of use. The comparison is based on the well-known Desharnais data set of 81 software projects derived from a Canadian software house in the late 1980s. The input variables are restricted to those available from the specification stage and significant effort is put into the GP and all of the other solution strategies to offer a realistic and fair comparison. There is evidence that GP can offer significant improvements in accuracy but this depends on the measure and interpretation of accuracy used. GP has the potential to be a valid additional tool for software effort estimation but set up and running effort is high and interpretation difficult, as it is for any complex meta-heuristic technique.

Can genetic programming improve software effort estimation? A comparative evaluation

This paper presents a survey of evolutionary algorithms that are designed for decision-tree induction. In this context, most of the paper focuses on approaches that evolve decision trees as an alternate heuristics to the traditional top-down divide-and-conquer approach. Additionally, we present some alternative methods that make use of evolutionary algorithms to improve particular components of decision-tree classifiers. The paper's original contributions are the following. First, it provides an up-to-date overview that is fully focused on evolutionary algorithms and decision trees and does not concentrate on any specific evolutionary approach. Second, it provides a taxonomy, which addresses works that evolve decision trees and works that design decision-tree components by the use of evolutionary algorithms. Finally, a number of references are provided that describe applications of evolutionary algorithms for decision-tree induction in different domains. At the end of this paper, we address some important issues and open questions that can be the subject of future research.

/pdf/a-survey-of-evolutionary-algorithms-for-decision-tree-jo3sneclhc.pdf

A Survey of Evolutionary Algorithms for Decision-Tree Induction

https://www.comp.nus.edu.sg/~rudys/arnie/or-datamining.pdf

Operations research and data mining

http://decweb.bournemouth.ac.uk/staff/kphalp/jsspredict.pdf

An investigation of machine learning based prediction systems

Previous work on the solution to analytical electronic customer relationship management (eCRM) problems has used either data-mining (DM) or optimization methods, but has not combined the two approaches. By leveraging the strengths of both approaches, the eCRM problems of customer analysis, customer interactions, and the optimization of performance metrics (such as the lifetime value of a customer on the Web) can be better analyzed. In particular, many eCRM problems have been traditionally addressed using DM methods. There are opportunities for optimization to improve these methods, and this paper describes these opportunities. Further, an online appendix (mansci.pubs.informs.org/ecompanion.html) describes how DM methods can help optimization-based approaches. More generally, this paper argues that the reformulation of eCRM problems within this new framework of analysis can result in more powerful analytical approaches.

/pdf/on-the-use-of-optimization-for-data-mining-theoretical-1v9autj4rl.pdf

On the Use of Optimization for Data Mining: Theoretical Interactions and eCRM Opportunities

The CALTROP program which is presented in this paper provides a test of the feasibility of representing a decision tree as a linear chromosome and applying a genetic algorithm to the optimisation of the decision tree with respect to the classification of test sets of example data. The unit of the genetic alphabet (the “caltrop”) is a 3-integer string corresponding to a subtree of the decision tree. The program offers a user a choice of mating strategies and mutation rates. Test runs with different data sets show that the decision trees produced by the CALTROP program usually compare favourably with those produced by the popular automatic induction algorithm, ID3.

L. Morss

Papers

The Construction and Evaluation of Decision Trees: a Comparison of Evolutionary and Concept Learning Methods