Sharing Data and Models in Software Engineering

Chapter 9

Effort Estimation

Abstract

In this part of the book Data Science for Software Engineering: Sharing Data and Models, we offer some tutorial notes on commonly used software engineering applications of data mining, along with some tutorial material on data mining algorithms. Covered topics of SE problems include effort estimation and defect prediction. Covered aspects of data mining include discretization, column pruning (also known as feature selection), row pruning, clustering, contrast set learning, decision learning, and learning for continuous classes.

One of the earliest questions asked about SE data is “How much will it cost to develop this software?” In fact, the whole field of software engineering was founded on the economic ...