Hyperparameter Optimization for Effort Estimation

TL;DR

This paper introduces a new hyperparameter optimization architecture called OIL for improving software effort estimation accuracy, demonstrating significant improvements with efficient tuning methods on a large dataset.

Contribution

The paper presents OIL, a novel hyperparameter optimization framework for effort estimation, and identifies effective tuning strategies that outperform existing methods in accuracy and efficiency.

Findings

Large improvements in effort estimation accuracy after tuning.

Regression trees (CART) with evolutionary tuning are highly effective.

Tuning can reduce optimization time from weeks to hours.

Abstract

Software analytics has been widely used in software engineering for many tasks such as generating effort estimates for software projects. One of the "black arts" of software analytics is tuning the parameters controlling a data mining algorithm. Such hyperparameter optimization has been widely studied in other software analytics domains (e.g. defect prediction and text mining) but, so far, has not been extensively explored for effort estimation. Accordingly, this paper seeks simple, automatic, effective and fast methods for finding good tunings for automatic software effort estimation. We introduce a hyperparameter optimization architecture called OIL (Optimized Inductive Learning). We test OIL on a wide range of hyperparameter optimizers using data from 945 software projects. After tuning, large improvements in effort estimation accuracy were observed (measured in terms of standardized accuracy). From those results, we recommend using regression trees (CART) tuned by different evolution combine with default analogy-based estimator. This particular combination of learner and optimizers often achieves in a few hours what other optimizers need days to weeks of CPU time to accomplish. An important part of this analysis is its reproducibility and refutability. All our scripts and data are on-line. It is hoped that this paper will prompt and enable much more research on better methods to tune software effort estimators.