-
Hyperparameter Optimization for Effort Estimation
Software analytics has been widely used in software engineering for many...
read it
-
How Different is Test Case Prioritization for Open and Closed Source Projects?
Improved test case prioritization means that software developers can det...
read it
-
Why Software Effort Estimation Needs SBSE
Industrial practitioners now face a bewildering array of possible config...
read it
-
Time-Aware Models for Software Effort Estimation
It seems logical to assert that the dynamic nature of software engineeri...
read it
-
Predicting Project Health for Open Source Projects (using the DECART Hyperparameter Optimizer)
Software developed on public platforms are a source of data that can be ...
read it
-
A deep learning model for estimating story points
Although there has been substantial research in software analytics for e...
read it
-
Revisiting Heterogeneous Defect Prediction: How Far Are We?
Until now, researchers have proposed several novel heterogeneous defect ...
read it
Sequential Model Optimization for Software Process Control
Many methods have been proposed to estimate how much effort is required to build and maintain software. Much of that research assumes a "classic" waterfall-based approach rather than contemporary agile projects. Also, much of that work tries to recommend a single method– an approach that makes the dubious assumption that one method can handle the diversity of software project data. To address these drawbacks, we apply a configuration technique called "ROME" (Rapid Optimizing Methods for Estimation), which uses sequential model-based optimization to find what combination of techniques works best for a particular data set. In this paper, we test this method using data from 1161 classic waterfall projects and 446 contemporary agile projects (from Github). We find that ROME achieves better performance (in terms of magnitude of relative error and standardized accuracy) than existing state-of-the-art methods for both classic and contemporary problems. From this work, we conclude that it is not best to recommend method for estimation. Rather, it is better to search through a wide range of different methods to find what works best for local data. To the best of our knowledge, this is the largest effort estimation experiment yet attempted and the only one to test its methods on classic and contemporary projects.
READ FULL TEXT
Comments
There are no comments yet.