Researchers are drowning in choice as to how to build software quality optimizers, programs that find project options that change quality measures like defects, development effort (total staff hours), and time (elapsed calendar months). However, given many possible changes to a software project, which ones are recommended?

Two distinct strategies seek out this goal. Model-based methods seek a more general abstractions to describe software projects. Case-based methods instead seek local lessons based entirely from historical cases, referred here as model-lite. Given that case-based methods do not rely on an underlying model, they can be quickly adapted to a new domain and maintained by simply adding more cases.

W2 is an case-based recommendation algorithm that seeks to improve software quality without constructing a general model. This thesis aims to justify the use of a simple, data-agnostic approach compared to a more sophisticated, data-specific model-based approach known as SEESAW.

We search for project recommendations within data from eight projects using various AI tools: six model-based methods and one case-based method, W2. Results were assessed by comparing effort, defects, development time values in the raw data versus the subset of the data selected by those recommendations.

In the majority case, significantly large reductions on effort, defects and development time were achieved. Further, W2 performed as well, or better, than any other methods in this study. While W2 offers no conclusion on case-based vs model-based methods overall, our results show that simpler algorithms can be just as useful if not more so.