Using genetic algorithms to optimize software quality estimation models
Bibliographic record
Abstract
Assessing software quality is fundamental in the software developing field. Most software quality characteristics cannot be measured before a certain period of use of the software product. However, they can be predicted or estimated based on other measurable quality attributes. Software quality estimation models are built and used extensively for this purpose. Most such models are constructed using statistical or machine learning techniques. However, in this domain it is very hard to obtain data sets on which to train such models; often such data sets are proprietary, and the publicly available data sets are too small, or not representative. Hence, the accuracy of the models often deteriorates significantly when they are used to classify new data. This thesis explores the use of genetic algorithms for the problem of optimizing existing rule-based software quality estimation models. The main contributions of this work are two evolutionary approaches to this optimization problem. In the first approach, we assume the existence of several models, and we use a genetic algorithm to combine them, and adapt them to a given data set. The second approach optimizes a single model. The core concept of this thesis is to consider existing models that have been constructed on one data set and adapt them to new data. In real applications, this can be seen as adapting already existing software quality estimation models that have been constructed on data extracted from common domain knowledge to context-specific data. Our technique maintains the white-box nature of the models which can be used as guidelines in future software development processes.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.012 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".