Paper A

Process-Metric-Based Defect Prediction at Scale

Six ML classifiers benchmarked head-to-head on 296,457 file instances across five mature OSS systems. Random Forest best at AUC 0.8998, F1 0.6355 binary, F1 0.7595 macro.

Paper B

Cross-Repository Transfer Learning

Leave-one-repository-out evaluation across five mature open-source projects. Cross AUC 0.867, cross F1 0.631; AUC–F1 asymmetry analysis and defect-rate mismatch as the primary degradation driver.

Paper C

Risk-Based CI/CD Test Prioritisation

Top 10% of files capture 43.82% of defects (4.37× risk-vs-random lift; 81.4% of the oracle ceiling). Production deployment as a FastAPI microservice triggered by GitHub Actions.

Paper D

Self-Healing Web Test Automation

Tree-ensemble locator ranking over eight DOM feature families. Mutation-based evaluation across 2,400 events and seven refactor classes; heuristic + ML hybrid with calibrated confidence gating.

Paper E

LLM-Based Test Case Generation

RAITG framework converting 312 natural-language requirements across three domains into executable tests. 94.1% requirement coverage, 96.3% first-pass verification, 68% effort reduction.

Paper F

Post-Execution Defect Attribution

An empirical comparison of four post-execution attribution methods on 6,000 synthetic failure events, fusing dynamic test-failure signals (stack traces, suspect-set ranking) with repository priors to produce practitioner-actionable triage, not just ranked file lists. Under review at Springer EMSE.

bdd2pw · sel2pw

Test-Automation Tooling & Modernization

Live-DOM page-object scaffolding from Gherkin specs via the Microsoft Playwright MCP (bdd2pw), and deterministic, AST-based migration from Selenium to Playwright TypeScript (sel2pw, validated on 409 Java files with 0 conversion failures). Both under review (Elsevier SoftwareX / Software Impacts) and published as npm packages.

Paper G1

Software Fraud Detection & Information Security

A deterministic timeline engine for detecting employment-experience fraud at scale, paired with an adversarial robustness study against AI-generated fakes (TruthHire). Submission-ready for Taylor & Francis Information Security Journal: A Global Perspective.

Cross-cutting

AI Governance for Quality Engineering

Unified governance rail across all services: payload controls, content redaction, author privacy hashing, prompt versioning, and verifiable audit trails for every model call.

Methodology

Reproducible Empirical Software Engineering

Every result on this site is reproducible from on-disk artefacts — trained models, CSVs, JSONs, and figures. Honest threats-to-validity disclosures including the resolved file_age_days sign bug.