Vijay Prasad Javvadi Independent Research · IEEE Senior Member · 2026

Vijay Prasad Javvadi

AI-Driven Software Quality Engineering

Building the empirical foundation for predictive software quality — two peer-reviewed publications (Elsevier SoftwareX; ICOSAAS 2026) and eight manuscripts submitted for peer review across Wiley, Springer, Elsevier, PeerJ, and Taylor & Francis, plus eight open-source npm packages and the TestForge AI platform in public beta. Mining 296,457 file instances across five open-source systems to make defect prediction, self-healing test automation, and LLM-based test generation reliable enough to ship.

View Publications → System Architecture
2
Peer-reviewed publications
8
Manuscripts submitted for review
15,700+
npm package downloads
296,457
File instances analysed
Research Pillars

Three pillars, one quality-engineering platform

A research program that turns repository signals, LLMs, and runtime DOM analysis into measurable testing outcomes — and ships them as open-source tools.

Pillar 1

Predictive Analytics for Software Quality

Process-metric-based defect prediction at 296,457-instance scale across five mature OSS systems. Random Forest AUC 0.8998; cross-repository transfer F1 0.6306.
Pillar 2

Intelligent Automation Architecture

Self-healing locators via tree-ensemble ranking on 2,400 mutation events; LLM test generation with deterministic rule verification across three domains.
Pillar 3

Research-to-Production Translation

Risk-based test prioritisation with the gb-paper1-v4 model in a FastAPI microservice on GitHub Actions. Top 10% of files capture 43.82% of defects (4.37× lift).
Professional Memberships

Societies and fellowships

IEEE · Senior grade

IEEE Senior Member

Elevated to Senior Member grade in August 2026 by the IEEE Admission and Advancement Committee. Princeton/Central Jersey Section, Region 1. Member #102410437.

IEEE Computer Society

IEEE Computer Society Member

Member of the IEEE Computer Society since 2026, the world's largest scholarly computing society.

Fellowship

Fellow, Institute of Analytics (FIoA)

Admitted as a Fellow of the Institute of Analytics, London, in August 2026.

Live in public beta

TestForge AI — the production platform built from this research

Defect prediction, self-healing automation, LLM test generation, and risk-based prioritisation, wired together with a unified AI governance layer.

Visit testforge-ai.com → Product overview
New · Free beta

TestForge PaperQC — catch what reviewers will catch, before they do

A pre-submission QC pass for software-engineering manuscripts: venue fit, benchmarking against accepted peers, structure, honesty & integrity checks, and a submission-package review — with an acceptance-likelihood estimate and a prioritised action list before you hit submit.

Try paperqc.testforge-ai.com → PaperQC overview
Recent Work

Published and under review

Two peer-reviewed publications and a selection of manuscripts currently in peer review. Tap a title for details, or see the full list.

PUBLISHED · SoftwareX

bdd2pw: Live-DOM Page Object Scaffolding via Playwright MCP

Elsevier SoftwareX vol. 35, 2026 · DOI 10.1016/j.softx.2026.102933
PUBLISHED · ICOSAAS 2026

Detecting and Mitigating Flaky Tests in CI

A decision catalogue for quality-engineering teams · Scopus-indexed proceedings
UNDER REVIEW · JSEP

Cross-Repository Defect Prediction (LORO)

Leave-one-repository-out · Cross AUC 0.867 · F1 0.631
UNDER REVIEW · Discover Computing

Risk-Based Test Prioritisation

Top-10% files capture 43.8% of defects · 4.37× lift · CI/CD pattern
UNDER REVIEW · STVR

Self-Healing Test Automation

Tree-ensemble locator ranking · 2,400 mutation events · 7 refactor classes
UNDER REVIEW · EMSE

Memorised, Not Generated

Verbatim fixture recall in LLM-generated test data · 5 models · 8 public schemas

All publications →