Products & Infrastructure
Software products, open-source libraries, and learning platforms taking problems from raw concept to shipped deployment.
FeatureSmith is an open-source, ML-focused Python library and Feature Engineering toolkit that makes tabular dataset quality checks as routine and automated as code reviews, supported by interactive examples and Jupyter notebooks.
Tabular datasets used in production machine learning models often suffer from unmonitored target leakage, silent schema drift, missingness spikes, and distribution anomalies. Unlike source code which undergoes strict automated linting and code reviews, datasets are often fed into compute-heavy model training loops blindly.
FeatureSmith provides a high-performance Python SDK and CLI powered by Polars that executes 8 automated dataset reviewers, generates explainable 0–100 ML readiness scorecards, flags 6 named target leakage patterns, and provides snapshot version diffing (fs.diff()) with a deterministic exit-code CI/CD gate.
RallyVerse is a sports marketing platform and community growth engine built for badminton tournament organizers, academies, and clubs in Bengaluru.
Grassroots sports event organizers and academies struggle with player acquisition, sponsorship visibility, manual UPI payment verification, and participant retention outreach.
Engineered a sports marketing web infrastructure platform providing dedicated tournament landing pages, automated UPI payment screenshot verification, organizer dashboards, and participant outreach channels.