Data Analyst / Data Scientist – GenAI | HCLTech
INNODATA · Jun 2025 – Present
- Built end-to-end data pipelines using Python and SQL to extract, transform, validate, and analyze healthcare claims data from multiple sources.
- Performed data cleaning, missing-value treatment, duplicate removal, outlier detection, and feature transformation using Pandas and NumPy.
- Conducted EDA and feature engineering to identify abnormal billing patterns, duplicate claims, provider anomalies, and suspicious patient-provider behavior.
- Developed supervised ML models using Logistic Regression, Random Forest, and Gradient Boosting to classify potentially fraudulent claims.
- Applied anomaly detection and fraud-risk scoring to identify suspicious claims and high-risk providers.
- Evaluated models using Precision, Recall, F1-Score, ROC-AUC, Confusion Matrix, and false-positive analysis.
- Integrated Azure OpenAI and LLMs to generate natural-language summaries explaining fraud alerts and risk indicators.
- Developed RAG-based workflows using LangChain to retrieve relevant fraud rules and generate contextual investigation summaries.
- Applied Prompt Engineering to generate structured claim-risk explanations and developed Power BI dashboards for fraud monitoring and investigation KPIs.
- Collaborated with fraud, compliance, and business teams to validate analytical findings and improve fraud-detection rules.
- Automated fraud-risk reporting by integrating ML model outputs with analytical workflows, enabling faster identification and prioritization of high-risk healthcare claims for investigation.