← Back to Portfolio

Hindi News Summarizer

State-of-the-art summarization methods for Hindi news articles using BART and T5 models. Achieved Rouge-2 score of 21.48 with IndicBART. Deployed as API on Hugging Face Spaces.

NLP BART Hugging Face

Customer Churn Analysis

ML system to identify customers likely to leave. Ensemble methods (KNN, Random Forest, AdaBoost, XGBoost) achieving 94% recall for at-risk customer identification.

ML Ensemble XGBoost

LegSum - Legal Documents Summarization

Legal document summarization using transformer models (T5, BART, PEGASUS, LED). Evaluated on BillSum dataset with both abstractive and extractive methods.

Legal AI Transformers NLP

Indian Legal Corpus (ILC)

Dataset of 3,000+ Indian legal judgments with summaries. Published research on legal document summarization with fine-tuned LED model on Hugging Face.

Legal AI Dataset Research