Conversational AI for Intelligent Financial Services
Built for a Bank of Baroda use case, this chatbot revolutionizes credit card distribution by simulating human-like conversations and offering personalized financial recommendations.
Developed during a Founder's Office internship assignment, this project showcases the potential of LLM-powered assistants in banking automation.
Understands complex queries with contextual memory management.
Pulls info from FAQs & docs via ChromaDB semantic search.
Uses OpenAI + Flan-T5 to suggest tailored financial products.
Response time ~3ms thanks to optimized pipelines.
Achieved 80% accuracy in product recommendations, 95% context retention, and demonstrated production-ready pipelines for enterprise banking.