Multilingual Conversational AI for Financial Assistance: Bridging Language Barriers in Indian FinTech
This addresses financial inclusion for India's linguistically diverse population where only 10% understand English, though it appears incremental as it applies existing methods to a new domain.
The paper tackles the problem of language barriers in Indian FinTech by developing a multilingual conversational AI system that supports code-mixed languages like Hinglish, resulting in significant improvements in user engagement with low latency overhead of 4-8%.
India's linguistic diversity presents both opportunities and challenges for fintech platforms. While the country has 31 major languages and over 100 minor ones, only 10\% of the population understands English, creating barriers to financial inclusion. We present a multilingual conversational AI system for a financial assistance use case that supports code-mixed languages like Hinglish, enabling natural interactions for India's diverse user base. Our system employs a multi-agent architecture with language classification, function management, and multilingual response generation. Through comparative analysis of multiple language models and real-world deployment, we demonstrate significant improvements in user engagement while maintaining low latency overhead (4-8\%). This work contributes to bridging the language gap in digital financial services for emerging markets.