• Posa Anjan Kumar
• Dr. Manjula H M
• Manda Kuswanth Sri Sai Syamala Rao
• Swathi M
• Anusha A

Conversational AI technologies are transforming customer interactions across all industries by delivering automated, real time, instant support. The focus of this project is to create a chatbot for the banking industry to serve as a users' center to the questions; to evaluate a potential borrower's ability to secure a loan; and to filter out any spam. Specific machine learning tasks are exploited through the use of machine learning models targeted on particular tasks using RASA framework for conversation management and natural language understanding (NLU). The chatbot features include, precise intent detection, multi turn conversation handling, and a modular design that makes it easy for you to expand it in future. Meaningful results of evaluation show that these chatbots are ultimately performing very well with intent recognition, spam filtering, and loan eligibility assessment, suggesting that these chatbots will effectively contribute to improve user experience and operate with greater efficiency. This work sets the stage for future work from exploring the opportunities for voice activated conversational AI in other industries like banking.

Chatbot, Conversational AI, Banking Sector, NLU, Machine Learning, RASA Framework, User Experience, Loan Eligibility, Intent Recognition, Spam Filtering.

"Customer Support Chatbot with Machine Learning for Banking System: Spam Detection and Customer Assistance", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 1, page no.d184-d194, January-2025, Available :http://www.jetir.org/papers/JETIR2501320.pdf

"Customer Support Chatbot with Machine Learning for Banking System: Spam Detection and Customer Assistance", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 1, page no. ppd184-d194, January-2025, Available at : http://www.jetir.org/papers/JETIR2501320.pdf