International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 10 Issue: 05 | May 2023
p-ISSN: 2395-0072
www.irjet.net
BANKING CHATBOT USING NLP AND MACHINE LEARNING ALGORITHMS B. Divija1, M. Pushpa Pavani2, S. Aashritha Reddy3, Mrs. Aruna Kumari4 1,2,3B.Tech Scholars, Dept. Electronics and Computer Engineering,SNIST,Hyderabad-501301,India
4Assistant Professor, Dept. Electronics and Computer Engineering, SNIST, Hyderabad-501301, India
---------------------------------------------------------------------***--------------------------------------------------------------------experience. Here we create a customer front-end application Abstract: The increasing demand for efficient and which further enhances the customer experience. This hypothesis is supported by previously published literature that highlights the potential benefits of chatbot systems in enhancing customer service in various industries, including banking. To reduce the burden on human customer service representatives and provide customers with immediate assistance at any time. The base paper of this project is a literature survey of previously published works that have explored the use of chatbot systems in customer service. The base paper highlights the potential benefits of using NLP and ML algorithms in developing chatbot systems that can handle complex customer inquiries and provide accurate responses in natural language.
personalized customer service in the banking industry has led to the development of Chatbot technology. In this project, we propose the development of a Bank Chatbot, which acts as an intelligent agent and provides personalized customer experience using Natural Language Processing (NLP) and Machine Learning (ML) techniques. The Bank Chatbot will be designed to handle customer inquiries, such as account balance, transaction history, and account details, in a conversational and intuitive manner. The data for this project is collected from open source like Github or Kaggle and perform the implementation. The Bank Chatbot will be trained on a large dataset of customer queries and responses, using state-of-the-art Natural Language Processing (NLP) techniques for text pre-processing and Machine Learning (ML) models such as Support Vector Machine (SVM) and Navie Baye’s (NB) Classifier. The conclusion is based on the present performance of the system can be further improved by using advanced machine learning algorithms such as Naive Bayes having 90.6% accuracy which has shown better accuracy than SVM is having the accuracy of 76.2% and highlights the potential benefits of using chatbots in the banking industry. This will enable the system to understand and respond to customer queries accurately and efficiently, then we will create a front- end application by connecting it to a server and provide answers to the queries. Hence, a convenient customer and bank interface can be developed.
II. Literature Survey (Background study) a. Title- Review on implementation techniques of chatbot: The methodology employed for this paper is a critical review of chatbots and their current development strategies. The study primarily relies on the analysis of existing literature in the field of chatbots and AI, including academic research papers, industry reports, and online publications. The review is focused on exploring the functionalities and limitations of chatbots, the available development frameworks, and the underlying technologies that support their implementation. The study reveals that chatbots are intelligent systems developed using AI and NLP algorithms that interface with users and answer inquiries. They are widely used by organizations, government associations, and non-profit organizations, and are deployed by financial institutions, online retail stores, and startups. The review highlights the challenges and limitations of chatbot development, including the handiness and flexibility of real dialogues. Also, popular intelligent personal assistants such as Amazon's Alexa, Microsoft's Cortana, and Google's Google Assistant are identified in the study. The capabilities of these automated assistants are lacking and today's chatbots use rule-based methods, intuitive machine learning algorithms or retrieval techniques that do not produce satisfactory results.
Index Terms— Chat bot, bank, classification, NLP, Machine Learning, Streamlit.
I. Introduction BANKING CHATBOT using NLP and Machine Learning is a project aimed at developing a chatbot system for banks that can assist customers with their inquiries, account information, and transactions. This system will utilize Natural Language Processing (NLP) and Machine Learning (ML) algorithms to provide an intelligent and personalized customer experience. Developing a chatbot system that meets these requirements presents several challenges. The system must be able to accurately understand and interpret customer inquiries, which can vary in complexity and language. The system must also be able to handle a high volume of customer inquiries simultaneously, ensuring that wait times are minimized. Additionally, the system must be able to recognize and personalize responses based on customer history and preferences to provide a more tailored
© 2023, IRJET
|
Impact Factor value: 8.226
b.Title-Enterprise Crowd Computing for Human Aided Chatbots: The methodology used in this paper involved a literature review of existing research on chatbots, their limitations, and the concept of Human Aided Chatbots. The paper also
|
ISO 9001:2008 Certified Journal
|
Page 475