Our Heritage ISSN: 0474-9030 Vol-67-Issue-10-December-2019 Page | 1762 Copyright ⓒ 2019Authors APPLICATION OF DATA MINING IN BANKING AND FINANCE Dr. Sachin Kashyap * , Dr. Abhishek Pandey * , Dr. Sanjeev Gupta * 1,2 Assistant Professor, Mittal School of Business Lovely Professional University, Phagwara, Punjab 3 Professor, School of Business & Management Studies, Central University of Himachal Pradesh, Dharamshala, H.P. Abstract Presently, banks and other financial institutions have to preserve the huge electronic data through fixation of reliable information in the data warehouses. It is illogical to detect the trend or pattern buy a human being so as to know the required information available from the huge data sources. The big giants in this field are very much fast in diagnosing this concept, resultantly the software market worldwide for data mining is expected to surpass ten billion United states dollar. This message is proposed for the financial institutions who would like to know the probable applications of data mining so as to increase their core business performance. In this paper, the wide application of data mining techniques say fraud detection, risk management, client profiling and consumer care has been discussed, where artificial intelligence techniques may be applied by banks to work efficiently. Keywords: Data Mining (DM), Artificial Intelligence (AI), Business Intelligence (BI), Risk Management, Customer Relationship Management, Support Vector Machine (SVM) 1. Introduction- In the current commercialisation era, the significance of information and evidence can never be seen as an outward factor of the business. Because the flow of knowledge contributes to wealth creation, so the strategy as a base is not superior than the information flow for competing in the current marketplace (Jayasree and Balan 2013). In the globalization era and hand to neck competition, the practitioners must have the precise information at the exact time contributing to the success of the organisation. Across the globe, banks and other financial organizations have to maintain large automated data sources and reliable information is entrenched in these data mines (Rajanish, 2006). The gigantic magnitude of these factual sources makes it hard for a financial analyst to use that information for right decision-making. Large number of the business enterprises have identified lot of scope in this field, resultantly of which the data mining software marketplace is projected to be ten billion dollars approximately by 2023. For better decision making, the business intelligence systems accentuate on extracting of knowledge from several internal and external electronic data storehouses. So, DM is playing significant role in discovering knowledge from the data warehouse (Malekpour et. al.2014). In the last years, the business intelligence techniques have performed pivot role in assisting the organizations to revive their business areas say fraud detection, brand promotion, client retention, efficiency and market saturation, where the decisions are taken through the historical data analysis (Desai and Kulkarni, 2013). Handling worldwide competitions with fast reduction cycle of technical innovation produces a challenging environment for the banking and finance sector. Quick accessibility of Global information