Business Analytics and Data Mining Techniques for Banking Industry

This report analyzes the applications of business intelligence analytics and data mining techniques in the banking industry. It explores the opportunities and challenges associated with these techniques for decision making.

University
Semester
TECH7406- Business Intelligence and Data
Warehousing
Research Report
Individual Report – 1 Banking Industry
Student ID
Student Name
Submission Date
1

Table of Contents
Introduction...........................................................................................................................................3
Business Analytics and Data mining Techniques for Banking Industry................................................3
Applications of the Banking Industry....................................................................................................4
Business Opportunities..........................................................................................................................5
Challenges.............................................................................................................................................5
Conclusion.............................................................................................................................................6
References.............................................................................................................................................6
2

Introduction
The main objective of this project is to prepare the report to analysis the business
analytics and data mining techniques to the selected domains, here we have chosen the
banking industry and, also this report is used to review the applications of business
intelligence analytics and data mining in the same industry for decision making. This project
is used to enable users to understand how business intelligence analytics and data mining
technique revolutionize business today.
In this project, the focus is on the following aspects:
 Business analytics and data mining techniques
 Applications of the banking industry.
 Generation of new opportunities for the respective industry.
 Analysis of challenges associated with the application of business
analytics and data mining techniques.
Business Analytics and Data mining Techniques for Banking Industry
The business analytics and data mining techniques are playing an imperative role in
banking industry. The banking sector is extremely competitive, then it is sensitive to
economic and political situations throughout the world, because it has numerous risks and
key strategies for various banks in order to improve their performance, including increasing
the revenues and reducing the costs (Biswas and Bishnu, 2015). Basically banking industry,
the data acts a main asset of the organization since valuable interesting, including knowledge
patterns are hidden. Thus, the data mining is used to discover the process of data analysis
from various perspectives and summarizing it into beneficial information which is utilized for
increasing the costs and revenues. It involves the below processes like:
 Data cleaning
 Data pre - processing
 Data transformation
 Data integration
 Data mining
 Data presentation
 Pattern evaluation
3

The data mining techniques are listed in below.
 Association - The correlation and association is utilized to determine the often
utilized data items in a large data set. It also finds the patterns where one event is
connected to the other.
 Clustering - It could be stated as identification of same classes of objects. It is
used to combine the transactions with similar behavior into customer with same
set of the transaction into one group. It is used to provide the effective mean of
unique the groups.
 Fore casting - It is regression technique which could be modified to complete
prediction. It is used to model the relationship between the more than one
dependent and independent variable. It is sued to discovering the patterns form
which one can create the sensible prediction.
 Classification - It is a widely applied data mining technique that is used to
employ a set of pre-classified in order to develop a model which could classify the
records’ population largely. It is utilized for estimating the classification rules’
accuracy (Jayasree, 2013).
Applications of the Banking Industry
The Data mining techniques application in the banking sector is represented as below.
 Customer Relationship Management
The system of customer relationship management for banking is very helpful
to create the brand value and understand and identify the customer needs by providing
the timely targeted and relevant information which is used to add the value to their
customers. It is utilized for creating customer profiling to group all the customers who
are likeminded. It is also used for discovering new customers by using the clustering
technique and it retain the customer to perform the market basket analysis which is
used to discovering the co-occurring items.
 Fraud Detection
It used to detect the actions of fraud in baking because the fraudulent is the
increasing distress for various types of business. Fraud detection is used to detect and
report the fraudulent actions by using the two approaches. The first approach is to
detect the bank taps which the third party’s data warehouse and the data mining utilize
4

to detect the fraud detections. The second approach is utilized for identifying the fraud
pattern in the banking sector (Jisha and Kumar, 2018).
Business Opportunities
The techniques of data mining are used for adding business value and to generate new
business opportunities within the banking industry. Marketing industry is the broadly utilized
areas of data mining.
In marketing, the banking department uses business analytics and data mining
techniques which are used to analyze customer databases and also it analyzed the data
collected for deciding the behavior of the consumer in terms of price, distribution and product
channel. It can analyze the previous patterns, evaluate the current demand and forecast the
customer behavior related to many products and services to increase the business
opportunities and foresee the behavioral patterns.
The techniques of data mining are used for identifying the profitable and non-
profitable customers and it is even utilized for determining how the customers reflect to the
adjustments in the interest rates, and customer segment’s risk profile for defaulting on the
loans.
Challenges
The challenges that are associated with the application of business analytics and data
mining for banking industry are illustrated below:
 Lack of transparency
 Small size of revenues do not justify the additional costs
 Traditional banking habits
 Security and Fraud instances
 Consumer Expectation
 Regulatory Pressure
Conclusion
5

This project was successfully prepared the report which is effectively analyze data
mining techniques and business analytics of Banking industry and, also this report is also
effectively reviews the applications of business intelligence analytics and data mining with
respect to the banking industry for decision making contents. This project is used to enable
user to understand the how business intelligence analytics and data mining technique
revolutionize business today. This report has focused on data mining techniques and Business
analytics; its applications in the banking industry; generating new opportunities for banking
industry and finally, analyzes the challenges related to the data mining techniques and
business analytics’ application in the banking sector.
References
6

Biswas, P. and Bishnu, P. (2015). Application of Data Mining and CRM in Banking Sector
Medical Insurance. International Journal of Innovative Research in Computer and
Communication Engineering, 03(01), pp.38-46.
Jayasree (2013). A REVIEW ON DATA MINING IN BANKING SECTOR. American
Journal of Applied Sciences, 10(10), pp.1160-1165.
Jisha, M. and Kumar, D. (2018). A CASE STUDY ON DATA MINING APPLICATIONS
ON BANKING SECTOR. International Journal of Computer Sciences and Engineering,
06(08), pp.67-70.
7