BIDA-100 Introduction to Business Intelligence and Data Analytics

Proposed activity – aims, objectives, research question(s), and state how it is novel

Owing to the expansion of sophisticated equipment, low-cost technology, and creative business procedures, numerous research and engineering fields, medicine, business, and economics have created massive volumes of data in various forms during the last two decades. Analyzing this huge data and providing a better consumer experience with better data management have led to the genesis of Big Data Analytics (BDA). This work contributes to theory by filling a gap in the literature about the extent to which commercial banks in developing countries, like India, use big data analytics applications. It investigates the influence of big data analytics approaches on bank performance and consumer behavior experimentally.

This paper aims to examine the influence of big data analytics applications in the Indian Banking and Insurance sectors by comparing the bank performances in the following segments:

• Spending Pattern of customers through various platforms and channel usages
• Customer Segmentation and Profiling in Insurance Sectors
• Sentiment and feedback analysis

Objective: How data analysis can be used to predict Consumer Behaviour that can impact the financial performance of an institution.

Banks internationally are beginning to harness the power of data in order to derive utility across various spheres of their functioning, ranging from sentiment analysis, product cross selling, regulatory compliances management, reputational risk management, financial crime management and much more. Indian banks are catching up with their international counterparts; however a lot of scope remains.

Methodology – rationale, data selection and collection, recruitment, participant demographics, analytical process

A conceptual framework was developed in this regard based on a comprehensive literature review and the Technology–Environment–Organization (TEO) model. Customer behaviors are directly collected through the major touch-points of the banks in our study. These touch-points include call centers, point-of-sale systems, Web sites and other operational systems managed by the firms. Customer attitudes were collected through commissioned Market Research studies of the firms as well as corporate web surveys, customer panels and emerging technologies for text analysis and customer voice analysis.

The data used is secondary data (previous researchers, Government websites, articles and open-source data), while the analysis is of primary nature. A quantitative approach with a sample of 5 banking firms (public and private) covers a period of two financial years 2014-15 and 2015-16 is considered for this study.

The study measures customer satisfaction by Feedback Analysis and Inference. It also looks into transactional analysis and consumer spending pattern to find any correlation. Consumer behavior analysis based on Channel usage for the spending pattern, consumption patterns for Cross Selling, and Security and Fraud Analysis are also considered.

The analysis would be conducted using IBM SPSS Statistics and Google Analytics after combining the required data sets using Python and Excel.

Research Data Management Plan (Describe the data you expect to acquire or generate during this research project, how you will manage, describe, analyze, and store the data and what mechanisms you will use to share and preserve your data.)

As mentioned above under Methadology, Secondary Data Analysis/ Archival study are used for the research. Raw data sets and Annual reports from government websites, literature reviews, case studies and other sources would be used to conduct the analysis. In addition, a statistical analysis method with the help of SPSS and Google analytics is be used to test the relationship between the variables for a particular period.

Planned outputs/publications/research datasets/impact/dissemination

Aim to find the upward or downward trends in the optimal implementation of data analysis to predict consumer behaviors in the segments mentioned above. In addition, the factors affecting the company's overall performance due to the decision-making based on consumer behavior explored.