Proceedings of the 2021 3rd International Conference on Economic Management and Cultural Industry (ICEMCI 2021)

<Previous Article In Volume
Next Article In Volume>

The Application of Business Analytics in the Era of Big Data

Authors
Tianhuiqi Chen1, *,a, †, Bowen Gu2, *, b, †, Zhenxin Jin3, *, c, †
1School of St. George, University of Toronto, Toronto, Ontario, M5S, Canada.
2School of Resources and Safety Engineering, Central South University, Changsha, Hunan 300000, China
3College of Biomedical Engineering & Instrument Science, Zhejiang University, Hangzhou, Zhejiang 310000, China
†

These authors contributed equally.

*Corresponding author. Email:athq.chen@mail.utoronto.ca
Corresponding Authors
Tianhuiqi Chen, Bowen Gu, Zhenxin Jin
Available Online 15 December 2021.
DOI
10.2991/assehr.k.211209.274How to use a DOI?
Keywords
Business Analytics; Big Data; Banking Industry
Abstract

With the advent of the big data era, data-based business analytics is more and more widely used in all industries, in which banking with the loan business is one of the most important businesses. In order to conduct more intelligent risk control, banks often build prediction models based on loan records to assess whether future clients will default on loans, and the factors generally considered include income level, loan amount, interest rate, etc. This ultimately helps banks to optimize the loan business, avoid credit risks, and reduce losses. This paper focuses on the solutions of choosing appropriate prediction models, classifying the clients, and predicting their defaults. It clarifies the four-step framework of business analytics in the first part. Then this paper introduces three typical statistical analysis models, including the logistic regression model, the decision tree and random forest model, and the K-mean cluster model. The bank loan risk control dataset includes 20,000 borrowers and the details of personal information and loan information. Based on the dataset, the best prediction results are obtained using a random forest model that area under the curve is 0.741 and the clients are divided into four clusters. The logistic regression indicates a negative coefficient between the annual income and the default, while the coefficients are positive between other factors, like the loan amount and the interest rate and the default. In practical application, these models can be combined to give full play to their advantages and make a better prediction.

Copyright
© 2021 The Authors. Published by Atlantis Press International B.V.
Open Access
This is an open access article under the CC BY-NC license.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 2021 3rd International Conference on Economic Management and Cultural Industry (ICEMCI 2021)
Series
Advances in Economics, Business and Management Research
Publication Date
15 December 2021
ISBN
978-94-6239-483-4
ISSN
2352-5428
DOI
10.2991/assehr.k.211209.274How to use a DOI?
Copyright
© 2021 The Authors. Published by Atlantis Press International B.V.
Open Access
This is an open access article under the CC BY-NC license.

Cite this article

risenwbib
TY  - CONF
AU  - Tianhuiqi Chen
AU  - Bowen Gu
AU  - Zhenxin Jin
PY  - 2021
DA  - 2021/12/15
TI  - The Application of Business Analytics in the Era of Big Data
BT  - Proceedings of the 2021 3rd International Conference on Economic Management and Cultural Industry (ICEMCI 2021)
PB  - Atlantis Press
SP  - 1704
EP  - 1711
SN  - 2352-5428
UR  - https://doi.org/10.2991/assehr.k.211209.274
DO  - 10.2991/assehr.k.211209.274
ID  - Chen2021
ER  -