Modelling bank customer behaviour using feature engineering and classification techniques

Mohammad Abedin, Petr Hajek, Taimur Sharif, Md. Shahriare Satu, Md. Imran Khan

Research output: Contribution to journalArticlepeer-review


This study investigates customer behaviour and activity in the banking sector and uses various feature transformation techniques to convert the behavioural data into different data structures. Feature selection is then performed to generate feature subsets from the transformed datasets. Several classification methods used in the literature are applied to the original and transformed feature subsets. The proposed combined knowledge mining model enable us to conduct a benchmark study on the prediction of bank customer behaviour. A real bank customer dataset, drawn from 24,000 active and inactive customers, is used for an experimental analysis, which sheds new light on the role of feature engineering in bank customer classification. This paper’s detailed systematic analysis of the modelling of bank customer behaviour can help banking institutions take the right steps to increase their customers’ activity.
Original languageEnglish
Article number101913
JournalResearch in International Business and Finance
Publication statusPublished - 1 Mar 2023


Dive into the research topics of 'Modelling bank customer behaviour using feature engineering and classification techniques'. Together they form a unique fingerprint.

Cite this