Applications of Deep Learning in Banking and Financial Technology : A systematic literature review

Abstract

This paper examines the interplay between the expanding prevalence of deep learning (DL) models for obtaining consumer insights and the delivery of next-generation customer experiences in banking and financial services (BFS). The scientific community has taken notice of deep learning because of its striking effectiveness as a data processing tool for revealing previously unseen patterns. A thorough review of the literature is being carried out on the application of DL models in the most relevant sectors of finance and banking. The objective of this study is to perform a methodical assessment of the various advantages that have been achieved in the BFS sector through the utilisation of DL models. The aim of this research is to systematically evaluate the diverse benefits that have been attained in the BFS industry by employing DL models. This study centres on the utilisation of deep learning models to identify anomalies, implement anti-money laundering (AML) practises, and track customer churn with the aim of improving customer loyalty. Our systematic literature review (SLR) has determined that these business domains have attracted the majority of research. We additionally draw attention to unresolved studies in this developing area to back up the data-driven programming paradigm of the future and its possible impact on the BFS industry. The objective of this study is to offer scholars and professionals with knowledge and direction regarding the present and forthcoming utilisation of DL models in the BFS industry.