Artificial Intelligence and Fraud Detection of Listed Deposit Money Banks in Nigeria

The study examined the impact of artificial intelligence on fraud detection of listed deposit money banks in Nigeria. Fraud detection was used as independent variable while Artificial intelligence was used as the independent variable. The determinants of artificial intelligence in this study will be automated chatbot, deep learning machine, machine learning solutions and natural language processing. The geographical coverage of this study will be in Nigeria. The study will cover 11years spanning from 2012 to 2022; within this period CBN introduced cashless policy into the Nigerian Financial system. More so, a lot of Banks introduced artificial intelligence into their operations within this period. This study employ survey design, Therefore the study employed a survey method of data collection, via a self-administered questionnaire. The data was collected from deposit money banks in Kaduna state. Out of the 14 Listed Deposit money Banks in Nigeria, 10 banks will be selected based on simple random Sampling Technique. The tool will be statistical Package for Statistical sciences (SPSS) version 20. Regression analysis will be used to predict the effect of the independent variable on the dependent variable and also used to either accept or reject null hypothesis. Validity and reliability test will be carried out. The result from Table 4.6 reveals that automated chat boat has a coefficient value of 0.413 and P-value 0.000. This signifies that automated chat boat has a positive and significant influence on deposit money banks. The regression model in Table 4.6 indicated that deep learning machine has a coefficient value 0.212 and P value 0.009. This signified that deep learning machine is positively and significantly impacting fraud detection among deposit money bank. From the Table 4.6 it was observed that machine learning solution has a coefficient value 0.172 and P value 0.069. This shows that machine learning solution is positively but not significant in detecting fraud. From the Table 4.6 the finding shows that natural learning process has a coefficient value -.207 and P value 0.230 this indicates that natural learning process is insignificant on fraud detection. Huge investment in acquisition of deep learning machine should be ensured in order to boost fraud detection and protection in credit issuing and assessment in order to improve corporate performance of banks.

Authors

Institutions

Publication Details

Journal
JOURNAL OF ACCOUNTING AND FINANCIAL MANAGEMENT
Published
2026-11-16
DOI
https://doi.org/10.56201/jafm.v10.no9.2024.pg42.62
Primary Topic
Digital Transformation in Financial Services
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Artificial Intelligence and Fraud Detection of Listed Deposit Money Banks in Nigeria

Hussaini Hannah Ojone
4 links
JOURNAL OF ACCOUNTING AND FINANCIAL MANAGEMENT
Digital Transformation in Financial Services
article

Artificial Intelligence and Fraud Detection of Listed Deposit Money Banks in Nigeria

Hussaini Hannah Ojone
article en

Abstract

The study examined the impact of artificial intelligence on fraud detection of listed deposit money banks in Nigeria. Fraud detection was used as independent variable while Artificial intelligence was used as the independent variable. The determinants of artificial intelligence in this study will be automated chatbot, deep learning machine, machine learning solutions and natural language processing. The geographical coverage of this study will be in Nigeria. The study will cover 11years spanning from 2012 to 2022; within this period CBN introduced cashless policy into the Nigerian Financial system. More so, a lot of Banks introduced artificial intelligence into their operations within this period. This study employ survey design, Therefore the study employed a survey method of data collection, via a self-administered questionnaire. The data was collected from deposit money banks in Kaduna state. Out of the 14 Listed Deposit money Banks in Nigeria, 10 banks will be selected based on simple random Sampling Technique. The tool will be statistical Package for Statistical sciences (SPSS) version 20. Regression analysis will be used to predict the effect of the independent variable on the dependent variable and also used to either accept or reject null hypothesis. Validity and reliability test will be carried out. The result from Table 4.6 reveals that automated chat boat has a coefficient value of 0.413 and P-value 0.000. This signifies that automated chat boat has a positive and significant influence on deposit money banks. The regression model in Table 4.6 indicated that deep learning machine has a coefficient value 0.212 and P value 0.009. This signified that deep learning machine is positively and significantly impacting fraud detection among deposit money bank. From the Table 4.6 it was observed that machine learning solution has a coefficient value 0.172 and P value 0.069. This shows that machine learning solution is positively but not significant in detecting fraud. From the Table 4.6 the finding shows that natural learning process has a coefficient value -.207 and P value 0.230 this indicates that natural learning process is insignificant on fraud detection. Huge investment in acquisition of deep learning machine should be ensured in order to boost fraud detection and protection in credit issuing and assessment in order to improve corporate performance of banks.

JOURNAL OF ACCOUNTING AND FINANCIAL MANAGEMENT
Kaduna State University (NG)
Digital Transformation in Financial Services
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon