1
|
[21]
|
2019
|
An investigation of the fraud risk and fraud scheme methods in Greek commercial banks
|
Money laundering
|
Chi-Square for association verification, correlation for determining internal consistency
|
Reliability = 87.2
|
2
|
[41]
|
2020
|
Managing a pool of rules for credit card fraud detection by a game
|
Credit card fraud
|
Shapley value for feature selection
|
F-score = 24.0
|
3
|
[13]
|
2022
|
Turning the tables: biased, imbalanced, dynamic tabular datasets for ML evaluation
|
New bank account fraud
|
GAN for data generation,
LGBM for classification
|
TPR = 60.0
|
4
|
[34]
|
2022
|
BTG: A bridge to graph machine learning in telecommunications fraud detection
|
Telecommunication fraud
|
Box-Cox for transformation, BTG for classification
|
Precision = 90.9
|
5
|
[40]
|
2022
|
Performance of different machine learning algorithms in detecting financial fraud
|
Money laundering
|
Shapley value for feature selection, RF for classification
|
Accuracy = 90.0
|
6
|
[27]
|
2022
|
Exploratory analysis of credit card fraud detection using machine learning techniques
|
Credit card fraud
|
SVM, GB, RF, KNN & LR for classification
|
Accuracy = 96.2\
|
7
|
[28]
|
2022
|
Insurance fraud detection: evidence from artificial intelligence and machine learning
|
Insurance fraud
|
LR, SVM, and Naïve Bayes for classification
|
Accuracy = 94.0
|
8
|
[23]
|
2022
|
Autonomous credit card fraud detection using a machine learning approach
|
Credit card
|
LSTM-RNN, SVM, and ANN for classification
|
Accuracy = 100.0
|
9
|
[33]
|
2022
|
An innovative perceptual pigeon galvanized optimization (PPGO) based likelihood naïve Bayes (LNB) classification approach for network intrusion detection system
|
Intrusion detection
|
ADC DBSCAN is used to strengthen group disparity and likelihood naïve Bayes for classification
|
Accuracy = 89.6
|
10
|
[8]
|
2022
|
Determinants of auditor's ability in fraud
detection
|
Financial statement fraud
|
Regression measures the effects of attributes on fraud detection
|
R2 = 82.0
|
11
|
[17]
|
2022
|
Electronic fraud: an emerging cause of bank failure in Nigerian deposit money banks
|
Financial fraud
|
OLS measures the relationship between variables
|
R2 = 67.0
|
12
|
[20]
|
2022
|
Prevention village fund fraud in Indonesia: moral sensitivity as a moderating variable
|
Financial statement fraud
|
Correlation & PLS -SEM measure the relationship between variables
|
R2 = 89.8
|
13
|
[18]
|
2022
|
A comparative study of frequentist vs Bayesian A/B testing in the detection of E-commerce fraud
|
E-commerce fraud
|
Regression analysis for prediction
|
R2 = 60.0
|
14
|
[35]
|
2022
|
credit card-not-present fraud detection and prevention using big data analytics algorithms
|
Credit CNP
|
t-SNE & PCA for data reduction, LR for classification
|
Accuracy = 99.9
|
15
|
[10]
|
2022
|
LGBM: a machine learning approach for Ethereum fraud detection
|
Defi fraud
|
LGBM for classification
|
FPR = 52.6
|
16
|
[24]
|
2023
|
Fraud detection in banking data by machine learning techniques
|
Credit card fraud
|
Ensemble learning for classification
|
ROC–AUC = 95.0
|
17
|
[25]
|
2023
|
Credit card fraud detection using ensemble data mining methods
|
Credit card fraud
|
Ensemble learning for classification
|
Accuracy = 99.4
|
18
|
[22]
|
2023
|
An efficient fraud detection framework with credit card imbalanced data in financial services
|
Credit card fraud
|
KNN, LR, LDA, NB, and CART for classification
|
Accuracy = 99.9
|
19
|
[30]
|
2023
|
Leveraging machine learning for multichain defi fraud detection
|
Defi fraud
|
XGBoost & ANN for classification
|
Precision = 99.9
|
20
|
[11]
|
2023
|
Modified genetic algorithm with deep learning for fraud transactions of Ethereum smart contract
|
Defi fraud
|
SVM for classification
|
TPR = 63.1
|
21
|
[9]
|
2023
|
Fraudsters beware: unleashing the power of metaverse technology to uncover financial fraud
|
Financial fraud
|
Game theory determines the strategies of participants, OLS analyses the effectiveness of metaverse treatment
|
R2 = 53.8
|
22
|
[7]
|
2023
|
Strategic earnings announcement timing and fraud detection
|
Financial statement fraud
|
Weibull hazard model estimate hazard ratio, OLS estimates the length of the detection period
|
P < 1.0
|
23
|
[19]
|
2023
|
The diffusion of health care fraud: a bipartite network analysis
|
Health care fraud
|
The BMIX index measures patient sharing across multiple agencies, regression analysis for prediction
|
Std error = 6.5
|
24
|
[12]
|
2023
|
Hybrid defense mechanism against malicious packet-dropping attacks for MANET using game theory
|
Intrusion detection
|
The game theory model is used to monitor neighbor nodes
|
FPR = 70.0
|
25
|
[15]
|
2023
|
Fairness-aware data valuation for supervised learning
|
New bank account fraud
|
LGBM for classification
|
TPR = 80.0
|
26
|
[14]
|
2023
|
An ensemble-based fraud detection model for financial transaction cyber threat classification and countermeasures
|
New bank account fraud
|
Ensemble learning for classification
|
TPR = 90.0
|
27
|
[36]
|
2023
|
Transparency and privacy: the role of explainable AI and federated learning in financial fraud detection
|
New bank account fraud
|
DNN for classification
|
TPR = 75.0
|
28
|
[26]
|
2024
|
Enhancing credit card fraud detection: an ensemble machine learning approach
|
Credit card fraud
|
Ensemble learning for classification
|
Recall = 99.9
|
29
|
[29]
|
2024
|
Heterogeneous graph neural networks for fraud detection and explanation in supply chain finance
|
financial fraud
|
GNN for classification
|
AUC = 95.1
|