Enhancing Credit Card Fraud Detection: A Comprehensive Study of Machine Learning Algorithms and Performance Evaluation DOI Open Access

Syeda Farjana Farabi,

Mani Prabha Ro,

Mahfuz Alam

et al.

Journal of Business and Management Studies, Journal Year: 2024, Volume and Issue: 6(3), P. 252 - 259

Published: June 13, 2024

Credit card fraud detection remains a significant challenge for financial institutions and consumers globally, prompting the adoption of advanced data analytics machine learning techniques. In this study, we investigate methodology performance evaluation various algorithms credit detection, emphasizing preprocessing techniques model effectiveness. Through thorough dataset analysis experimentation using cross-validation approaches, assess logistic regression, decision trees, random forest classifiers, Naïve Bayes K-nearest neighbors (KNN), artificial neural networks (ANN-DL). Key metrics such as accuracy, sensitivity, specificity, F1-score are compared to identify most effective models detecting fraudulent transactions. Additionally, explore impact different folds in on performance, providing insights into classifiers' robustness stability. Our findings contribute ongoing efforts develop efficient systems, offering valuable researchers striving combat effectively.

Language: Английский

Advancements in Retail Price Optimization: Leveraging Machine Learning Models for Profitability and Competitiveness DOI Open Access

Mohammad Anisur Rahman,

Chinmoy Modak,

Md Abu Sufian Mozumder

et al.

Journal of Business and Management Studies, Journal Year: 2024, Volume and Issue: 6(3), P. 103 - 110

Published: May 23, 2024

Retail price optimization is essential for maximizing profitability and maintaining competitiveness in today's dynamic retail landscape. This study addresses as a regression problem, utilizing machine learning models to predict optimal points products. Leveraging factors such product attributes, competitor pricing dynamics, customer behaviors, analysis provides structured approach understanding the intricate relationships between variables. Among various techniques, Random Forest Regressor emerges potent strategy, offering robustness versatility tackling complex tasks. Results indicate that outperforms Decision Tree Logistic Regression regarding accuracy, precision, recall, overall predictive performance. With achieving an accuracy of 94%, it demonstrates superior capability capturing data patterns making accurate predictions prices. By leveraging advanced analytics retailers can optimize strategies, maximize profits, maintain market. underscores importance continuously analyzing refining strategies gain competitive edge

Language: Английский

Citations

6
Machine Learning Model in Digital Marketing Strategies for Customer Behavior: Harnessing CNNs for Enhanced Customer Satisfaction and Strategic Decision-Making DOI Open Access

Chinmoy Modak,

Sandip Kumar Ghosh,

Md Ariful Islam Sarkar

et al.

Journal of Economics Finance and Accounting Studies, Journal Year: 2024, Volume and Issue: 6(3), P. 178 - 186

Published: June 22, 2024

In the realm of digital marketing for banking industry, integration deep learning methodologies, particularly Convolutional Neural Networks (CNNs) such as VGG16, Resnet50, and InceptionV3, has revolutionized strategic decision-making customer satisfaction. This study explores how models leverage neural networks with multiple layers to analyze vast complex datasets, uncovering intricate patterns in behavior preferences. By enhancing segmentation, optimizing campaign performance, refining personalized experiences, CNNs empower banks make precise, data-driven decisions that elevate satisfaction loyalty. Comparative analyses demonstrate CNNs' superior performance over traditional like Random Forest Logistic Regression, achieving accuracies up 89% F1 scores 88%, thereby highlighting their transformative potential reshaping strategies within sector. research underscores critical implications adopting advanced techniques meet evolving demands customers today's dynamic landscape.

Language: Английский

Citations

4
Enhancing Credit Card Fraud Detection: A Comprehensive Study of Machine Learning Algorithms and Performance Evaluation DOI

Maniruzzaman Bhuiyan,

Syeda Farjana Farabi

SSRN Electronic Journal, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

Language: Английский

Citations

0
Revolutionizing Organizational Decision-Making for Banking Sector: A Machine Learning Approach with CNNs in Business Intelligence and Management DOI Open Access

Md Abu Sufian Mozumder,

Md Murshid Reja Sweet,

Norun Nabi

et al.

Journal of Business and Management Studies, Journal Year: 2024, Volume and Issue: 6(3), P. 111 - 118

Published: May 23, 2024

This research investigates the transformative impact of deep learning, particularly Convolutional Neural Networks (CNNs) such as VGG16, ResNet50, and InceptionV3, on organizational management business intelligence within banking sector. Employing a comprehensive methodology, study emphasizes crucial role high-quality datasets in harnessing learning for improved decision-making. Results reveal superior performance CNN models over traditional algorithms, with (VGG16) achieving an impressive accuracy rate 90%. These findings underscore potential extracting valuable insights from complex data, presenting paradigm shift optimizing various processes. The article concludes by highlighting importance investing infrastructure expertise successful integration, while also addressing ethical privacy considerations. contributes to evolving discourse applications management, offering banks navigating challenges global market.

Language: Английский

Citations

3
Enhancing Credit Card Fraud Detection: A Comprehensive Study of Machine Learning Algorithms and Performance Evaluation DOI Open Access

Syeda Farjana Farabi,

Mani Prabha Ro,

Mahfuz Alam

et al.

Journal of Business and Management Studies, Journal Year: 2024, Volume and Issue: 6(3), P. 252 - 259

Published: June 13, 2024

Credit card fraud detection remains a significant challenge for financial institutions and consumers globally, prompting the adoption of advanced data analytics machine learning techniques. In this study, we investigate methodology performance evaluation various algorithms credit detection, emphasizing preprocessing techniques model effectiveness. Through thorough dataset analysis experimentation using cross-validation approaches, assess logistic regression, decision trees, random forest classifiers, Naïve Bayes K-nearest neighbors (KNN), artificial neural networks (ANN-DL). Key metrics such as accuracy, sensitivity, specificity, F1-score are compared to identify most effective models detecting fraudulent transactions. Additionally, explore impact different folds in on performance, providing insights into classifiers' robustness stability. Our findings contribute ongoing efforts develop efficient systems, offering valuable researchers striving combat effectively.

Language: Английский

Citations

3