Journal of Advanced Research in Computer Technology & Software Applications

A Review on Hybrid Machine Learning and Deep Learning Approaches for Fraud Detection in Online Marketplace Transactions

Mayank Mishra — 2026-06-19

E-commerce platforms have expanded rapidly over past decades, resulting in significantly increased online transactions and increased fraudulent activities. Traditional techniques in fraud detection, which include rule-based systems and conventional machine learning models, struggle to accommodate high-dimensional data, swift evolving fraud patterns, or severe class imbalance. The study offers an extensive review of the existing approaches in fraud detection, focusing on the hybrid approaches of machine learning and deep learning. Particular emphasis is given to the use of advanced pre-processing methods, such as data normalization, categorical encoding, and Synthetic Minority Over-sampling Technique (SMOTE), to deal with data imbalance problems. The study also observes and evaluates different algorithms like Logistic Regression, Decision Trees, Random Forest, Gradient Boosting, and CatBoost, plus deep learning techniques-such as Autoencoders-in detecting anomalies. Another point to note is the importance of hybrid approaches utilizing both supervised and unsupervised learning to improve both performance accuracy and model robustness. The study also indicates that CatBoost is good at handling categorical features, while also restricting overfitting; Autoencoders, due to their reconstruction errors, tend to effectively capture stealth anomalies. The research also elaborates on key evaluation metrics, sufficient accuracy, precision, recall, and F1-score, to assess the performance of models for imbalanced datasets. It argues that hybrid methods do much better than traditional technique performances by enhancing the sensitivity of fraud detection while reducing false negatives. Finally, paper ends with future research trends Danstellerity defines the future trends in this discussion by integrating explainable AI and superior deep learning architectures, which would create significant fraud detection systems on a larger scale.

How to cite this article:
Mishra M, Rai A K. A Review on Hybrid Machine Learning and Deep Learning Approaches for Fraud Detection in Online Marketplace Transactions. J Adv Res Comp Tech Soft Appl 2026; 10(2): 1-9.

Blockchain for Cybersecurity: Ensuring Data Integrity and Secure Transactions in the Agricultural Industry and Supply Chain Management

Mohd Afroz — 2026-06-13

The rapid digitalization of agriculture has significantly improved operational efficiency, precision farming, and supply chain transparency. Traditional centralized information systems can face problems in offering enough security, traceability, and trust in complicated multi-stakeholder agricultural supply chains. This paper explores the possibility of blockchain as a cybersecurity architecture to provide data integrity and secure transactions in agricultural applications. A qualitative research method and structured analysis of 47 scholarly papers and four real-world blockchain deployments (IBM Food Trust, AgriDigital, TE-FOOD, and Ambrosus) are used in the study. The results show that blockchain technology can substantially improve the security and transparency of agricultural value chains through various mechanisms such as distributed ledger, consensus validation, smart contracts, decentralized identity management, and role-based access control. By leveraging case studies, it is evident that traceability has improved significantly, fraud prevention has increased, auditability has been enhanced, and transaction security has been bolstered; in some deployments, traceability time is in the order of seconds rather than days. Various mitigation measures such as IoT data attestation, HSMs, consortium governance models and harmonising policies are explored. The study concludes that blockchain technology offers a strong and durable cybersecurity infrastructure for the modern agricultural ecosystem by providing a platform for transparent and trusted data sharing, tamper-resistant data recording, and safe digital transactions throughout the supply chain.Keywords—Blockchain, Cybersecurity, Agricultural Supply Chain, Data Integrity, Smart Contracts, Distributed Ledger Technology, Food Traceability, IoT Security, Secure Transactions, Consortium Blockchain.
DOI: https://www.doi.org/10.24321/3051.4304.202605

How to cite this article:
Afroz M, Vishnu D, Alam I, Lamkuche H S, Patheja P S, Blockchain for Cybersecurity: Ensuring Data Integrity and Secure Transactions in the Agricultural Industry and Supply Chain Management. J Adv Res Comp Tech Soft Appl 2026; 10(2): 26-32.

DOI: https://www.doi.org/10.24321/3051.4304.202605

Financial Fraud Detection Using Cyber Security

Ujjwal Kaul — 2026-06-25

Financial technology (fintech) and the rapid growth in mobile payment systems have transformed the financial sector with faster, more convenient and ubiquitous digital transactions. With the greater use of digital financial services, however, comes an increased risk of cyberattacks and financial fraud. Phishing, SIM-swap attacks, identity theft, faux Know Your Customer (KYC) methods and transaction manipulation are among the methods cybercriminals use to compromise mobile apps, digital wallets, APIs, and fintech platforms. While there are advanced cybersecurity solutions, such as AI-driven fraud detection, blockchain technology, biometric authentication, and multi-factor authentication, that have been developed to address these threats, there are several challenges to the effectiveness of these solutions. Challenges encompass data privacy, data model opacity, new fraud methods and regulatory intricacies. The research aims to explore the key issues related to detecting and preventing financial fraud in mobile payment and fintech settings. The study summarises the latest trends in cybersecurity, discusses the shortcomings of current fraud detection systems, and suggests a combination of explainable artificial intelligence, real-time analytics, behavioural authentication, and secure mobile architecture to address fraud more effectively. The proposed approach seeks to boost the accuracy of fraud detection, increase the transparency of the system, bolster user authentication and create a more flexible defence mechanism for new cyber threats in the digital financial system.

DOI: https://doi.org/10.24321/3051.4304.202606

How to cite this article:
Kaul U. Financial Fraud Detection Using Cyber Security. J Adv Res Comp Tech Soft Appl 2026; 10(2): 10-19.