Loading...
T. Aditya Sai Srinivas is an Associate Professor in the Department of Computer Science and Engineering at Ravindra College of Engineering for Women, India. His research interests include Artificial Intelligence, cloud computing, and intelligent computing systems.
The swift expansion of e-commerce has revolutionised the worldwide retail sector by allowing consumers to acquire goods and services at any time and from any location via digital platforms. Progress in cloud computing, mobile commerce, the Internet of Things (IoT), digital payment solutions, and Artificial Intelligence (AI) has markedly improved customer convenience and operational efficiency. Nonetheless, the rising number of online transactions has exacerbated cybersecurity threats, such as payment fraud, phishing, account hijacking, identity theft, counterfeit websites, dangerous bots, and data breaches. Conventional security measures reliant on fixed regulations frequently fall short in identifying complex and advancing cyber threats. Artificial Intelligence (AI), Machine Learning (ML), Deep Learning (DL), Behavioural Analytics, Big Data Analytics, Blockchain, and Federated Learning have surfaced as formidable technologies for safeguarding online retail environments. This chapter examines AI-based security frameworks, sophisticated fraud detection methods, privacy-enhancing technologies, obstacles, applications, and prospective research avenues for safeguarding contemporary online retail settings.
The swift digital transformation of banking, financial services, insurance, e-commerce, and FinTech has markedly amplified the quantity and intricacy of financial transactions. Although digital financial ecosystems enhance convenience and operational efficacy, they have simultaneously generated novel avenues for hackers to perpetrate fraud, money laundering, identity theft, insider threats, account takeover, and payment fraud. Conventional rule-based detection systems frequently struggle to recognise complex and adaptive criminal activities because of their dependence on established rules and fixed thresholds. Behavioural Analytics has arisen as a formidable AI-driven methodology that examines user behaviour, transaction trends, device attributes, and contextual data to identify suspicious actions instantaneously. Through the amalgamation of Machine Learning (ML), Deep Learning (DL), Big Data Analytics, Graph Analytics, and Explainable Artificial Intelligence (XAI), behavioural analytics empowers financial entities to preemptively detect irregularities, mitigate fraud-related losses, and enhance adherence to regulations. This chapter delineates the principles, framework, methodology, applications, problems, and prospective research avenues of behavioural analytics for the identification of financial crimes within intelligent financial ecosystems.