• Prajakta Durgadas Pachpor
• Madhuri R. Rajput
• Neha Vilas Patil
• Sakshi Shrikrushna Tayade
• Vrushali Mohan Kolte

Cybercrime is fostered by e-commerce's rapid growth. The problem of online payment fraud detection, which online services must overcome, is crucial to the quickly developing e-commerce industry. It is acknowledged that behavior-based approaches have promise in the fight against online payment fraud. Nevertheless, using low-quality behavioral data to construct high-resolution behavioral models is quite difficult. We primarily tackle this issue from data enhancement for behavioral modelling in our paper. Using a knowledge graph, we are able to extract transactional attribute co-occurrence correlations at a finer level. Additionally, in order to learn and get better at portraying comprehensive relationships, we use heterogeneous network embedding. In particular, we investigate tailored network embedding strategies for several behavioral model types, including generalized agent-based, population-level, and individual-level models. Cybercrime is fostered by e-commerce's rapid growth. The problem of online payment fraud detection, which online services must overcome, is crucial to the quickly developing e-commerce industry. It is acknowledged that behavior-based approaches have promise in the fight against online payment fraud. Nevertheless, using low-quality behavioral data to construct high-resolution behavioral models is quite difficult. We primarily tackle this issue from data enhancement for behavioral modelling in our paper. Using a knowledge graph, we are able to extract transactional attribute co-occurrence correlations at a finer level. Additionally, in order to learn and get better at portraying comprehensive relationships, we use heterogeneous network embedding. In particular, we investigate tailored network embedding strategies for several behavioral model types, including generalized agent-based, population-level, and individual-level models.

Online payment services, Fraud detection, Network embedding, user Behavioural modelling.

"Representing Fine-Grained Co-Occurrences for Behavior-Based Fraud Detection in Online Payment Services", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 3, page no.d385-d388, March-2024, Available :http://www.jetir.org/papers/JETIR2403346.pdf

"Representing Fine-Grained Co-Occurrences for Behavior-Based Fraud Detection in Online Payment Services", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 3, page no. ppd385-d388, March-2024, Available at : http://www.jetir.org/papers/JETIR2403346.pdf