| C. Hadjisofokelous, G. Drakopoulos, S. Sioutas, Ph. Mylonas |
| Discovering Fraudulent Card Transactions With Higher Order Graph Embeddings Over Neo4j |
| 21st International Conference on Artificial Intelligence Applications & Innovations (AIAI 2025), Limassol, Cyprus, June 26-29, 2025 |
|
ABSTRACT
|
| Credit card transactions, especially when linked to smart devices and the IoT ecosystem in general, are one of the drivers of contemporary digital economy as well as a major indicator of the overall financial activity. As such as well as for a plethora of other reasons it is imperative that fraudulent transactions be efficiently and reliably discovered. Because of their interconnected and time-dependent nature, a graphic representation not only is convenient, but also lends itself to machine learning strategies. To this end one viable approach it to develop higher order analytics in Neo4j either in the form of graph queries in Neo4j or by employing the underlying methods. Two concrete examples presented here are the transaction clustering and the application of machine learning directly on the transaction graph augmented with vertex embeddings. The results corroborate the efficiency of the above and are encouraging for the development of more higher order fraudulent transaction methods towards a more robust and reliable digital economy.
|
| 26 June , 2025 |
| C. Hadjisofokelous, G. Drakopoulos, S. Sioutas, Ph. Mylonas, "Discovering Fraudulent Card Transactions With Higher Order Graph Embeddings Over Neo4j", 21st International Conference on Artificial Intelligence Applications & Innovations (AIAI 2025), Limassol, Cyprus, June 26-29, 2025 |
[
BibTex] [
Print] [
 Back] |
