EvoAnom: Longitudinal Temporal Deep Learning for Evolutionary  Anomaly Detection in Digital Identities

Suman Kumar Sanjeev Prasanna, Shardul Pandya

EvoAnom: Longitudinal Temporal Deep Learning for Evolutionary Anomaly Detection in Digital Identities

Authors

Suman Kumar Sanjeev Prasanna, Shardul Pandya

Keywords:

Longitudinal modeling, Temporal deep learning, Evolutionary anomaly detection, Drift adaptation, Transfer learning, Sequential datasets, Robust representation.

Abstract

Identity fraud and behavioral anomalies evolve continuously, often rendering static detection methodsineffective. This research introduces EvoAnom, a longitudinal temporal deep learning framework forevolutionary anomaly detection in digital identity systems. By modeling sequential interactions as temporal embeddings, the framework captures both immediate irregularities

References

Amen, B., and Grigoris, A. A theoretical study of anomaly detection in big data distributed static and stream analytics. In 2018 IEEE 20th International Conference on High Performance Computing and Communications; IEEE 16th International Conference on Smart City; IEEE 4th International on Data Science and Systems (HPCC/SmartCity/DSS), 2018: 1177–1182

Downloads

Published

2022-02-15

How to Cite

Suman Kumar Sanjeev Prasanna, Shardul Pandya. (2022). EvoAnom: Longitudinal Temporal Deep Learning for Evolutionary Anomaly Detection in Digital Identities . Journal of Computational Analysis and Applications (JoCAAA), 30(2), 1142–1153. Retrieved from https://eudoxuspress.com/index.php/pub/article/view/5280