arbiter
JournalsPricingAccount

Applying deep learning to detect abnormal event log traces: a non-rule-based framework

Yunsen Wang et al.

The International Journal of Digital Accounting Research2024https://doi.org/10.4192/1577-8517-v24_5article
ABDC B
Weight
0.38

What the paper says

Process mining is an efficient method that can analyze the full population of transactions using the event log of business processes. Conventional rule-based process mining techniques can detect anomalies; however, it tends to trigger a large number of false alarms. To improve the efficiency of anomaly detection using process mining, this study adopts a deep learning-based classification approach to detect anomalies in the traces of event logs. This approach contributes to the literature by proposing a non-rule-based process mining technique based on deep learning. Results demonstrate that the proposed non-rule-based process mining method can help auditors focus on transactional anomalies. Keywords: Process mining, deep learning, anomaly detection, fraudulent activities.

1 citation

Open paper page →

Cite this paper

https://doi.org/https://doi.org/10.4192/1577-8517-v24_5

Or copy a formatted citation

@article{yunsen2024,
  title        = {{Applying deep learning to detect abnormal event log traces: a non-rule-based framework}},
  author       = {Yunsen Wang et al.},
  journal      = {The International Journal of Digital Accounting Research},
  year         = {2024},
  doi          = {https://doi.org/https://doi.org/10.4192/1577-8517-v24_5},
}

Paste directly into BibTeX, Zotero, or your reference manager.

Flag this paper

Applying deep learning to detect abnormal event log traces: a non-rule-based framework

Flags are reviewed by the Arbiter methodology team within 5 business days.

Evidence weight

0.38

Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40

F · citation impact0.18 × 0.4 = 0.07
M · momentum0.53 × 0.15 = 0.08
V · venue signal0.50 × 0.05 = 0.03
R · text relevance †0.50 × 0.4 = 0.20

† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.