Saved in:
Bibliographic Details
Main Authors: Wang, Yi, Fang, Ruoyi, Xie, Anzhuo, Feng, Hanrui, Lai, Jianlin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.12122
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909905164697600
author Wang, Yi
Fang, Ruoyi
Xie, Anzhuo
Feng, Hanrui
Lai, Jianlin
author_facet Wang, Yi
Fang, Ruoyi
Xie, Anzhuo
Feng, Hanrui
Lai, Jianlin
contents This study addresses the problem of dynamic anomaly detection in accounting transactions and proposes a real-time detection method based on a Transformer to tackle the challenges of hidden abnormal behaviors and high timeliness requirements in complex trading environments. The approach first models accounting transaction data by representing multi-dimensional records as time-series matrices and uses embedding layers and positional encoding to achieve low-dimensional mapping of inputs. A sequence modeling structure with multi-head self-attention is then constructed to capture global dependencies and aggregate features from multiple perspectives, thereby enhancing the ability to detect abnormal patterns. The network further integrates feed-forward layers and regularization strategies to achieve deep feature representation and accurate anomaly probability estimation. To validate the effectiveness of the method, extensive experiments were conducted on a public dataset, including comparative analysis, hyperparameter sensitivity tests, environmental sensitivity tests, and data sensitivity tests. Results show that the proposed method outperforms baseline models in AUC, F1-Score, Precision, and Recall, and maintains stable performance under different environmental conditions and data perturbations. These findings confirm the applicability and advantages of the Transformer-based framework for dynamic anomaly detection in accounting transactions and provide methodological support for intelligent financial risk control and auditing.
format Preprint
id arxiv_https___arxiv_org_abs_2511_12122
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dynamic Anomaly Identification in Accounting Transactions via Multi-Head Self-Attention Networks
Wang, Yi
Fang, Ruoyi
Xie, Anzhuo
Feng, Hanrui
Lai, Jianlin
Machine Learning
This study addresses the problem of dynamic anomaly detection in accounting transactions and proposes a real-time detection method based on a Transformer to tackle the challenges of hidden abnormal behaviors and high timeliness requirements in complex trading environments. The approach first models accounting transaction data by representing multi-dimensional records as time-series matrices and uses embedding layers and positional encoding to achieve low-dimensional mapping of inputs. A sequence modeling structure with multi-head self-attention is then constructed to capture global dependencies and aggregate features from multiple perspectives, thereby enhancing the ability to detect abnormal patterns. The network further integrates feed-forward layers and regularization strategies to achieve deep feature representation and accurate anomaly probability estimation. To validate the effectiveness of the method, extensive experiments were conducted on a public dataset, including comparative analysis, hyperparameter sensitivity tests, environmental sensitivity tests, and data sensitivity tests. Results show that the proposed method outperforms baseline models in AUC, F1-Score, Precision, and Recall, and maintains stable performance under different environmental conditions and data perturbations. These findings confirm the applicability and advantages of the Transformer-based framework for dynamic anomaly detection in accounting transactions and provide methodological support for intelligent financial risk control and auditing.
title Dynamic Anomaly Identification in Accounting Transactions via Multi-Head Self-Attention Networks
topic Machine Learning
url https://arxiv.org/abs/2511.12122