A Hybrid DNN Transformer AE Framework for Corporate Tax Risk Supervision and Risk Level Assessment

2025-09-28

AI Summary

Traditional rule-based methods struggle to effectively detect complex, dynamic anomalies in large-scale enterprise tax data. To address this, we propose a hybrid deep learning framework integrating Deep Neural Networks (DNNs), Transformers, and temporal autoencoders to jointly model static enterprise attributes, dynamic financial time-series dependencies, and unsupervised anomalous behaviors. Our architecture employs multi-module collaboration and multimodal feature fusion, augmented by an interpretable risk-level mapping mechanism enabling fine-grained risk stratification. Evaluated on real-world tax data, the model achieves a classification accuracy of 0.91 and a Macro F1-score of 0.88—significantly outperforming baseline approaches. The framework balances high discriminative accuracy with operational interpretability, offering a practical, deployable solution for intelligent tax supervision.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Time-Series/Data Streams
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Tax risk supervision has become a critical component of modern financial governance, as irregular tax behaviors and hidden compliance risks pose significant challenges to regulatory authorities and enterprises alike. Traditional rule-based methods often struggle to capture complex and dynamic tax-related anomalies in large-scale enterprise data. To address this issue, this paper proposes a hybrid deep learning framework (DNN-Transformer-Autoencoder) for corporate tax risk supervision and risk level assessment. The framework integrates three complementary modules: a Deep Neural Network (DNN) for modeling static enterprise attributes, a Transformer-based architecture for capturing long-term dependencies in historical financial time series, and an Autoencoder (AE) for unsupervised detection of anomalous tax behaviors. The outputs of these modules are fused to generate a comprehensive risk score, which is further mapped into discrete risk levels (high, medium, low). Experimental evaluations on a real-world enterprise tax dataset demonstrate the effectiveness of the proposed framework, achieving an accuracy of 0.91 and a Macro F1-score of 0.88. These results indicate that the hybrid model not only improves classification performance but also enhances interpretability and applicability in practical tax regulation scenarios. This study provides both methodological innovation and regulatory implications for intelligent tax risk management.

Problem

• Detecting corporate tax risks using hybrid deep learning
• Assessing tax risk levels from enterprise financial data
• Overcoming limitations of traditional rule-based tax supervision

Innovation

• Hybrid DNN-Transformer-Autoencoder framework for tax risk
• DNN models static attributes, Transformer captures time dependencies
• Autoencoder detects anomalies, fused outputs generate risk scores