Chen Chen

This paper targets key challenges in enterprise financial anomaly monitoring, including coupled multi-source heterogeneous features, concealed anomaly signals, and cost-sensitive alerting. It proposes a unified monitoring framework based on representation-driven data modeling. The approach first normalizes and encodes transaction and identity-related fields within a unified feature space. A learnable representation mapping function is then used to obtain low-dimensional latent representations. A reconstruction consistency mechanism is introduced to suppress noise while preserving essential behavioral information. In the latent space, normal behavior structures are statistically characterized. Structural anomaly signals are derived by measuring the deviation between representation centers and sample representations. These signals are combined with reconstruction errors from the original inputs to form a unified anomaly score. This enables continuous ranking of samples and threshold-based anomaly decisions. To ensure controllability in training and deployment, the framework is systematically analyzed from the perspectives of hyperparameter sensitivity, including learning rate, optimizer choice, and network depth, as well as environmental sensitivity under input noise injection. The analysis delineates the impact boundaries of key configurations on overall detection performance and stability. The results demonstrate that the framework maintains consistent risk identification characteristics under different configurations and perturbations. It provides sortable and configurable anomaly signals for enterprise risk alerts, audit sampling, and compliance inspection.

Traditional Enterprise Resource Planning (ERP) systems excel at quantifying budgetary variances but fail to identify their root causes, leaving financial analysts with time-consuming manual investigation. We present Causal-LLM, a hybrid framework that integrates causal discovery algorithms with Large Language Models (LLMs) to automate root cause diagnosis in budgetary variance analysis. Our approach combines constraint-based causal inference to construct financial causal graphs with LLM-powered contextual reasoning to generate human-interpretable explanations. By leveraging a domain-specific Financial Causal Knowledge Graph, Causal-LLM bridges the gap between statistical correlation and genuine causation. Experimental evaluation on 240 labeled variance cases from a real-world enterprise (24 months of data) demonstrates that our framework achieves 0.87 top-1 accuracy in root cause identification (95% CI: [0.82, 0.91]), outperforming traditional statistical methods (0.68), pure LLM approaches (0.76), and standalone causal methods (0.72). The system generates actionable insights with 0.92 explainability scores (inter-rater agreement ICC=0.84), reducing investigation time from an estimated 2--4 hours (mean: 3.2 hours, based on internal workflow estimates from five senior analysts) to under 10 seconds per case. Results are demonstrated on one manufacturing enterprise; generalization to other industries requires domain-specific ontology adaptation.

His study investigates the application of causal representation learning in financial auditing risk identification, aiming to address problems in traditional methods such as spurious correlations, limited interpretability, and unstable recognition. The proposed framework is built around causal-driven latent representations, where nonlinear mapping is used to obtain deep feature representations of financial data, and structural equation models are employed to establish causal dependencies, thereby removing the interference of non-causal features in risk modeling. On this basis, causal regularization constraints are introduced, and the joint optimization of the objective function enhances the consistency and robustness of representations, improving the reliability and interpretability of the model in complex scenarios. Furthermore, in the risk scoring stage, causal representation is combined with intervention effect calculation, which enables risk identification to provide not only outcome judgments but also insights into the underlying driving mechanisms, thereby improving traceability of risk sources. To verify effectiveness, a dataset closely related to financial auditing tasks was constructed, and comparative experiments under an alignment robustness benchmark were conducted. The results show that the proposed method outperforms existing models in ACC, Precision, Recall, and F1-Score, with notable advantages in robustness and interpretability. In addition, hyperparameter sensitivity experiments analyzed the impact of the causal regularization coefficient on model performance, and the results indicate that appropriate causal constraints can significantly improve stability while maintaining predictive accuracy. Overall, the proposed causal representation learning framework enables more precise and reliable risk identification in financial auditing and provides strong support for building intelligent and data-driven auditing systems.

This study proposes an intelligent audit risk assessment method that integrates causal structure modeling, causal identifiability reasoning, and interpretable representation learning to address the lack of transparency in risk identification, the presence of confounded variable relationships, and the limitations of correlation-based inference in complex audit scenarios. The method first constructs a structured causal graph of the audit workflow to formalize the triggering relationships and interaction paths among audit features, and then applies structural equations and identifiability analysis to reveal latent causal dependencies. Based on this foundation, the model generates interpretable feature embeddings through causally constrained representation learning, allowing inference results to map back to the business semantic space along causal paths and enabling visual analysis of risk formation. To validate the effectiveness of the approach, this study conducts comparison experiments, ablation experiments, and multidimensional sensitivity analyses on a public audit dataset, and evaluates the method across model accuracy, interpretability, noise robustness, distributional shifts, and hyperparameter variations. The experimental results show that the method achieves significant improvements over existing models in accuracy, precision, recall, and F1-score, while maintaining stable performance under noise interference, class imbalance, learning rate changes, and latent dimension adjustments. The model also produces clear causal chain explanations that help auditors understand risk sources, identify key process components, and trace potential triggering mechanisms through structured reasoning logic. Overall, this study achieves a deep integration of causal inference and intelligent auditing and provides a complete methodological framework and empirical evidence for building transparent, trustworthy, and highly interpretable audit risk assessment systems.

Fraudulent financial reporting continues to undermine market integrity and threaten stakeholder interests globally. Conventional analytical methodologies demonstrate limited effectiveness in recognizing intricate temporal relationships and nuanced irregularities characteristic of accounting manipulation. This research introduces an enhanced recurrent neural architecture incorporating multi-head attention layers with bidirectional LSTM components, specifically engineered for identifying accounting anomalies. Our architectural design combines attention-weighted feature selection with dual-directional temporal processing to simultaneously extract prolonged sequential patterns and pivotal indicators spanning multiple reporting cycles. Through rigorous evaluation using a dataset of 2,500 corporate entities across 12 reporting cycles, our methodology achieves 93.87% classification accuracy, 92.41% positive predictive value, 91.56% sensitivity, and 91.98% harmonic mean of precision-recall. These metrics surpass conventional statistical methods and standard deep architectures by substantial margins. The attention weight distributions offer transparent interpretability, revealing which specific accounting ratios and temporal windows contribute decisively to fraud predictions, thereby enhancing practical deployment feasibility in professional audit environments.