A FEDformer-Based Hybrid Framework for Anomaly Detection and Risk Forecasting in Financial Time Series

2025-11-16

AI Summary

Financial time series exhibit strong non-stationarity, long-range dependencies, and multi-scale periodic patterns—challenging to model simultaneously. To address these issues, this paper proposes the Frequency-Enhanced Decomposition Transformer (FED-Transformer), a hybrid architecture that integrates FEDformer’s time-frequency decomposition with LSTM-based sequential modeling, residual anomaly detection, and a latent-space risk classification head. The framework jointly models trend, seasonal, and residual components while enabling multi-task collaborative learning. By explicitly disentangling time- and frequency-domain representations and incorporating an interpretable risk prediction pathway, the model significantly enhances early financial risk identification. Evaluated on three benchmark financial datasets, FED-Transformer achieves a 15.7% reduction in RMSE and an 11.5% improvement in F1-score over prior methods, and demonstrates superior crash预警 performance compared to state-of-the-art approaches.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Natural Language Processing: Safety and Robustness
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Financial markets are inherently volatile and prone to sudden disruptions such as market crashes, flash collapses, and liquidity crises. Accurate anomaly detection and early risk forecasting in financial time series are therefore crucial for preventing systemic instability and supporting informed investment decisions. Traditional deep learning models, such as LSTM and GRU, often fail to capture long-term dependencies and complex periodic patterns in highly nonstationary financial data. To address this limitation, this study proposes a FEDformer-Based Hybrid Framework for Anomaly Detection and Risk Forecasting in Financial Time Series, which integrates the Frequency Enhanced Decomposed Transformer (FEDformer) with a residual-based anomaly detector and a risk forecasting head. The FEDformer module models temporal dynamics in both time and frequency domains, decomposing signals into trend and seasonal components for improved interpretability. The residual-based detector identifies abnormal fluctuations by analyzing prediction errors, while the risk head predicts potential financial distress using learned latent embeddings. Experiments conducted on the S&P 500, NASDAQ Composite, and Brent Crude Oil datasets (2000-2024) demonstrate the superiority of the proposed model over benchmark methods, achieving a 15.7 percent reduction in RMSE and an 11.5 percent improvement in F1-score for anomaly detection. These results confirm the effectiveness of the model in capturing financial volatility, enabling reliable early-warning systems for market crash prediction and risk management.

Problem

• Detecting anomalies and forecasting risks in volatile financial time series data
• Capturing long-term dependencies and periodic patterns in nonstationary financial markets
• Improving prediction accuracy for market crashes and financial distress signals

Innovation

• FEDformer models time-frequency dynamics for financial data
• Residual-based detector identifies anomalies from prediction errors
• Risk head forecasts financial distress using latent embeddings