Adaptive Multi-Scale Anomaly Detection for Cross-Sector Financial Time Series via End-to-End Wavelet-Attention Fusion

Mengting Zhang; Junxiang Lu

doi:10.62177/apemr.v3i5.1855

Authors

Mengting Zhang Xi'an Polytechnic University
Junxiang Lu Xi'an Polytechnic University

DOI:

https://doi.org/10.62177/apemr.v3i5.1855

Keywords:

Financial Time Series, Anomaly Detection, Differentiable Wavelet, Sector Heterogeneity, Adaptive Fusion

Abstract

Traditional two-stage pipelines for financial anomaly detection suffer from a critical yet often overlooked flaw: the wavelet decomposition and the downstream detector are optimized independently. When a fixed Haar filter encounters the fat-tail shocks typical in A-share sectors, gradient flow breaks at the decomposition boundary, and the detector receives suboptimal frequency segments. We introduce EWAF-AE, an autoencoder that embeds discrete wavelet transform as a learnable layer, allowing the spectral filters to co-train with the encoder. Instead of a homogeneous backbone, we split the encoding: a shallow Transformer handles the low-frequency trend branch, while a masked locality-sensitive attention module processes high-frequency details. A gating network then calibrates the fusion ratio per sector—nonferrous metals receive heavier trend weighting (0.888), whereas banking shifts toward detail sensitivity (0.252)—based on rolling volatility and a learnable sector embedding. The anomaly score is not a single MSE, but a weighted composite of pixel-level, trend-consistency, detail-sparsity, and spectral losses, augmented by a triplet margin loss on pseudo-anomalous samples. On six A-share sector indices from 2015 to 2025, EWAF-AE hits 83.3% of benchmark crisis events, compared with 25.0% for Isolation Forest and 41.7% for LSTM-AE.

Downloads

Download data is not yet available.

References

Box, G. E. P., & Jenkins, G. M. (1970). Time series analysis: forecasting and control. Holden-Day.

Bollerslev, T. (1986). Generalized autoregressive conditional heteroskedasticity. Journal of Econometrics, 31, 307–327.

Chandola, V., Banerjee, A., & Kumar, V. (2009). Anomaly detection: A survey. ACM Computing Surveys, 41, 1–58.

Liu, F. T., Ting, K. M., & Zhou, Z. H. (2008). Isolation forest. In Proceedings of the 2008 IEEE International Conference on Data Mining (ICDM) (pp. 413–422). IEEE.

Breunig, M. M., Kriegel, H.-P., Ng, R. T., & Sander, J. (2000). LOF: identifying density-based local outliers. In Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data (pp. 93–104). ACM.

Huo, W. G., & Wang, H. F. (2020). Time series anomaly detection method based on autoencoder and hidden Markov model. Journal of Computer Applications, 40, 1329–1334. (in Chinese)

Malhotra, P., Ramakrishnan, A., Anand, G., Vig, L., Agarwal, P., & Shroff, G. (2016). LSTM-based encoder-decoder for multi-sensor anomaly detection. arXiv preprint arXiv:1607.00148.

Su, Y., Zhao, Y., Niu, C., Liu, R., Sun, W., & Pei, D. (2019). Robust anomaly detection for multivariate time series through stochastic recurrent neural network. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (pp. 2828–2837). ACM.

Xu, H., Zhang, X., & Li, X. (2022). Anomaly transformer: Time series anomaly detection with association discrepancy. In International Conference on Learning Representations (ICLR).

Tuli, S., Casale, G., & Jennings, N. R. (2022). TranAD: Deep transformer networks for anomaly detection in multivariate time series data. Proceedings of the VLDB Endowment, 15, 1201–1214.

Yang, Y., Zhang, C., Zhou, T., Wang, Y., & Chen, H. (2023). DCdetector: Dual attention contrastive representation learning for time series anomaly detection. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (pp. 3033–3045). ACM.

Cho, Y., Lee, J. H., Ham, G., & Park, J. (2025). Generality-aware self-supervised transformer for multivariate time series anomaly detection. Applied Intelligence, 55(7), 604. https://doi.org/10.1007/s10489-025-06304-4

Zhou, H., Zhang, S., Peng, J., Zhang, S., Li, J., Xiong, H., & Zhang, W. (2021). Informer: Beyond efficient transformer for long sequence time-series forecasting. In AAAI Conference on Artificial Intelligence (pp. 11106–11115).

Wu, H., Xu, J., Wang, J., & Long, M. (2021). Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. In Advances in Neural Information Processing Systems (NeurIPS) (Vol. 34, pp. 22419–22430).

Zhou, T., Niu, P., Wang, X., Sun, L., & Jin, R. (2022). FEDformer: Frequency enhanced decomposed transformer for long-term series forecasting. In International Conference on Machine Learning (ICML) (pp. 27268–27286). PMLR.

Wu, H., Hu, T., Liu, Y., Zhou, J., Wang, J., & Long, M. (2023). TimesNet: Temporal 2D-variation modeling for general time series analysis. In International Conference on Machine Learning (ICML) (pp. 37881–37896). PMLR.

Chen, Z., Chen, D., Zhang, X., & Liu, Y. (2024). DGTAD: Decomposition GAN-based transformer for anomaly detection in multivariate time series data. Applied Intelligence, 54(24), 13038–13056.

Yahya, M. A., Ali, S., Hussain, A., & Khan, Z. (2025). Deep learning for multivariate time series anomaly detection. Applied Intelligence, 55(7), 1–20.

Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323, 533–536.

Baldi, P., & Hornik, K. (1989). Neural networks and principal component analysis: Learning from examples without local minima. Neural Networks, 2, 53–58.

Japkowicz, N., Myers, C., & Gluck, M. A. (1995). A novelty detection approach to classification. In Proceedings of the 14th International Joint Conference on Artificial Intelligence (IJCAI) (pp. 518–523). Morgan Kaufmann.

Moya, M. M., & Hush, D. R. (1996). Network constraints and multi-objective optimization for one-class classification. Neural Networks, 9, 463–474.

Mallat, S. G. (1989). A theory for multiresolution signal decomposition: The wavelet representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 11, 674–693.

Daubechies, I. (1988). Orthonormal bases of compactly supported wavelets. Communications on Pure and Applied Mathematics, 41, 909–996.

Zhang, Q., & Benveniste, A. (1992). Wavelet networks. IEEE Transactions on Neural Networks, 3, 889–898.

Mallat, S. (1999). A wavelet tour of signal processing (2nd ed.). Academic Press. (Chapter 9: Adaptive Filtering).

Itti, L., Koch, C., & Niebur, E. (1998). A model of saliency-based visual attention for rapid scene analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20, 1254–1259.

Bahdanau, D., Cho, K., & Bengio, Y. (2015). Neural machine translation by jointly learning to align and translate. In Proceedings of the 3rd International Conference on Learning Representations (ICLR).