Time-Aligned Rolling-Correlation Graph Fusion for Financial Fair-Value Observability Proxies: A Controlled Transformer Study

Authors

  • Quinn Cruz Wisconsin School of Business, University of Wisconsin–Madison, Madison, United States

DOI:

https://doi.org/10.54097/hm6fa751

Keywords:

Fair value hierarchy, temporal graph neural networks, rolling correlation, Transformer, negative control, synthetic benchmark

Abstract

Fair-value hierarchy decisions concern the observability and significance of valuation inputs, whereas securities-market time series provide only indirect proxies. We study whether time-aligned rolling-correlation graphs improve sequence-based prediction under an explicitly synthetic three-class observability task. A reproducible architecture pairs window-level Transformer representations with Pearson-correlation message passing, then uses an element-wise gate to combine own-instrument and peer context. We test stable and changed-correlation regimes over three independently generated populations and two model initializations each, including static, recent-only and randomly rewired graph controls. In the changed-correlation setting, the dynamic hybrid obtains macro-F1 0.671 ± 0.081, compared with 0.667 ± 0.083 for the static hybrid, 0.668 ± 0.070 for rewired edges, and 0.832 ± 0.020 for random forests. Removing the fusion gate reduces dynamic macro-F1 to 0.536 ± 0.072. The stable-regime comparison likewise shows no systematic advantage for rolling graphs. The evidence suggests that fusion can be useful, but small gains attributed to dynamic topology can disappear under appropriate negative controls. The archived source, data generation process, individual probabilities, and paired comparisons make these results independently testable. The proxy classes are not audited IFRS 13 fair-value levels.

Downloads

Download data is not yet available.

References

[1] IFRS Foundation. (2011). IFRS 13 Fair Value Measurement. International Accounting Standards Board. https://www.ifrs.org/issued-standards/list-of-standards/ifrs-13-fair-value-measurement/

[2] Song, C. J., Thomas, W. B., & Yi, H. (2010). Value relevance of FAS No. 157 fair value hierarchy information and the impact of corporate governance mechanisms. The Accounting Review, 85(4), 1375–1410. https://doi.org/10.2308/accr.2010.85.4.1375 DOI: https://doi.org/10.2308/accr.2010.85.4.1375

[3] Teng, D. (2025). TRIAD: Deadline- and reliability-aware scheduling for post-earthquake structural assessment workflows. World Journal of Engineering Research, 3(6), 55–66. DOI: https://doi.org/10.61784/wjer4124

[4] Jiang, B., Wu, B., Cao, J., & Tan, Y. (2025). Interpretable fair value hierarchy classification via hybrid Transformer-GNN architecture. IEEE Access, 13, 198142–198163. https://doi.org/10.1109/ACCESS.2025.3634551 DOI: https://doi.org/10.1109/ACCESS.2025.3634551

[5] Vaswani, A., et al. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30.

[6] Kipf, T. N., & Welling, M. (2017). Semi-supervised classification with graph convolutional networks. In Proceedings of the ICLR. arXiv:1609.02907.

[7] Hamilton, W. L., Ying, Z., & Leskovec, J. (2017). Inductive representation learning on large graphs. Advances in Neural Information Processing Systems, 30, 1024–1034.

[8] Veličković, P., et al. (2018). Graph attention networks. In Proceedings of the ICLR. arXiv:1710.10903.

[9] Pareja, A., et al. (2020). EvolveGCN: Evolving graph convolutional networks for dynamic graphs. Proceedings of the AAAI Conference on Artificial Intelligence, 34(4), 5363–5370. https://doi.org/10.1609/aaai.v34i04.5984 DOI: https://doi.org/10.1609/aaai.v34i04.5984

[10] Chen, J., Han, X., Zhang, X., & Yang, Y. (2023). Exact concept-level explanations for early detection of financial misstatements. Eurasia Journal of Science and Technology, 5(2), 34–48. DOI: https://doi.org/10.61784/ejst4162

[11] Corradini, F., Gerosa, F., Gori, M., Lucheroni, C., Piangerelli, M., & Zannotti, M. (2026). A systematic literature review of spatio-temporal graph neural network models for time series forecasting and classification. Neural Networks, 195, 108269. https://doi.org/10.1016/j.neunet.2025.108269 DOI: https://doi.org/10.1016/j.neunet.2025.108269

[12] Lim, B., Arık, S. Ö., Loeff, N., & Pfister, T. (2021). Temporal fusion Transformers for interpretable multi-horizon time series forecasting. International Journal of Forecasting, 37(4), 1748–1764. https://doi.org/10.1016/j.ijforecast.2021.03.012 DOI: https://doi.org/10.1016/j.ijforecast.2021.03.012

[13] Wu, Z., Pan, S., Long, G., Jiang, J., Chang, X., & Zhang, C. (2020). Connecting the dots: Multivariate time series forecasting with graph neural networks. In Proceedings of the ACM SIGKDD (pp. 753–763). https://doi.org/10.1145/3394486.3403118 DOI: https://doi.org/10.1145/3394486.3403118

[14] Shchur, O., Mumme, M., Bojchevski, A., & Günnemann, S. (2018). Pitfalls of graph neural network evaluation. In NeurIPS Relational Representation Learning Workshop. arXiv:1811.05868.

[15] Breiman, L. (2001). Random forests. Machine Learning, 45, 5–32. https://doi.org/10.1023/A:1010933404324 DOI: https://doi.org/10.1023/A:1010933404324

[16] Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the ACM SIGKDD (pp. 785–794). https://doi.org/10.1145/2939672.2939785 DOI: https://doi.org/10.1145/2939672.2939785

[17] Borisov, V., Leemann, T., Seßler, K., Haug, J., Pawelczyk, M., & Kasneci, G. (2024). Deep neural networks and tabular data: A survey. IEEE Transactions on Neural Networks and Learning Systems, 35(6), 7499–7519. https://doi.org/10.1109/TNNLS.2022.3229161 DOI: https://doi.org/10.1109/TNNLS.2022.3229161

[18] Gu, S., Kelly, B., & Xiu, D. (2020). Empirical asset pricing via machine learning. The Review of Financial Studies, 33(5), 2223–2273. https://doi.org/10.1093/rfs/hhaa009 DOI: https://doi.org/10.1093/rfs/hhaa009

[19] Jain, S., & Wallace, B. C. (2019). Attention is not explanation. In Proceedings of NAACL-HLT (pp. 3543–3556). https://doi.org/10.18653/v1/N19-1357 DOI: https://doi.org/10.18653/v1/N19-1357

[20] Zhou, F. (2026). Moment-constrained side-force allocation for wind-assisted merchant ships: Hydrodynamic performance of retractable anti-leeway fins and flap rudders. Innovation and Technology Studies, 3(1), 27–41. DOI: https://doi.org/10.61784/its4027

[21] Guo, C., Pleiss, G., Sun, Y., & Weinberger, K. Q. (2017). On calibration of modern neural networks. In Proceedings of the 34th International Conference on Machine Learning (Vol. PMLR 70, pp. 1321–1330).

[22] Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 16, 321–357. https://doi.org/10.1613/jair.953 DOI: https://doi.org/10.1613/jair.953

[23] Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. In Proceedings of the ICLR. arXiv:1412.6980.

[24] Bergstra, J., Bardenet, R., Bengio, Y., & Kégl, B. (2011). Algorithms for hyper-parameter optimization. Advances in Neural Information Processing Systems, 24, 2546–2554.

[25] Han, X., Yang, Y., Chen, J., Wang, M., & Zhou, M. (2025). Symmetry-Aware Credit Risk Modeling: A Deep Learning Framework Exploiting Financial Data Balance and Invariance. Symmetry, 17(3), 341. https://doi.org/10.3390/sym17030341 DOI: https://doi.org/10.3390/sym17030341

[26] Chen, Z., Wang, M., Zeng, Z., & Ping, W. (2026). Uncertainty-Aware Financial Forecasting: Leveraging Conformal Prediction for Risk-Adjusted Models. IEEE Access. https://doi.org/10.1109/ACCESS.2026.3702666 DOI: https://doi.org/10.1109/ACCESS.2026.3702666

Downloads

Published

16-11-2026

Issue

Section

Articles

How to Cite

Cruz, Q. (2026). Time-Aligned Rolling-Correlation Graph Fusion for Financial Fair-Value Observability Proxies: A Controlled Transformer Study. International Journal of World Economic Research, 4(1), 26-33. https://doi.org/10.54097/hm6fa751