Academic Journal of Business & Management, 2025, 7(7); doi: 10.25236/AJBM.2025.070722.
Haoyu Wu1, Jingwen Zhang2
1International Business College, Dongbei University of Finance and Economics, Dalian, 116025, China
2School of Accounting, Dongbei University of Finance and Economics, Dalian, 116025, China
As the impact of climate change on financial and industrial systems intensifies, building a high-precision and strong generalization prediction model has become an important research direction for intelligent economic management. This paper proposes a multi-step time series prediction method based on the Informer model, which integrates multi-source heterogeneous data such as meteorology, finance and industry to achieve medium- and short-term predictions of key variables such as carbon prices and industrial output value. The constructed model retains the advantages of the Transformer structure and introduces the ProbSparse Attention mechanism and the time embedding module, which significantly improves the efficiency of long sequence modeling and the ability to identify nonlinear relationships. Experimental results show that Informer is superior to traditional machine learning and deep learning models in terms of prediction accuracy, stability and multi-step fitting ability, and is suitable for multi-variable and multi-scale time series modeling needs in complex systems. This study provides theoretical support and algorithmic basis for the application of intelligent prediction models in scenarios such as green finance, energy scheduling and industrial early warning.
Informer Model, Time Series Forecasting, Climate Finance, Sparse Attention Mechanism, Industrial Economy
Haoyu Wu, Jingwen Zhang. A Multi-Source Time Series Forecasting Framework Based on Informer for Climate Finance and Industrial Economy. Academic Journal of Business & Management (2025), Vol. 7, Issue 7: 168-175. https://doi.org/10.25236/AJBM.2025.070722.
[1] Y. Wang, Z. Wang, and Y. Luo, “A hybrid carbon price forecasting model combining time series clustering and data augmentation,” Energy, vol. 308, p. 132929, Nov. 2024, doi: 10.1016/j. energy. 2024. 132929.
[2] M. Mohsin and F. Jamaani, “A novel deep-learning technique for forecasting oil price volatility using historical prices of five precious metals in context of green financing – a comparison of deep learning, machine learning, and statistical models,” Resour. Policy, vol. 86, p. 104216, Oct. 2023, doi: 10.1016/j.resourpol.2023.104216.
[3] M. Ji, J. Du, P. Du, T. Niu, and J. Wang, “A novel probabilistic carbon price prediction model: integrating the transformer framework with mixed-frequency modeling at different quartiles,” Appl. Energy, vol. 391, p. 125951, Aug. 2025, doi: 10.1016/j.apenergy.2025.125951.
[4] A. Ma, F. Shen, Z. Li, X. Peng, and W. Zhong, “An adjustable robust optimization model under dynamic informer-based framework for industrial renewable energy systems,” Process Saf. Environ. Prot., vol. 197, p. 107062, May 2025, doi: 10.1016/j.psep.2025.107062.
[5] X. Zhang, J. Wang, and X. He, “An optimal multi-scale ensemble transformer for carbon emission allowance price prediction based on time series patching and two-stage stabilization,” Energy, vol. 328, p. 136457, Aug. 2025, doi: 10.1016/j.energy.2025.136457.
[6] X. Cui and D. Niu, “Carbon price point–interval forecasting based on two-layer decomposition and deep learning combined model using weight assignment,” J. Cleaner Prod., vol. 483, p. 144124, Dec. 2024, doi: 10.1016/j.jclepro.2024.144124.
[7] B. Jia, H. Wu, and K. Guo, “Chaos theory meets deep learning: a new approach to time series forecasting,” Expert Syst. Appl., vol. 255, p. 124533, Dec. 2024, doi: 10.1016/j.eswa.2024.124533.
[8] A. Zeb, J. Linnosmaa, M. Seppi, and O. Saarela, “Developing deep learning surrogate models for digital twins in mineral processing – a case study on data-driven multivariate multistep forecasting,” Miner. Eng., vol. 216, p. 108867, Sep. 2024, doi: 10.1016/j.mineng.2024.108867.
[9] M. J. Jiménez-Navarro, M. Lovrić, S. Kecorius, E. K. Nyarko, and M. Martínez-Ballesteros, “Explainable deep learning on multi-target time series forecasting: an air pollution use case,” Results Eng., vol. 24, p. 103290, Dec. 2024, doi: 10.1016/j.rineng.2024.103290.
[10] A. Nagdiya, V. Kapoor, and V. Tokekar, “Hybrid deep learning architecture combining attention mechanisms and recurrent neural networks for enhanced time series analysis,” Int. Conf. Mach. Learn. Data Eng., vol. 258, pp. 3315–3323, Jan. 2025, doi: 10.1016/j.procs.2025.04.589.
[11] Z. Chen, M. Ma, T. Li, H. Wang, and C. Li, “Long sequence time-series forecasting with deep learning: a survey,” Inf. Fusion, vol. 97, p. 101819, Sep. 2023, doi: 10.1016/j.inffus.2023.101819.
[12] J. Chen, A. Guan, J. Du, and A. Ayush, “Multivariate time series prediction with multi-feature analysis,” Expert Syst. Appl., vol. 268, p. 126302, Apr. 2025, doi: 10.1016/j.eswa.2024.126302.
[13] D. Yang, B. Gao, S. Wang, and H. Xiang, “Robustness test for fouling state identification of homogeneous pressure electrodes based on confidence ellipsoids,” IEICE Electron. Express, 2025, doi: 10.1587/elex.22.20240283.
[14] F. M. D’Arcangelo, T. Kruse, M. Pisu, and M. Tomasi, “The effect of climate policies on firm financing and investment through the banking channel,” J. Environ. Manage, vol. 387, p. 125866, Jul. 2025, doi: 10.1016/j.jenvman.2025.125866.
[15] C. Zhao, K. Dong, R. Nepal, and K. K. Zander, “The panacea of heatwaves: can climate finance mitigate heatwave welfare costs?,” International Journal of Disaster Risk Reduction, vol. 117, p. 105197, Feb. 2025, doi: 10.1016/j.ijdrr.2025.105197.