Article: The construction of energy price legal regulation effect prediction model based on LSTM neural network Journal: International Journal of Information and Communication Technology (IJICT) 2026 Vol.27 No.32 pp.1 - 17 Abstract: As global energy markets grow more complex and volatile, existing forecasting accuracy and policy effect evaluations remain insufficient. An urgent need exists for a precise prediction model integrating legal policies and multi-dimensional energy market data. This paper proposes an LSTM-based model to predict legal regulation effects on energy prices: it uses semantic feature extraction for policy texts, builds a spatiotemporal fusion framework for multi-source heterogeneous data, and designs a hierarchical memory unit's dynamic regulation module to adapt to stage-specific policy adjustments. In historical data, the model's training-set MAE declined fluctuatingly: 56.72 CNY/ton standard coal (vague initial policies) dropped to 28.9 CNY (refined policies). After tiered pricing, policy-related price volatility fell to 45.6%. Policy clarity correlates positively with model accuracy; refinement reduced LSTM's price trend capture error by 66.6%. Inderscience Publishers - linking academia, business and industry through research

Title: The construction of energy price legal regulation effect prediction model based on LSTM neural network

Authors: Yan Zhao; Yingguo Jiang; Guoyu Wang

Addresses: Xinxiang Vocational and Technical College, Xinxiang, 453006, China ' Xinxiang Vocational and Technical College, Xinxiang, 453006, China ' Xinxiang Vocational and Technical College, Xinxiang, 453006, China

Abstract: As global energy markets grow more complex and volatile, existing forecasting accuracy and policy effect evaluations remain insufficient. An urgent need exists for a precise prediction model integrating legal policies and multi-dimensional energy market data. This paper proposes an LSTM-based model to predict legal regulation effects on energy prices: it uses semantic feature extraction for policy texts, builds a spatiotemporal fusion framework for multi-source heterogeneous data, and designs a hierarchical memory unit's dynamic regulation module to adapt to stage-specific policy adjustments. In historical data, the model's training-set MAE declined fluctuatingly: 56.72 CNY/ton standard coal (vague initial policies) dropped to 28.9 CNY (refined policies). After tiered pricing, policy-related price volatility fell to 45.6%. Policy clarity correlates positively with model accuracy; refinement reduced LSTM's price trend capture error by 66.6%.

Keywords: LSTM neural network; energy price forecasts; legal regulation; multi-source heterogeneous data; spatio-temporal fusion.

DOI: 10.1504/IJICT.2026.152861

International Journal of Information and Communication Technology, 2026 Vol.27 No.32, pp.1 - 17

Received: 19 Sep 2025
Accepted: 29 Oct 2025
Published online: 13 Apr 2026 *

Title: The construction of energy price legal regulation effect prediction model based on LSTM neural network

Keep up-to-date