Analysis of Dynamic Cost Variations in Electricity Data Based on Machine Learning

With the advancement of the digital era, data has become a critical production resource, offering broader business perspectives and decision-making support for both enterprises and individuals, and driving innovation. In the electricity sector, electricity data is equally significant, yet determining the valuation of electricity data remains a crucial issue. This paper examines the characteristics of electricity data assets and analyzes the strengths and weaknesses of existing data valuation models. By integrating Analytic Hierarchy Process (AHP) with machine learning techniques, a pricing model for electricity data assets is constructed. Combining subjective assessments with machine learning, the study develops a hierarchical structure and judgment matrix to quantitatively analyze the specific value of electricity data. This research provides robust support for enhancing the efficiency of electrical systems, reducing costs, and promoting sustainable development.