Abstract: Focusing on the accurate prediction of electricity sales revenue of electric power enterprises, this paper innovatively constructs a comprehensive forecasting model based on factor analysis. In-depth analysis of macroeconomic environment, market policy orientation, enterprise operation efficiency and user behavior characteristics of the four core dimensions, through Pearson correlation coefficient method scientific selection of key influencing factors, and the use of principal component analysis (PCA) technology to achieve data dimensionality reduction, extract economic factors, policy factors and technical factors three core components. On this basis, the multiple linear regression prediction model is constructed, and the ridge regression algorithm is introduced to effectively solve the multicollinearity problem and significantly improve the prediction accuracy of the model. With the actual data of a provincial power company of the State Grid as the validation sample, the prediction error of the model is successfully controlled within ±2%, which fully proves the applicability and reliability of the model in the forecast of electricity sales revenue.