Aiming to solve the problems in the traditional multiple regression analysis model for predicting college sports performance based on the principles of econometrics, a predictive model that combines genetic algorithm (GA), college sports performance evaluation and regression analysis is proposed. GA is used to conduct dynamic and supervised optimisation evaluation of college sports performance; on this basis, combined with regression analysis and GA's global optimisation capabilities, a complex nonlinear relationship between student sports performance and influencing factors is established; the student's performance is calculated based on the college sports performance. The results show that the method has high prediction accuracy and good stability.