This study integrates fuzzy logic with DuPont ratio analysis reϐlecting ϐinancial ratios to construct enterprise proϐitability prediction model. The main indicators of DuPont analysis system are processed by principal component analysis (PCA) algorithm to obtain the calculation method of the mean value of enterprise comprehensive proϐitability indicators. The BP neural network is used to construct the enterprise proϐitability index model, and the momentum term is introduced into the model to improve the convergence speed of the BP neural network. The Takagi-Sugeno type fuzzy neural network is utilized to construct the enterprise development ability index model, and the enterprise proϐitability prediction model is constructed by combining the output structure of BP neural network. The relevant data of 792 listed enterprises in a certain industry in China’s A-share market are selected as the research objects of this paper, and the data are inputted into BP neural network and Takagi-Sugeno fuzzy neural network to obtain the output results of the model, and the output results are used as the input data of the ϐinal proϐitability prediction model to forecast the proϐitability of the enterprise in the next ϐive years. The experimental results show that the model in this paper can effectively realize the prediction of corporate proϐitability, which is signiϐicantly conducive to the sustainable development of enterprises and the adjustment and improvement of strategic policies.