Using fuzzy logic and mathematical models to predict the financial efficiency of industrial enterprises

Abstract

The frequent development and unpredictable, dynamic nature of industrial enterprises require an effective financial efficiency detection process. The prediction process uses a large volume of information to identify the details of resources and operational performance in industrial applications. Traditional statistical techniques like regression analysis, decision tree, and machine learning approaches significantly improve prediction efficiency. However, the existing methods face uncertainty, robustness, and scalability issues when exploring high-dimensional data. The research difficulties are addressed by integrating the Fuzzy logic and mathematical model called the FuzzyMath approach. The FuzzyMath concept understands the industrial economic details and predicts financial performance with maximum recognition accuracy. The collected inputs are explored using fuzzy systems that use the multivariate and salp optimization algorithm at every step to improve the overall system efficiency. The optimized membership function, fuzzy rule, and defuzzification process minimize the computation difficulties and can handle the uncertainty issues effectively. Thus, the FuzzyMath-based created rules ensure 99.23% accuracy while predicting financial efficiency in industrial applications.