Assessing the Performance of Small and Medium-Sized Enterprises Through Data Processing Techniques and GRBT Model

The evaluation of small and medium-sized enterprises (SMEs) is of utmost importance given their significant role in the global economy. As such, a reliable and accurate indicator system is essential to effectively assess their performance. Currently, the existing index system for evaluating the growth of SMEs is predominantly a single index system or a composite index system designed for direct evaluation. This paper proposes a growth evaluation model for SMEs based on the growth evaluation system theory, data processing, and machine learning algorithm models. The proposed model examines the impact of various dimensions on enterprise growth. To validate its utility and feasibility, we evaluate the SMEs listed in the National Equities Exchange and Quotations (NEEQ), utilizing data processing techniques, Gradient Boosted Regression Trees (GBRT) algorithm in machine learning, and empirical analog verification to assess their growth potential.