Academic Journal of Business & Management, 2025, 7(4); doi: 10.25236/AJBM.2025.070431.
Chunxue Yao
Statistics and Mathematics College, Inner Mongolia University of Finance and Economics, Hohhot, China
In the rapidly changing digital business environment, accurately assessing corporate growth is of utmost importance for corporate strategy formulation, investment decisions, and industry research. This study focuses on multiple industries, collects data from 84 Chinese A-share companies from 2000 to 2022, and uses time-series analysis to explore data trends. After data processing, the K-means clustering algorithm is adopted. The elbow method is used to determine the clustering strategy, and K-means classification is carried out. According to the growth characteristics, the enterprises are divided into three categories. Dimensionality reduction is performed to find 13 factors to assist in decision-making, showing the commonalities and differences in different stages. Researchers use the K-Nearest Neighbor algorithm (KNN), Classification and Regression Tree algorithm (CART), and Support Vector Machine (SVM) to build a growth prediction model. By optimizing with time-series data, the accuracy of the model has been significantly improved. The research results prove that the combination of machine learning and time-series analysis is accurate and reliable in evaluating and predicting corporate growth, and can effectively identify growth patterns. The results of this study are helpful for enterprises to formulate strategic plans, assist investors in making decisions, and provide references for policymakers to support industrial development.
Time series, Machine learning, Multiple industries, Cluster analysis
Chunxue Yao. Application of Machine Learning in Enterprise Growth Assessment: A Study of China's A-Share Listed Enterprises in Multiple Industries from 2000 to 2022. Academic Journal of Business & Management (2025), Vol. 7, Issue 4: 246-252. https://doi.org/10.25236/AJBM.2025.070431.
[1] Yu L, Gao X, Lyu J, et al. Green growth and environmental sustainability in China: the role of environmental taxes[J]. Environmental Science and Pollution Research, 2023, 30(9): 22702-22711.
[2] Jordan M I, Mitchell T M. Machine learning: Trends, perspectives, and prospects[J]. Science, 2015, 349(6245): 255-260.
[3] Cui M. Introduction to the k-means clustering algorithm based on the elbow method[J]. Accounting, Auditing and Finance, 2020, 1(1): 5-8.
[4] Wang X, Smith K, Hyndman R. Characteristic-based clustering for time series data[J]. Data mining and knowledge Discovery, 2006, 13: 335-364.
[5] Wang R, Tan J. Exploring the coupling and forecasting of financial development, technological innovation, and economic growth[J]. Technological Forecasting and Social Change, 2021, 163: 120466.
[6] Li C, Zhang Y, Li X, et al. Artificial intelligence, household financial fragility and energy resources consumption: Impacts of digital disruption from a demand-based perspective[J]. Resources Policy, 2024, 88: 104469.
[7] Wang J, Liu W, Chen L, et al. Analysis of China's non-ferrous metals industry's path to peak carbon: A whole life cycle industry chain based on copper[J]. Science of The Total Environment, 2023, 892: 164454.
[8] Teepapal T. AI-driven personalization: Unraveling consumer perceptions in social media engagement[J]. Computers in Human Behavior, 2025, 165: 108549.