Answers are grounded in this paper and cite their sources.
Analysis reveals a novel approach to classify enterprise tax sources in China, suggesting improved tax administration practices.
In the era of intelligent and sustainable development, artificial intelligence (AI) presents novel approaches for optimizing tax administration. This study delves into the potential of K-means clustering analysis in tax source management, leveraging AI’s data analysis prowess to refine the classification and oversight of enterprise tax sources in China. The research identifies four pivotal indicators — corporate income tax, net operating cash flow, total assets, and tax payable — for effectively monitoring enterprise tax payment status. Through clustering analysis and the incorporation of sustainability metrics, 433 listed companies are precisely categorized into three tiers: key, secondary key, and general tax source enterprises. This study unveils the latent application potential of K-means clustering in tax source management, offering governments and institutions a novel, efficient tool for tax data analysis. It addresses challenges such as the vastness and complexity of tax data, tax loophole identification, and tax plan optimization. With the proliferation of IoT-based fiscal and tax monitoring systems, enterprises generate immense volumes of tax-related data. K-means clustering, known for its computational simplicity and efficacy, provides a solution for real-time data classification and anomaly detection in these large-scale distributed data settings. By employing K-means clustering analysis, this study gains profound insights into the internal structure and latent patterns of tax data, facilitating more accurate tax trend predictions, anomaly detection, and the formulation of targeted tax policies.
No takes yet. Share an insight, caveat, or question.
Xin Han (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: