<![CDATA[Digital transformation within used automotive industry today demands paradigm shift from intuitive decision-making towards data-driven approach to face increasingly intense market competition dynamics. The primary problem identified in this research is high level of subjectivity in stock management and dependence on individual experience triggering organizational knowledge loss risks or knowledge loss. This study aims to optimize stock management strategy and mitigate these risks through integration of K-Means clustering algorithm and Socialization, Externalization, Combination, Internalization framework. The research method involves in-depth analysis of five hundred fifty-eight thousand eight hundred thirty-seven vehicle transaction data using data mining techniques to discover hidden patterns from automotive market behavior. Research results show that the algorithm successfully classified stock into three optimal clusters, where symbol k represents cluster number of three, with high performance proven by Calinski-Harabasz Index score of 283,364.95. These clusters differentiate assets into medium, high-risk, and premium categories based on physical condition and mileage, which allows companies to determine liquidation or retention strategies accurately. Integration with the framework ensures that data mining findings are transformed into permanently documented organizational knowledge management. The implementation of this model provides a significant impact for companies in improving operational efficiency and reducing dependence on individual memory. This research study provides a real contribution in creating an objective foundation for more measurable, systematic, and sustainable managerial decision-making for national industry sectors and other related complex business environment systems.]]>
Copyrights © 2026
