<![CDATA[Data-driven Human Resources (HR) management is an important aspect in improving organizational productivity and efficiency in the digital era. This research aims to cluster employees based on performance using the K-Means Clustering algorithm and evaluate the influence of demographic factors on job performance. The dataset used is a public dataset from Kaggle, including employee performance information such as Key Performance Indicators (KPIs), training scores, multiple trainings, performance appraisals, awards, as well as demographic attributes such as gender, age, education level, and recruitment channels. Using the six-stage CRISP-DM framework, the data was processed using StandardScaler, and the optimal number of clusters was determined through the Elbow Method, Davies-Bouldin Index, and Silhouette Score, resulting in two main clusters. Cluster 0 includes high-performing employees with KPIs above 80%, good performance ratings, and good training scores, while Cluster 1 consists of low-performing employees, with lower KPIs, poor performance ratings, and training scores. Analysis showed demographic factors did not significantly affect employee performance. This research recommends focused training for low-performing employees and rewards for high-performing employees, so that each employee can reach their full potential and support organizational productivity.]]>
Copyrights © 2025
