Unsupervised Clustering and Visual Learning Analytics for Intelligent Competency Assessment in Government Education Selection Systems

Main Article Content

👤 Chen Junru
🏢 Liaoning University of Science and Technology, China
👤 Cheng Fan
🏢 Southwest University, China

Artificial intelligence and learning analytics have become increasingly important in supporting data driven educational assessment and competency profiling. This study proposes an unsupervised machine learning approach for competency profiling of government education selection participants using clustering and learning analytics techniques based on Seleksi Kompetensi Dasar (SKD) assessment data. The dataset consisted of 2,150 participants and included four assessment variables, namely Tes Wawasan Kebangsaan (TWK), Tes Intelegensia Umum (TIU), Tes Karakteristik Pribadi (TKP), and total SKD score. Prior to clustering, all variables were standardized using the StandardScaler method. The K Means algorithm was employed to identify latent competency structures, while the optimal number of clusters was determined using the Elbow Method and Silhouette Score analysis. Clustering performance was evaluated using Silhouette Score, Davies Bouldin Index, and Calinski Harabasz Score. The experimental results demonstrated that the optimal clustering configuration was achieved at with a silhouette score of 0.585, indicating good cluster cohesion and separation. The findings revealed two distinct participant competency groups, where Cluster 0 represented high performing participants with consistently higher scores across all SKD dimensions, while Cluster 1 demonstrated lower competency readiness. Among all variables, TIU emerged as the most discriminative factor in competency differentiation. Furthermore, PCA and t SNE visualizations confirmed clear cluster separation with minimal overlap, indicating the presence of meaningful latent competency structures within the dataset. These findings demonstrate that unsupervised machine learning and learning analytics approaches can effectively support intelligent educational assessment, competency mapping, and data driven decision making in educational selection systems.

Junru, C., & Fan, C. (2026). Unsupervised Clustering and Visual Learning Analytics for Intelligent Competency Assessment in Government Education Selection Systems. Artificial Intelligence in Learning, 2(4), 288–307. https://doi.org/10.63913/ail.v2i4.75

Article Details

Section
Articles

Similar Articles

1 2 3 4 > >> 

You may also start an advanced similarity search for this article.