esc

Type at least two characters to start searching.

↑↓ select↵ openesc close

Share

Export Citation

APA
MLA
Chicago
Harvard
Vancouver
BIBTEX
RIS
Universitas Hasanuddin
Research output:Contribution to journal›Article›peer-review

Student Career Preferences Segmentation Based on Personality, Interests, and Competencies

Erna A.

2025 7th International Conference on Cybernetics and Intelligent System Icoris 2025

Published: 2025

Abstract

The disparity between graduate capabilities and industrial needs has significant implications for higher education. Consequently, institutions are expected to produce graduates whose skills align with the evolving demands of labor market societies, thereby contributing to inclusive and sustainable economic growth. However, many Indonesian institutions still lack a structured, data-driven mechanism to align students' personalities, interests, and competencies with suitable career pathways. This study addresses this gap by applying the K-means algorithm to analyze career preference patterns among 100 students at Dipa University of Makassar. In segmentation research, this algorithm is a preferred method due to its balance of simplicity and power, particularly in areas like customer profiling, career guidance, and educational analytics. Our data on the 100 students included demographic profiles, personality types (introvert, extrovert, ambivert), dominant interests (analytical, creative, interpersonal), and competencies (data science, programming, intelligent systems, graphic design). The analysis identified three distinct profiles: Cluster 0, namely The Balanced Adaptors, characterized by a balanced mix of personalities with versatile interests and moderate technical skills; Cluster 1, namely The Creative Communicators, predominantly introverted, with strong creative and interpersonal inclinations and proficiency in graphic-related skills; and Cluster 2, namely The Analytical Ambiverts, mainly ambiverted, exhibiting pronounced analytical and computational strengths. These findings underscore the potential of cluster-based analysis techniques for generating actionable student profiles, enabling institutions to design data-informed career guidance policies. The proposed approach offers a viable model for reducing the skills-industry mismatch and enhancing graduate employability within the Indonesian higher education context.

Other files and links

Fingerprint

EmployabilitySciences
Market segmentationSciences
Personality psychologySciences
SegmentationSciences
Higher educationSciences
PersonalitySciences
PsychologySciences
Cluster (spacecraft)Sciences
Computer scienceSciences
Career developmentSciences
Knowledge managementSciences
Interpersonal communicationSciences
HeuristicsSciences
PreferenceSciences
IndonesianSciences
ProductivitySciences
MarketingSciences
ProactivitySciences
Reliability (semiconductor)Sciences
Transferable skills analysisSciences
Career portfolioSciences
Medical educationSciences
TypologySciences
Big Five personality traitsSciences
Graduate studentsSciences
Cognitive Information ProcessingSciences
ConstructiveSciences
TUTORSciences
Applied psychologySciences
Public relationsSciences
AssertivenessSciences