Cross-Industry Standard Process For Data Mining (CRISP-DM) For Discovering Association Rules in Graduate Tracer Study Data of Islamic Higher Education Institution

The Career Development Center (CDC) at UIN Syarif Hidayatullah Jakarta faces challenges when designing development programs for its diverse graduate groups, including those employed, pursuing further studies, or engaged in entrepreneurship. The complexity of tracer study data hampers the identification of prevailing association patterns. This study aims to uncover these patterns within UIN Syarif Hidayatullah Jakarta’s tracer study data, aiding the CDC in enhancing career services and target mapping for diverse graduates. The research follows the CRISP-DM (Cross-Industry Standard Process for Data Mining) methodology, using the FP-Growth algorithm. Tracer study data from 2021 UIN Syarif Hidayatullah Jakarta graduates (1355 records) is reduced to 925 records for analysis using RapidMiner and Microsoft Excel. The findings reveal association patterns for graduates categorized by employment status, educational pursuits, entrepreneurship endeavors, and advanced graduates not employed. This research offers a structured approach to navigate tracer study data complexities and proposes an action plan for enhancing UIN Syarif Hidayatullah Jakarta Career Center services based on these patterns, providing a systematic guide to address the tracer study data complexity.