The Implementation of Data Mining in Measuring Student Satisfaction Levels at IAIN Kerinci

Measuring student satisfaction is crucial to consider, given the high level of competition in the education sector alongside the advancement of knowledge and technology. It is essential to ensure that the services expected by students align with what they actually receive. Measuring student satisfaction can significantly assist higher education institutions in improving the quality of services, which in turn can impact the increase in student enrollment. This study employs a quantitative method, utilizing one of the data mining techniques, namely classification with the C4.5 algorithm, to measure student satisfaction levels. The population in this study consists of active students at IAIN Kerinci, with a sample size of 100 respondents. These students act as subjects who provide assessments or opinions on variables characterized by Tangible, Reliability, Responsiveness, Assurance, and Empathy. The data is then processed using data mining classification techniques, and testing is performed with the aid of RapidMiner software. The calculation and testing results demonstrate that data mining successfully classifies the variables in measuring student satisfaction with excellent performance, producing 10 rules from the decision tree with an accuracy rate of 98.22%. These rules are expected to serve as a basis for decision-making to determine actions that need to be taken to enhance student satisfaction.