Prediction of the Number of New Students at Bangka Belitung University Using Fuzzy Logic Tsukamoto Method

Abstract

The fluctuation in the number of new students each year is a significant challenge for universities in designing admission policies and providing efficient academic facilities. This study aims to predict the number of new students at Bangka Belitung University using the Tsukamoto fuzzy logic method. This method was chosen because of its ability to manage uncertain historical numerical data and produce precise linguistic rule-based estimates. The data analyzed included the number of applicants and students accepted in six faculties during the period 2020–2023. The analysis process involved the stages of fuzzification, fuzzy inference, and defuzzification. The prediction results for 2024 showed a Mean Absolute Percentage Error (MAPE) value of 16.19%, which is included in the “accurate” category according to the Lewis scale. These findings indicate that the Tsukamoto method is effective in producing reliable predictions and can be applied as a tool in strategic decision making, especially in managing capacity and improving the quality of higher education services.