Prediction of Factors Supporting the Success of BAZNAS RI Digital Fundraising Using the C4.5 Algorithm

Abstract

The C4.5 algorithm as a prediction method in zakat fundraising. The approach utilized incorporates the CRISP-DM (Cross-Industry Standard Process for Data Mining), which encompasses the data preparation phase to transform raw data into analyzable format, alongside the application of the C4.5 algorithm for constructing a decision tree model. The prediction model formed has the ability to predict the success  of zakat fundraising from prospective muzaki. The primary aim of this research is to create a predictive model aimed at assisting the National Amil Zakat Agency of the Republic of Indonesia (BAZNAS RI) in enhancing the efficacy of their zakat fundraising strategy planning. Through this prediction model, BAZNAS RI can optimize  zakat fundraising strategies  and allocate resources more efficiently. The dataset for Muzaki encompasses various demographic factors such as age, gender, occupation group, transaction period, nominal amount, and nominal category, which served as inputs for this study. Evaluation of the model revealed an impressive accuracy rate of 92% in predictive capabilities, suggesting the potential effectiveness of this model as a supportive tool for BAZNAS RI's zakat fundraising endeavors.