A Web-Based Zakat Recipient Determination System using the Naïve Bayes Algorithm

Abstract

As the third pillar of Islam, zakat must be fulfilled by Muslims who have met the requirements of Islamic law. In Indonesia, zakat is managed by by the National Amil Zakat Agency (BAZNAS). BAZNAS is obliged to distribute zakat to eligible people who call in Islamic is Mustahiq to receive zakat according to the applicable category rules. Mustahiq (beneficiaries) are groups entitled to receive zakat according to the priority scale arranged in the Zakat program. As a case study, BAZNAS in Pekanbaru city determines the recipient of zakat manually by interviewing each candidate. Factors influencing decisions, such as feelings, emotions, sentiments, and moods, can lead to wrong decisions. Human weakness contrasts with the advantages of artificial intelligence. Therefore, this study aimed to design and build a web-based application system to determine the category of the recipient of zakat automatically and quickly using the Naïve Bayes algorithm. A total of 3222 data in 2015–2017 were obtained in BAZNAS Pekanbaru for training data. Based on the experimental testing results, the highest accuracy was 93.7%, and F-measure was 96.7% in 80% of training data. Based on the test results, it can be concluded that web-based applications using the Naïve Bayes method has the potential to be used in determining the recipient of zakat in BAZNAS Pekanbaru.