Predicting child alimony under Islamic shariah law using hybrid fuzzy inference system

Abstract

This paper proposes a novel approach to predicting child alimony under Islamic shariah law using a hybrid fuzzy inference system, integrating Mamdani and Takagi-Sugeno-Kang (TSK) fuzzy systems. Machine learning algorithms have become valuable tools for legal decision-making, but judicial process delays can lead to adverse effects. Our model aims to expedite decision-making and minimize legal fees by accurately determining the proper amount of alimony for children after divorce. We collected data from 94 alimony cases and evaluated the model’s performance using accuracy, precision, recall, and F1-score metrics. The hybrid fuzzy system achieved promising results with 69% accuracy, 70% precision, 75% recall and 69% F1 score. Notably, the model reduced bias and standardization in decision-making, promoting fairness. However, the study suggests potential areas for improvement and emphasizes trans-parent judgment processes and coordination among judges in assessing alimony costs based on sufficiency and ma’ruf criteria. This research significantly contributes to machine learning applications in the judicial domain. It provides a valuable decision-making tool for judges and lawyers to enhance the judicial process’s efficiency and ensure children’s welfare in divorce cases under Islamic shariah law. Further research can enhance the model’s effectiveness and reliability, opening avenues for continued exploration in this field.