Egyptian Social Insurance Big Data Mining Using Supervised Learning Algorithms
Youssef Senousy, Wael K. Hanna, Abdulaziz Shehab, Alaa Mohamed Riad, Hazem Mokhtar El-Bakry, Nashaat El-Khamisy · Revue d intelligence artificielle · 2019
Social insurance is an important way to defend individuals from the dangers of retirement, sickness, and financial despondency.However, the social insurance data of Egypt are extremely massive, diverse and complex, due to the intricate provisions in Egyptian laws on social insurance.This calls for an effective method to distinguish between the insured and the uninsured based on the big data.Therefore, this paper fully demonstrates the capability of supervised learning algorithms in predicting the insured and the uninsured based on some of the data on social insurance.The big dataset of Egyptian social insurance was preprocessed in details, including replacing the missing values with mean values, normalization, and removal of outliers and extreme values.Next, three supervised learning algorithms, namely, Naive Bayes, Decision Tree Algorithm, and CN2 Rule Induction, were applied to classify the Egyptians based on the preprocessed data.The results show that all three algorithms achieved highly accuracy classification results.The research provides a new way to mine useful information from the big data of social insurance.