Analysis Factors Affecting Egyptian Inflation Based on Machine Learning Algorithms

Abstract

Given that inflation is one of the most important problems facing the Egyptian economy, determining the factors affecting it is very important. Thus, we aim to use machine learning algorithms like Support vector machine (SVM), K-nearest neighbor (KNN), Random Forest (R.F.), Neural Network (ANN), Gradient boosting (G.B.) and decision tree (D.T.) to determine the accurate algorithm and analyze the factors affecting on Egypt inflation. The study found that the G.B. algorithm is the most accurate among the used algorithms and showed that The major significant variables determining inflation in Egypt are the exchange rate (30.5%), gross fixed formation (24.5%) and government expenditure (12.3%). We also found a positive relationship between the inflation rate and government expenditure, money supply, gross domestic product (GDP) growth, gross fixed formation, foreign direct investment, GDP per capita and exchange rate. Furthermore, there is a negative relationship between the inflation rate, household expenditure and the external trade balance.

Keywords

• inflation rate forecasting
• mmachine learning
• nneural network
• gradient boosting
• decision tree