Forecasting of Inflation Rate Contingent on Consumer Price Index

Abstract

Variations of inflation rate possess a diverse influence on the economic growth of any country. Inflation rate control can be accommodated to stabilize the financial aspect’s condition, including the political area. The way to restrain the inflation rate is the prediction of the inflation rate. This paper proposes forecasting the inflation rate by applying machine learning algorithms: support vector regression (SVR), random forest regressor (RFR), decision tree, AdaBoosting, gradient boosting, and XGBoost. These algorithms are employed since the predicting value is nonlinear and complex. Moreover, the regression and boosting algorithms confer good accuracy, as inflation is a frequent dynamic variable that depends on several factors. The models show decent accuracy using the elements consumer price index (CPI), food, non-food, clothing-footwear, and transportation. Among the models, AdaBoost retrospectives the most desirable outcome with the lowest MSE value of 0.041.