Regression Based Price Prediction of Staple Food Materials Using Multivariate Models

Abstract

Profit margins for essential foodstuffs could be a demand rising problem. There are several variables influencing currency fluctuations. For example, the various variables of commodity food prices are climate, crude prices, and so on. Forecasting the fluctuating prices of basic foodstuffs is also relevant even for the government, producers, and customers. The article will use ARCH (autoregressive conditional heteroskedasticity) to forecast the essential food market considering external conditions. The findings agree well enough with the assessment price in the industry by employing two main approaches, ARCH and GARCH (generalized autoregressive conditional heteroskedasticity). For jalapeno, the best result (96.87%) in estimating the cost of employing ARCH is achieved. In the meantime, the best result (99.94%) for the basic food tomato is observed using GARCH. Proportionally, the ARCH is stronger than GARCH, since GARCH is very consistent without disrupting current information.