Afsaneh Kazemi Mehrabadi; Vahid Taghinezhad Omran; Mohammad Valipour Khatir; Saeed Rasekhi
Abstract
Forecasting industrial production is essential for efficient planning by managers. Although there are many statistical and mathematical methods for prediction, the use of intelligent algorithms with desirable features has made significant progress in recent years. The current study compared the accuracy ...
Read More
Forecasting industrial production is essential for efficient planning by managers. Although there are many statistical and mathematical methods for prediction, the use of intelligent algorithms with desirable features has made significant progress in recent years. The current study compared the accuracy of the Artificial Neural Networks (ANN) and Adaptive Nero-Fuzzy Inference System (ANFIS) approaches to assess the current state and predict the future state of industrial production. The seasonal dataset comprised the labor force, capital stock, human capital, trade openness, liquidity and credit financing to the industrial sector as input variables and value added of industrial production as the output variable for the period of 1988 to 2018. The dataset was used to forecast industrial production for Seasons of the year 2019 and 2020. The results showed that, while both are appropriate tools for forecasting industrial production, ANFIS had a lower the Mean Squared Error (MSE) and Mean Absolute Percentage Error (MAPE) than ANN. The findings of the research indicate that ANFIS is more effective in forecasting industrial production, which can help policymakers in planning and creating an effective strategy for the future.