An ANFIS Based Vehicle Sales Forecasting Model Utilizing Feature Clustering and Genetic Algorithms

  • Atınç Yılmaz Beykent University
  • Umut Kaya Beykent University
  • Ediz Şaykol Beykent University
Keywords: Adaptive Neuro Fuzzy Inference System (ANFIS), Feature Clustering, Genetic Algorithms, Vehicle Sales Prediction

Abstract

The automotive sector is one of Turkey’s most important industries, and the developments in technology are affecting the automotive sector as well as the other sectors. The methods that have been used to date indicate that the use of AI should be increased when the demand forecasting applications take into account the developments in the industry. For this purpose, by using the data taken from the Automotive Distributors Association and Turkish Statistical Institute Internet pages, intuitive learning hybrid ANFIS method is used to forecast the sales in this study. A clustering scheme is first applied to group the features, and then the features are fed into genetic algorithms to improve the prediction model performance. The experiments show that the prediction performance of the proposed method is good when compared to existing related studies in the literature.

Published
2020-01-17
How to Cite
[1]
A. Yılmaz, U. Kaya, and E. Şaykol, “An ANFIS Based Vehicle Sales Forecasting Model Utilizing Feature Clustering and Genetic Algorithms”, JAST, vol. 13, no. 1, pp. 139-154, Jan. 2020.
Section
Articles