Estimation Of Car Ownership In Turkey Using Artificial Bee Colony Algorithm

Abstract

This study proposes Artificial Bee Colony (ABC) models to estimate the number of cars in Turkey. In other words, car ownership is defined the number of cars per 1000 people. In the models development, population (P), per capita Gross Domestic Product (GDP) as dollars and fuel prices as Petrol, Diesel and Lpg were selected as model parameters. Two different ABC models were developed using the data covering from 2004 to 2015. According to fuel type, the coefficients of models were determined for each fuel type. Therefore, the sum of number of cars for each fuel type presented car ownership in Turkey. Developed models' results were statistically compared to observed values in terms of root mean square errors (RMSE), mean absolute percentage errors (MAPE) and coefficient of determination (R-2). The results of the ABC models showed that they were suitable to estimate the number of cars. To investigate the performance of ABC models for future estimations, a ten-year period from 2016 to 2025 was considered. Thus, future values of population were obtained from the projection of Turkish Statistical Institute (TSI) and the projections of other parameters, per capita GDP and fuel price, were executed according to current growth curve. The results obtained from future estimations reveal the suitability of ABC approach for determination of car ownership.