Transportation Sector in Turkey: Future Expectations About Railway Transportation of Turkey

Sevüktekin, Mustafa; Keser, Hilal Yıldırır; Ay, Sema; Çetin, Işın

doi:10.18025/kauiibf.58857

Cited by 1 publication

(1 citation statement)

References 3 publications

(3 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tsai, Mulley, and Clifton (2013) employed a univariate model (Autoregressive Integrated Moving Average (ARIMA)) and a multivariate direct demand model (partial adjustment model) to forecast public transport demand. Sevuktekin et al (2014) used the statistical models including ARIMA, single exponential smoothing and linear trend models to analyze the development in transportation sector in Turkey. Li and Li (2018) employed the random forest algorithm, time series-random forest algorithm, and autoregressive moving average-random forest algorithm to forecast ticket prices.…”

Section: Introductionmentioning

confidence: 99%

Assesment of Ticket Price Forecasting in Turkey

Dosdoğru

Ipek²,

Göçken³

et al. 2022

Çukurova Üniversitesi Sosyal Bilimler Enstitüsü Dergisi

View full text Add to dashboard Cite

Fast, reliable, and comfortable transportation of people increase the level of livability in cities. It also influences people's quality of life. Therefore, research is needed to improve transportation services. Various models are developed to analyze the transportation services but each of them has its own advantages and disadvantages. Today, companies collect large amounts of data to improve their service quality. To survive in a competition environment, they must use the collected data to create value for their customers and employees. Many factors affect the transportation services. Therefore, it is difficult to solve the problems in transportation services using classical methods. The main goal of our study is to determine the bus ticket price accurately. In this study, the k-means algorithm, which is popular because of its simplicity and versatility, is firstly used to discover information that is more meaningful. Then the bus ticket price, which is one of the most important elements of passenger transportation, is forecasted using six different forecasting models including linear regression, support vector regression, regression tree, gaussian process regression, genetic algorithm based artificial neural network, and an ensemble model. The results of this study showed that proposed forecasting models can meet expectations in dynamic environmental conditions.

show abstract

Section: Introductionmentioning

confidence: 99%