Predicting Used Car Prices with Heuristic Algorithms and Creating a New Dataset
Article Sidebar
Published
Jul 29, 2021
Main Article Content
Abstract
Turkey is one of the countries with a high-volume second-hand car market.. Today, used car sales advertisements given over the internet have accelerated this market even more. This situation has caused difficulties in determining the most suitable price for the vehicle to be bought or sold. The problem of determining the price of second-hand vehicles causes both buyers and sellers to have difficulties since it contains many variables. In this study, it is aimed to determine the best prediction model by using heuristic algorithms for the solution of this problem. In this direction, a new dataset including car features and price information was created by compiling the advertisements on the sites that provide car buying and selling advertisement services over the internet, and this dataset was shared for researchers to use in the model development phase. As a result of the estimation processes made with different algorithms and models on the dataset, it was seen that the Fisher+ANN model provided the lowest estimation error with MAE 0.01050, MSE 0.000281 and the highest performance value observed with R2 was 0.8958.
Article Details
How to Cite
BILEN, Mehmet.
Predicting Used Car Prices with Heuristic Algorithms and Creating a New Dataset.
Journal of Multidisciplinary Developments, [S.l.], v. 6, n. 1, p. 29-43, july 2021.
ISSN 2564-6095.
Available at: <http://www.jomude.com/index.php/jomude/article/view/91>. Date accessed: 18 mar. 2025.
Section
Natural Sciences - Regular Research Paper
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
[1] Lessman, S., & Vob, S. (2017). Car resale price forecasting: The impact of regression method, private information, and heterogeneity on forecast accuracy. International Journal of Forecasting, 33(4), 864-877.
[2] Due, J., Xie, L., & Schroeder, S. (2009). PIN optimal distribution of auction vehicle system: Applying price forecasting, elasticity estimation and genetic algorithms to used vehicle distribution. Marketing Science, 28, 637-644.
[3] Lessmann, S., Kistiani, M., & Vob, S. (2010). Decision support in car leasing: a forecasting model for residual value estimation. Proceedings of the international conference on information systems, (s. 17). Saint Louis.
[4] Murray, J., & Sarantis, N. (1999). Price-quality relations and hedonic price indexes for cars in the United Kingdom. International Journal of the Economics of Business, 6(21), 5-27.
[5] Dastan, H. (2016). Türkiye’de İkinci El Otomobil Fiyatlarını Etkileyen Faktörlerin Hedonik Fiyat Modeli ile Belirlenmesi. Gazi Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 18(1), 303-327.
[6] Cumhur, E., & Şentürk, İ. (2009). A Hedonic Analysis of Used Car Prices in Turkey. International Journal of Economic Perspectives, 3(2), 141-149.
[7] Çelik, Ö., & Osmanoğlu, U. Ö. (2019). Prediction of The Prices of Second-Hand Cars. Avrupa Bilim ve Teknoloji Dergisi, 16, 77-83.
[8] Özçalıcı, M. (2017). Predicting Second-Hand Car Sales Price Using Decision Trees and Genetic Algorithms. The Journal of Operations Research, Statistics, Econometrics and Management Information Systems, 5(1), 103-114.
[9] Noor, K., & Jan, S. (2017). Vehicle price prediction system using machine learning techniques. International Journal of Computer Applications, 167(9), 27-31.
[10] Pal, N., Arora, P., Kohli, P., Sundararaman, D., & Palakurthy, S. S. (2018). How Much Is My Car Worth? A Methodology for Predicting Used Cars’ Prices Using Random Forest. In Future of Information and Communication Conference, (s. 413-422). Cham.
[11] Demissie, S., LaValley, M. P., & Horton, N. J. (2003). Bias due to missing exposure data using complete-case analysis in the proportional hazards regression model. Stat Med, 22, 545-547.
[12] UCI Irvine, Machine Learning Repository, https://archive-beta.ics.uci.edu/ml/datasets
[13] Jain, S., Shukla, S., & Wadhvani, R. (106). Dynamic selection of normalization techniques using data complexity measures. Expert Systems with Applications, 106, 252-262.
[14] Çevik, H. (2004). Türkiyenin kısa dönem elektrik yük tahmini. İstanbul Teknik Üniversitesi Fen Bilimleri Enstitüsü, Yüksek Lisans Tezi, 5-31.
[15] Balcı, H., Esener, İ., & Kurban, M. (2012). Regresyon analizi kullanarak kısa dönem yük tahmini. Eleco Elektrik-Elektronik ve Bilgisayar Mühendisliği Sempozyumu, (s. 796-797). Bursa.
[16] Tekin, H. (2019). Yeni bir metot olan geri beslemeli lineer regresyon ile akıllı şebekeye bağlı meskenlerde kısa dönem yük tahmini. Batman Üniversitesi Fen Bilimleri Enstitüsü, 53.
[17] Cortes, C., & Vapnik, V. N. (1995). Support-Vector Networks. Machine Learning, 20(3), 273-297.
[18] Blanton, H. (1997). An Introduction to Neural Networks for Technicians, Engineers and Other non PhDs. Proceedings of 1997 Artificial Neural Networks in Engineering Conference. St. Louis.
[19] McCulloch, W. S., & Pitts, A. (1943). A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematics and Biophysics, 5, 115-133.
[20] Xiong, M., Fang, X., & Zhao, J. (2001). Biomarker identification by feature wrappers. Genome Res, 11(11), 1878-1887.
[21] Adiwijaya, Wisesty, U. N., Lisnawati, E., Aditsania, A., & Kusumo, D. S. (2018). Dimensionality Reduction using Principal Component Analysis for Cancer Detection Based on Microarray Data Classification. Journal of Computer Science, 14(11), 1521-1530.
[2] Due, J., Xie, L., & Schroeder, S. (2009). PIN optimal distribution of auction vehicle system: Applying price forecasting, elasticity estimation and genetic algorithms to used vehicle distribution. Marketing Science, 28, 637-644.
[3] Lessmann, S., Kistiani, M., & Vob, S. (2010). Decision support in car leasing: a forecasting model for residual value estimation. Proceedings of the international conference on information systems, (s. 17). Saint Louis.
[4] Murray, J., & Sarantis, N. (1999). Price-quality relations and hedonic price indexes for cars in the United Kingdom. International Journal of the Economics of Business, 6(21), 5-27.
[5] Dastan, H. (2016). Türkiye’de İkinci El Otomobil Fiyatlarını Etkileyen Faktörlerin Hedonik Fiyat Modeli ile Belirlenmesi. Gazi Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 18(1), 303-327.
[6] Cumhur, E., & Şentürk, İ. (2009). A Hedonic Analysis of Used Car Prices in Turkey. International Journal of Economic Perspectives, 3(2), 141-149.
[7] Çelik, Ö., & Osmanoğlu, U. Ö. (2019). Prediction of The Prices of Second-Hand Cars. Avrupa Bilim ve Teknoloji Dergisi, 16, 77-83.
[8] Özçalıcı, M. (2017). Predicting Second-Hand Car Sales Price Using Decision Trees and Genetic Algorithms. The Journal of Operations Research, Statistics, Econometrics and Management Information Systems, 5(1), 103-114.
[9] Noor, K., & Jan, S. (2017). Vehicle price prediction system using machine learning techniques. International Journal of Computer Applications, 167(9), 27-31.
[10] Pal, N., Arora, P., Kohli, P., Sundararaman, D., & Palakurthy, S. S. (2018). How Much Is My Car Worth? A Methodology for Predicting Used Cars’ Prices Using Random Forest. In Future of Information and Communication Conference, (s. 413-422). Cham.
[11] Demissie, S., LaValley, M. P., & Horton, N. J. (2003). Bias due to missing exposure data using complete-case analysis in the proportional hazards regression model. Stat Med, 22, 545-547.
[12] UCI Irvine, Machine Learning Repository, https://archive-beta.ics.uci.edu/ml/datasets
[13] Jain, S., Shukla, S., & Wadhvani, R. (106). Dynamic selection of normalization techniques using data complexity measures. Expert Systems with Applications, 106, 252-262.
[14] Çevik, H. (2004). Türkiyenin kısa dönem elektrik yük tahmini. İstanbul Teknik Üniversitesi Fen Bilimleri Enstitüsü, Yüksek Lisans Tezi, 5-31.
[15] Balcı, H., Esener, İ., & Kurban, M. (2012). Regresyon analizi kullanarak kısa dönem yük tahmini. Eleco Elektrik-Elektronik ve Bilgisayar Mühendisliği Sempozyumu, (s. 796-797). Bursa.
[16] Tekin, H. (2019). Yeni bir metot olan geri beslemeli lineer regresyon ile akıllı şebekeye bağlı meskenlerde kısa dönem yük tahmini. Batman Üniversitesi Fen Bilimleri Enstitüsü, 53.
[17] Cortes, C., & Vapnik, V. N. (1995). Support-Vector Networks. Machine Learning, 20(3), 273-297.
[18] Blanton, H. (1997). An Introduction to Neural Networks for Technicians, Engineers and Other non PhDs. Proceedings of 1997 Artificial Neural Networks in Engineering Conference. St. Louis.
[19] McCulloch, W. S., & Pitts, A. (1943). A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematics and Biophysics, 5, 115-133.
[20] Xiong, M., Fang, X., & Zhao, J. (2001). Biomarker identification by feature wrappers. Genome Res, 11(11), 1878-1887.
[21] Adiwijaya, Wisesty, U. N., Lisnawati, E., Aditsania, A., & Kusumo, D. S. (2018). Dimensionality Reduction using Principal Component Analysis for Cancer Detection Based on Microarray Data Classification. Journal of Computer Science, 14(11), 1521-1530.