Car Price Prediction Using an Artificial Neural Network

Year 2020, Volume: 6 Issue: 2, 44 - 48, 16.12.2020

Mehmet Mehdi Karakoç , Gaffari Çelik , Asaf Varol

Abstract

When buying and selling cars, it can be a challenge to assign the correct price. Artificial neural networks, a branch of artificial intelligence, are frequently used for such calculations. In this study we designed two different artificial neural networks for car price forecasting and tested them using data from a car sales website. For data, a software was developed using the C# programming language and the MSSQL Server database management system, also HTMLAgilityPack library was used to read the data on the website. A procedure was written with T-SQL language to digitize the data. As a result of the study, using data from approximately 1000 cars, a success rate of 91.38% was obtained. More data is needed for better results.

Keywords

Artificial Neural Networks, Artificial Intelligence, Car Price Prediction

References

• Talu M. F. and Tatar Y.; An Edge detection Method for Using Model based Artificial Neural Network (In Turkish). Journal of Turkey Informatics and Computer Science Foundation. 1(1), 74-80, (2005)
• Laxmi V. and Rohil H.: License Plate Recognition System using Back Propagation Neural Network. International Journal of Computer Applications, 99 (8), 29-37, (2014)
• Han M.-W. and Kopacck, P.: Optimization Using Artificial Neural Networks. IFAC Proceedings Volumes. 28 (24), 357-360, (1995)
• Thati A., Biswas A., and Chowdhury S. R.: Breath acetone-based non-invasive detection of blood glucose levels. International Journal on Smart Sensing and Intelligent Systems, 2 (8), 1244-1260, (2015)
• Deperlioğlu Ö. and Köse, U.: An educational tool for artificial neural networks. Computers & Electrical Engineering. 37 (3), 392-402, (2011)
• Elmas Ç.: Artificial Neural Network – theory, architecture, training, implementation (In Turkish), Ankara, Turkey: Seçkin Press, (2003)
• Karcı A. and Demir M.: Estimation of protein structures by classification of angles between a carbons of amino acids based on artificial neural Networks. Expert Systems with Applications, 36 (1), 5541-5548, (2009)
• Google Trends: https://trends.google.com /trends/explore?q=Arabam.com,Sahibinden.com, Araba.com, arabam.com, tasit.com&geo=TR. (2018). Accessed 12 November 2018
• Bala R. and Kumar D.: Classification Using ANN: A Review. International Journal of Computational Intelligence Research. 13 (7), 1811-1820, (2017)