|About This Journal||Editorial Board||For Contributors||Journal Archive|
You are not permitted to access the full text of articles.
If you have any questions about permissions,
please contact the Society.
회원님은 논문 이용 권한이 없습니다.
권한 관련 문의는 학회로 부탁 드립니다.
|[ Article ]|
|korean management review - Vol. 50, No. 2, pp.357-381|
|ISSN: 1226-1874 (Print)|
|Print publication date 30 Apr 2021|
|Received 28 Jul 2020 Revised 15 Nov 2020 Accepted 09 Dec 2020|
|Art Price Prediction Using Decision Tree-Based Machine Learning Methods|
Dongryul Jang ; Minjae Park
|(First Author) Department of Culture and Arts Management, Graduate School, Hongik University (firstname.lastname@example.org)|
|(Corresponding Author) College of Business Administration, Hongik University (email@example.com)|
결정 트리 기반 학습 모형을 이용한 미술품 경매 가격 예측
Copyright 2011 THE KOREAN ACADEMIC SOCIETY OF BUSINESS ADMINISTRATION
This is an open access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted, distribution, and reproduction in any medium, provided the original work is properly cited.
Funding Information ▼
Recently, many researchers not only from industry but also from academia have interested in the art finance market. Although many people have studied growing art finance market, very few studies on the prediction model to evaluate the art price have been conducted. Therefore, in this study we have gathered a database of 12,105 paintings auctioned between 2009 and 2018 and have implemented decision tree-based machine learning algorithms (e.g., random forests, gradient boosting, XGboost) to develop prediction models for art prices and to improve the reliability for art experts’ estimates accurately. We have compared the prediction accuracy of the proposed approach based on root mean square error and mean absolute error. As a result of the analysis, we noticed that experts’ estimates from auction houses are more accurate only for high-priced artworks but overestimates low-priced artworks. On the other hand, the suggested prediction model’s accuracy considering decision tree-based model is better than the accuracy based on the parametric OLS model. Finally, we test the accuracy of prediction models considering expert evaluation to enhance the models’ predictive power. These results show that an integrated approach between expert appraisal systems and statistical models improves the prediction accuracy for artworks’ price.
|Keywords: art price, decision tree, extreme gradient boosting, gradient boosting, random forests
Minjae Park’s work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT) (NRF-2020R1F1A104823711).
A previous version of this paper won a third prize at the “18th Thesis Competition“ hosted by Statistics Korea.
|1.||Anderson, R. C.(1974), “Paintings as an Investment,” Economic Inquiry, 12(1), pp.13-26
|2.||Artsy (2019), “The Online Art Collector Report 2019.”|
|3.||Ashenfelter, O., K. Graddy, and M. Stevens. (2002), “A Study of Sale Rates and Prices in Impressionist and Contemporary Art Auctions,” Princeton University and University of Oxford.|
|4.||Aubry, M., R. Kraeussl, G. Manso, and C. Spaenjers. (2019), “Machines and Masterpieces: Predicting Prices in the Art Auction Market,” SSRN,
|5.||Ayub, R., C. Orban, and V. Mukund. (2017), “Art Appraisal using Convolutional Neural Networks.”|
|6.||Bailey, J.(2020), “Can Machine Learning Predict the Price of Art at Auction?” Harvard Data Science Review, 2(2).|
|7.||Bauwens, L. and V. Ginsburgh.(2000), “Art Experts and Auctions: Are Pre-Sale Estimates Unbiased and Fully Informative?” Recherches Economiques De Louvain/Louvain Economic Review, 66(2), pp.131-144.|
|8.||Beggs, A. and K. Graddy.(1997), “Declining Values and the Afternoon Effect: Evidence from Art Auctions,” The Rand Journal of Economics, 28(3), pp.544-565.
|9.||Beggs, A. and K. Graddy.(2009), “Anchoring Effects: Evidence from Art Auctions,” American Economic Review, 99(3), pp.1027-1039.
|10.||Breiman, L.(1996), “Bagging Predictors,” Machine Learning, 24(2), pp.123-140.
|11.||Breiman, L.(2001), “Random Forests,” Machine Learning, 45(1), pp.5-32.
|12.||Chen, T. and C. Guestrin.(2016), “Xgboost: A Scalable Tree Boosting System,” Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp.785-794.
|13.||Choudhry, R. and K. Garg.(2008), “A Hybrid Machine Learning System for Stock Market Forecasting,” World Academy of Science, Engineering and Technology, 39(3), pp.315-318.|
|14.||Fedderke, J. W. and K. Li.(2020), “Art in Africa: Hedonic Price Analysis of the South African Fine Art Auction Market, 2009-2014,” Economic Modelling, 84, pp.88-101.
|15.||Friedman, J. H.(2001), “Greedy Function Approximation: A Gradient Boosting Machine,” Annals of Statistics, 29(5), pp.1189-1232.
|16.||Garay, U.(2021), “Determinants of Art Prices and Performance by Movements: Long-Run Evidence from an Emerging Market,” Journal of Business Research. 127, pp.413-426
|17.||Grömping, U.(2009), “Variable Importance Assessment in Regression: Linear Regression Versus Random Forest,” The American Statistician, 63(4), pp.308-319.
|18.||Higgs, H. and A. Worthington.(2005), “Financial Returns and Price Determinants in the Australian Art Market, 1973-2003,” Economic Record, 81(253), pp.113-123.
|19.||Huh, B. G. and Y. K. Jung.(2013), “The Effects of Data Mining Ensemble Techniques on Audit Risk Reduction,” Korean Management Review, 42(5), pp.1523-1559.|
|20.||James, G., D. Witten, T. Hastie, and R. Tibshirani. (2013), “An Introduction to Statistical Learning,” Vol. 112, Springer.
|21.||Jang, D. R. and M. J. Park.(2019), “Price Determinant Factors of Artworks and Prediction Model Based on Machine Learning,” Journal of Korean Society for Quality Management , 47(4), pp.687-700.|
|22.||Jang, D. R. and M. J. Park.(2020a), “A Study on the Art Price Prediction Model using the Random Forest,” Journal of Applied Reliability, 20(1), pp.34-42.
|23.||Jang, D. R. and M. J. Park.(2020b), “Financial Returns and Price Determinants of Art: A Hedonic Quantile Regression Approach,” Journal of Applied Reliability, 20(2), pp. 133-144.
|24.||Kim, T. H., M. S. Kim, H. D. Shin, and Y. S. Kim. (2016), “Study on the Art Price Index Including Non-Auction Market in Korea,” The Journal of Cultural Policy, 30(1), pp.32-54.
|25.||Korea Arts Management Service(2019), “Survey on the Art Market.”|
|26.||Lee, C. R. and K. H. Park.(2016), “Application of Machine Learning Models for Estimating House Price,” Journal of the Korean Geographical Society, 51(2), pp.219-233.|
|27.||Lee, D. K.(2019), “Study on Art Authentication and Appraisal Policy in Visual Arts Administration,” Journal of Governance Studies, 14(1), pp.83-103.|
|28.||McAndrew, Clare(2019), The Art Basel and UBS Global Art Market ReportArt Basel and UBS, Art Basel and UBS|
|29.||McAndrew, C. and R. Thompson.(2007), “The Collateral Value of Fine Art,” Journal of Banking & Finance , 31(3), pp.589-607.
|30.||Mei, J. and M. Moses.(2005a), “Beautiful Asset: Art as Investment,” Journal of Investment Consulting , 7(2), pp.45-51.|
|31.||Mei, J. and M. Moses.(2005b), “Vested Interest and Biased Price Estimates: Evidence from an Auction Market,” The Journal of Finance, 60(5), pp.2409-2435.
|32.||Ministry of Culture, Sports and Tourism, (2018), “Mid & Long Term Plan for Promotion of Visual Arts.”|
|33.||Nahm, J. W.(2011), “Price Determinants and Financial Returns in Korean Art Investment,” The Korean Journal of Economic Studies, 59(1), pp.5-24.|
|34.||Park, B. H. and J. K. Bae.(2015), “Using Machine Learning Algorithms for Housing Price Prediction: The Case of Fairfax County, Virginia Housing Data,” Expert Systems with Applications, 42(6), pp.2928-2934.
|35.||Park, J. H. and H. D. Shin.(2012), “Would Online Artwork Auction be Better than Offline? Focusing on the Impacts of Price Determinants on the Fetching Price,” Korean Management Review, 41(4), pp.789-808.|
|36.||Patel, J., S. Shah, P. Thakkar, and K. Kotecha. (2015), “Predicting Stock and Stock Price Index Movement using Trend Deterministic Data Preparation and Machine Learning Techniques,” Expert Systems with Applications, 42(1), pp.259-268.
|37.||Shen, S., H. Jiang, and T. Zhang.(2012), “Stock Market Forecasting using Machine Learning Algorithms,” Department of Electrical Engineering, Stanford University, Stanford, CA pp.1-5.|
|38.||Sproule, R. and C. Valsan.(2006), “Hedonic Models and Pre-Auction Estimates: Abstract Art Revisited,” Economics Bulletin, 26(5), pp. 1-10.|
|39.||Taylor, D. and L. Coleman.(2011), “Price Determinants of Aboriginal Art, and its Role as an Alternative Asset Class,” Journal of Banking & Finance, 35(6), pp.1519-1529.
|40.||Worthington, A. C. and H. Higgs.(2006), “A Note on Financial Risk, Return and Asset Pricing in Australian Modern and Contemporary Art,” Journal of Cultural Economics, 30(1), pp.73-84.
|41.||Yu, L., W. Dai, and L. Tang.(2016), “A Novel Decomposition Ensemble Model with Extended Extreme Learning Machine for Crude Oil Price Forecasting,” Engineering Applications of Artificial Intelligence, 47, pp.110-121.
∙The author Dongryul Jang graduated from Hongik University with a master's degree in Arts and Cultural Management. His main interests are machine learning, big data modeling, and cultural industry. His paper related was selected as outstanding paper award in 'the 18th Statistics Korea Research Competition’.
∙The author Minjae Park is currently an associate professor at Business School, Hongik University, Seoul, Korea. His research interests include quality management, reliability modeling, maintenance policy, mean shift detection, optimization, and applied statistics.