Stacked Generalization with Sequential-Model Based Optimization for estimating Used Car Valuation in Indonesia
Received: 26 June 2024 | Revised: 9 August 2024 | Accepted: 24 August 2024 | Online: 9 October 2024
Corresponding author: Isti Surjandari
Abstract
In Indonesia, the purchase and sale of used vehicles is a common practice. The valuation of a used vehicle is influenced by several factors, making it challenging to determine an appropriate selling price. To address this issue, this study employs a stacked generalization (stacking) algorithm to integrate Machine Learning (ML) techniques that have demonstrated efficacy in prior research on used car valuations. The Sequential Model-Based Optimization (SMBO) algorithm is employed to achieve high accuracy while ensuring an efficient hyperparameter optimization process. The initial price of a vehicle is undoubtedly a significant determinant of its resale value. However, this fact is frequently overlooked in previous studies on developing car price estimation models. This study makes a contribution to the field by addressing this issue. The use of the initial price as an input for the model enables two distinct types of analysis: one for the assessment of used car prices and the other for the measurement of the degree of residual valuation of used cars in relation to their initial costs. The results demonstrated that the optimized stacking model exhibited superior predictive ability compared to the other algorithms in both analyses. Feature analysis substantiated the considerable influence of the initial price on the used car's price. This study also corroborates the assertion that accurately predicting the valuation of a used car cannot be achieved by solely considering the usage of the previous owner, such as the car's age and mileage. It is crucial to take into account the car's original attributes, particularly its initial price.
Keywords:
used car valuation, residual value, stacked generalization, sequential model-based optimization, feature analysisDownloads
References
A. Jawed, M. A. H. Talpur, I. A. Chandio, and P. N. Mahesar, "Impacts of In-Accessible and Poor Public Transportation System on Urban Enviroment: Evidence from Hyderabad, Pakistan," Engineering, Technology & Applied Science Research, vol. 9, no. 2, pp. 3896–3899, Apr. 2019. DOI: https://doi.org/10.48084/etasr.2482
M. A. H. Talpur, M. Napiah, I. A. Chandio, T. A. Qureshi, and S. H. Khahro, "Development of a Regional Transport Policy Support System for Rural Planning Agencies in Developing World," Procedia Engineering, vol. 77, pp. 2–10, Jan. 2014. DOI: https://doi.org/10.1016/j.proeng.2014.07.003
Number of Motor Vehicle by Type - Statistical Data. Indonesia: BPS-Statistics, 2018.
Indonesian Automobile Industry Data. Indonesia: GAIKINDO.
D. J. Bayu, Konsumen Lebih Pilih Beli Mobil Bekas Usai Pandemi. Indonesia: Katadata, Nov. 19, 2020.
F. R. Amik, A. Lanard, A. Ismat, and S. Momen, "Application of Machine Learning Techniques to Predict the Price of Pre-Owned Cars in Bangladesh," Information, vol. 12, no. 12, Dec. 2021, Art. no. 514. DOI: https://doi.org/10.3390/info12120514
E. Liu, J. Li, A. Zheng, H. Liu, and T. Jiang, "Research on the Prediction Model of the Used Car Price in View of the PSO-GRA-BP Neural Network," Sustainability, vol. 14, no. 15, Jan. 2022, Art. no. 8993. DOI: https://doi.org/10.3390/su14158993
C. Chen, L. Hao, and C. Xu, "Comparative analysis of used car price evaluation models," AIP Conference Proceedings, vol. 1839, no. 1, May 2017, Art. no. 020165. DOI: https://doi.org/10.1063/1.4982530
J.-D. Wu, C.-C. Hsu, and H.-C. Chen, "An expert system of price forecasting for used cars using adaptive neuro-fuzzy inference," Expert Systems with Applications, vol. 36, no. 4, pp. 7809–7817, May 2009. DOI: https://doi.org/10.1016/j.eswa.2008.11.019
A. Wang, Q. Yu, X. Li, Z. Lu, X. Yu, and Z. Wang, "Research on Used Car Valuation Problem Based on Machine Learning," in 2022 International Conference on Computer Network, Electronic and Automation (ICCNEA), Xi’an, China, Sep. 2022, pp. 101–106. DOI: https://doi.org/10.1109/ICCNEA57056.2022.00032
S. Lessmann and S. Voß, "Car resale price forecasting: The impact of regression method, private information, and heterogeneity on forecast accuracy," International Journal of Forecasting, vol. 33, no. 4, pp. 864–877, Oct. 2017. DOI: https://doi.org/10.1016/j.ijforecast.2017.04.003
E. Gegic, B. Isakovic, D. Keco, Z. Masetic, and J. Kevric, "Car Price Prediction using Machine Learning Techniques," TEM Journal, vol. 8, no. 1, pp. 113–118, Feb. 2019. DOI: https://doi.org/10.18421/TEM81-16
N. Pal, P. Arora, P. Kohli, D. Sundararaman, and S. S. Palakurthy, "How Much Is My Car Worth? A Methodology for Predicting Used Cars’ Prices Using Random Forest," in Advances in Information and Communication Networks, Cham, Switzerland: Springer, 2019, pp. 413–422. DOI: https://doi.org/10.1007/978-3-030-03402-3_28
P. Cerda and G. Varoquaux, "Encoding high-cardinality string categorical variables," IEEE Transactions on Knowledge and Data Engineering, vol. 34, no. 3, pp. 1164–1176, Mar. 2022. DOI: https://doi.org/10.1109/TKDE.2020.2992529
K. J. Liapis and D. D. Kantianis, "Depreciation Methods and Life-cycle Costing (LCC) Methodology," Procedia Economics and Finance, vol. 19, pp. 314–324, Jan. 2015. DOI: https://doi.org/10.1016/S2212-5671(15)00032-5
F. Pargent, F. Pfisterer, J. Thomas, and B. Bischl, "Regularized target encoding outperforms traditional methods in supervised machine learning with high cardinality features," Computational Statistics, vol. 37, no. 5, pp. 2671–2692, Nov. 2022. DOI: https://doi.org/10.1007/s00180-022-01207-6
N. Zhang, Y. Su, B. Wu, X. Tu, Y. Jin, and X. Bao, "Cloud resource prediction model based on LSTM and RBF," in 2021 2nd International Conference on Big Data & Artificial Intelligence & Software Engineering (ICBASE), Zhuhai, China, Sep. 2021, pp. 189–194. DOI: https://doi.org/10.1109/ICBASE53849.2021.00043
A. A. Alhashmi, A. M. Alashjaee, A. A. Darem, A. F. Alanazi, and R. Effghi, "An Ensemble-based Fraud Detection Model for Financial Transaction Cyber Threat Classification and Countermeasures," Engineering, Technology & Applied Science Research, vol. 13, no. 6, pp. 12433–12439, Dec. 2023. DOI: https://doi.org/10.48084/etasr.6401
M. Wistuba, N. Schilling, and L. Schmidt-Thieme, "Hyperparameter Search Space Pruning – A New Component for Sequential Model-Based Hyperparameter Optimization," in Machine Learning and Knowledge Discovery in Databases, Cham, Switzerland: Springer, 2015, pp. 104–119. DOI: https://doi.org/10.1007/978-3-319-23525-7_7
M. Massaoudi, S. S. Refaat, I. Chihi, M. Trabelsi, F. S. Oueslati, and H. Abu-Rub, "A novel stacked generalization ensemble-based hybrid LGBM-XGB-MLP model for Short-Term Load Forecasting," Energy, vol. 214, Jan. 2021, Art. no. 118874. DOI: https://doi.org/10.1016/j.energy.2020.118874
A. H. Alkenani, Y. Li, Y. Xu, and Q. Zhang, "Predicting Alzheimer’s Disease from Spoken and Written Language Using Fusion-Based Stacked Generalization," Journal of Biomedical Informatics, vol. 118, Jun. 2021, Art. no. 103803. DOI: https://doi.org/10.1016/j.jbi.2021.103803
Y. A. Alsariera, M. H. Alanazi, Y. Said, and F. Allan, "An Investigation of AI-Based Ensemble Methods for the Detection of Phishing Attacks," Engineering, Technology & Applied Science Research, vol. 14, no. 3, pp. 14266–14274, Jun. 2024. DOI: https://doi.org/10.48084/etasr.7267
Z.-H. Zhou, Ensemble Methods: Foundations and Algorithms, 1st ed. Boca Raton, FL, USA: Chapman & Hall/CRC, 2012.
A. C. Faul, A Concise Introduction to Machine Learning, 1st ed. Boca Raton, FL, USA: Chapman and Hall/CRC, 2019.
A. Callens, D. Morichon, S. Abadie, M. Delpey, and B. Liquet, "Using Random forest and Gradient boosting trees to improve wave forecast at a specific location," Applied Ocean Research, vol. 104, Nov. 2020, Art. no. 102339. DOI: https://doi.org/10.1016/j.apor.2020.102339
C. Antonio, "Sequential model based optimization of partially defined functions under unknown constraints," Journal of Global Optimization, vol. 79, no. 2, pp. 281–303, Feb. 2021. DOI: https://doi.org/10.1007/s10898-019-00860-4
"Jual Beli Mobil Bekas Terpercaya di Indonesia." Carsome, https://www.carsome.id/.
A. A. Tanvir, I. A. Khandokar, A. K. M. Islam, S. Islam, and S. Shatabda, "A gradient boosting classifier for purchase intention prediction of online shoppers," Heliyon, vol. 9, no. 4, Apr. 2023, Art. no. e15163. DOI: https://doi.org/10.1016/j.heliyon.2023.e15163
J. Sill, G. Takács, L. Mackey, and D. Lin, "Feature-Weighted Linear Stacking," Nov. 2009.
A. Hebbal, L. Brevault, M. Balesdent, E.-G. Talbi, and N. Melab, "Bayesian optimization using deep Gaussian processes with applications to aerospace system design," Optimization and Engineering, vol. 22, no. 1, pp. 321–361, Mar. 2021. DOI: https://doi.org/10.1007/s11081-020-09517-8
W. Gan, J. Li, and Y. Guo, "Research on ant colony optimization network access algorithm based on model of vehicle fog calculation, " in 2021 2nd International Conference on Big Data & Artificial Intelligence & Software Engineering (ICBASE), Zhuhai, China, Sep. 2021, pp. 52–55. DOI: https://doi.org/10.1109/ICBASE53849.2021.00018
N. Monburinon, P. Chertchom, T. Kaewkiriya, S. Rungpheung, S. Buya, and P. Boonpou, "Prediction of prices for used car by using regression models," in 2018 5th International Conference on Business and Industrial Research (ICBIR), Bangkok, Thailand, May 2018, pp. 115–119. DOI: https://doi.org/10.1109/ICBIR.2018.8391177
F. Hutter, L. Kotthoff, and J. Vanschoren, Eds., Automated Machine Learning: Methods, Systems, Challenges, 1st ed. Cham, Switzerland: Springer, 2019. DOI: https://doi.org/10.1007/978-3-030-05318-5
J.-C. Lévesque, C. Gagné, and R. Sabourin, “Bayesian hyperparameter optimization for ensemble learning,” in Proceedings of the Thirty-Second Conference on Uncertainty in Artificial Intelligence, Arlington, VA, USA, Jun. 2016, pp. 437–446.
Downloads
How to Cite
License
Copyright (c) 2024 Isti Surjandari, Ahmad Dzikri, Arian Dhini, Enrico Laoh, Kinanthy D. Pangesty, Pocut S. Aurora, Dewa Ferrouzi
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the 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) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
