Analysis of Electric Vehicle Clustering and Price Prediction Using K-Means Clustering and Multiple Linear Regression

Authors

  • Kharla Septiana Universitas Bengkulu
  • Afni Cahaya Putri Universitas Bengkulu
  • Nadya Monalisa Universitas Bengkulu
  • Dewi Astuti Universitas Bengkulu
  • Etis Sunandi Universitas Bengkulu
  • Wina Ayu Lestari Statistika, Universitas Bengkulu

DOI:

https://doi.org/10.25181/rt.v4i2.4975

Keywords:

K-Means Clustering, Cross-Validation, Electric Vehicles, Multiple Linear Regression, Evaluation Metrics

Abstract

The development of the electric vehicle industry has increased the need for accurate and data-driven vehicle price prediction systems. This study aimed to analyze clustering and predict electric vehicle prices based on vehicle technical characteristics using K-Means Clustering and multiple linear regression methods. The dataset consisted of 2,000 observations with variables including vehicle price, production year, battery capacity, driving range, and charging speed. The optimal number of clusters was determined using the Elbow Method, followed by the implementation of K-Means Clustering with three clusters. The clustering results were then used as additional variables in the multiple linear regression model evaluated using 10-fold cross-validation. The results showed that the addition of cluster variables improved prediction model performance, indicated by a decrease in RMSE from 33,366.41 to 29,981.22 and MAE from 26,211.76 to 23,508.42, as well as an increase in R² from 0.1092 to 0.2827. These findings indicate that the combination of K-Means Clustering and multiple linear regression can improve the model’s ability to predict electric vehicle prices based on vehicle characteristics.

Downloads

Download data is not yet available.

Author Biographies

Kharla Septiana, Universitas Bengkulu

Universitas Bengkulu

Afni Cahaya Putri, Universitas Bengkulu

Universitas Bengkulu

Nadya Monalisa, Universitas Bengkulu

Universitas Bengkulu

Dewi Astuti, Universitas Bengkulu

Universitas Bengkulu

Etis Sunandi, Universitas Bengkulu

Universitas Bengkulu

Wina Ayu Lestari, Statistika, Universitas Bengkulu

Statistika, Universitas Bengkulu

References

[1] S. Afandizadeh, D. Sharifi, N. Kalantari, and H. Mirzahossein, "Using machine learning methods to predict electric vehicles penetration in the automotive market," Scientific Reports, vol. 13, p. 8345, 2023, https://doi.org/10.1038/s41598-023-35366-3.

[2] S. J. Choi and J. Jiao, "Uncovering electric vehicle ownership disparities using K-means clustering analysis: A case study of Austin, Texas," Journal of Computational Social Science, vol. 7, pp. 2403–2456, 2024, https://doi.org/10.1007/s42001-024-00310-6.

[3] S. Dubey, A. Renavikar, and S. Kanungo, "Machine learning model for prediction of electric vehicle prices," Journal of Information Systems Engineering and Management, vol. 10, no. 50s, pp. 1006–1017, 2025, https://doi.org/10.52783/jisem.v10i50s.10456.

[4] Y. Gan, M. Wang, Z. Lu, and J. Kelly, "Taking into account greenhouse gas emissions of electric vehicles for transportation decarbonization," Energy Policy, vol. 155, p. 112353, 2021, https://doi.org/10.1016/j.enpol.2021.112353.

[5] M. S. Hossain, L. Kumar, M. M. Islam, and J. Selvaraj, "A comprehensive review on the integration of electric vehicles for sustainable development," Journal of Advanced Transportation, vol. 2022, p. 3868388, 2022, https://doi.org/10.1155/2022/3868388.

[6] I. Hussain, K. B. Ching, C. Uttraphan, K. G. Tay, and A. Noor, "Evaluating machine learning algorithms for energy consumption prediction in electric vehicles: A comparative study," Scientific Reports, vol. 15, no. 1, pp. 1–20, 2025, https://doi.org/10.1038/s41598-025-94946-7.

[7] A. M. Ikotun, A. E. Ezugwu, L. Abualigah, B. Abuhaija, and J. Heming, "K-means clustering algorithms: A comprehensive review, variants analysis, and advances in the era of big data," Information Sciences, vol. 622, pp. 178–210, 2023, https://doi.org/10.1016/j.ins.2022.11.139.

[8] A. Khan, N. Iqbal, Z. Kaleem, Z. Qarnain, and M. M. Bait-Suwailam, "A multi-model approach for predicting electric vehicle specifications and energy consumption using machine learning," The Journal of Supercomputing, vol. 81, p. 314, 2025, https://doi.org/10.1007/s11227-024-06820-4.

[9] R. D. Mishra, S. K. Dash, S. Chudjuarjeen, S. Mohanty, S. P. Gautam, R. I. Mohanty, and M. T. Tanvir, "Hybrid LSTM-GBRT based machine learning technique implementation for electric vehicle sales prediction analysis," International Journal of Sustainable Engineering, vol. 17, no. 1, pp. 843–858, 2024, https://doi.org/10.1080/19397038.2024.2411284.

[10] S. Pokharel, P. Sah, and D. Ganta, "Improved prediction of total energy consumption and feature analysis in electric vehicles using machine learning and Shapley additive explanations method," World Electric Vehicle Journal, vol. 12, no. 3, p. 94, 2021, https://doi.org/10.3390/wevj12030094.

[11] J. A. Sanguesa, V. Torres-Sanz, P. Garrido, F. J. Martinez, and J. M. Marquez-Barja, "A review on electric vehicles: Technologies and challenges," Smart Cities, vol. 4, no. 1, pp. 372–404, 2021, https://doi.org/10.3390/smartcities4010022.

[12] A. I. Simsek, E. Koç, B. Desticioglu Tasdemir, A. Aksöz, M. Turkoglu, and A. Sengur, "Deep learning forecasting model for market demand of electric vehicles," Applied Sciences, vol. 14, no. 23, p. 10974, 2024, https://doi.org/10.3390/app142310974.

[13] K. P. Sinaga and M. S. Yang, "Unsupervised K-means clustering algorithm," IEEE Access, vol. 8, pp. 80716–80727, 2020, https://doi.org/10.1109/ACCESS.2020.2988796.

[14] H. Sonar, H. M. Belal, C. Foropon, R. Manatkar, and V. Sonwaney, "Examining the causal factors of the electric vehicle adoption: A pathway to tackle climate change in resource-constrained environment," Annals of Operations Research, vol. 355, no. 1, pp. 59–85, 2023, https://doi.org/10.1007/s10479-023-05519-8.

[15] I. Ullah, K. Liu, T. Yamamoto, R. E. Al Mamlook, and A. Jamal, "A comparative performance of machine learning algorithm to predict electric vehicles energy consumption: A path towards sustainability," Energy & Environment, vol. 33, no. 8, pp. 1583–1612, 2022, https://doi.org/10.1177/0958305X211044998.

[16] J. R. R. Uy, A. K. S. Ong, D. M. B. De Guzman, I. T. Dela Cruz, and J. C. Dela Cruz, "Consumer segmentation and market analysis for sustainable marketing strategy of electric vehicles in the Philippines," World Electric Vehicle Journal, vol. 15, no. 7, p. 301, 2024, https://doi.org/10.3390/wevj15070301.

[17] C. Wongoutong, "The impact of neglecting feature scaling in k-means clustering," PLOS ONE, vol. 19, no. 12, p. e0310839, 2024, https://doi.org/10.1371/journal.pone.0310839.

[18] B. Zhang and J. Kang, "Profiling user segments and spatial clusters of EV uptake through multi-method modeling," Sustainable Environment, vol. 11, no. 1, p. 2544396, 2025, https://doi.org/10.1080/27658511.2025.2544396.

Downloads

Published

2026-07-27

Issue

Section

Articles