price predictions essential to boost the efficiency and
profit of the industry. Therefore, applying machine
learning methods to assist participants with decision-
making is promising. This study offers insightful
information about used automobile pricing
predictions. Not only has it found the key features
which might affect the price of cars, but also shown
the preference of customers for those features. For
example, the importance values of various features
indicate that a 2.0-litre engine affects the price more
than its 1.2-litre counterparts. This study also
demonstrates the effectiveness of used car price
prediction based on machine learning methodology,
with XGBoost and RF showing superior
performance. The cross-validation scores indicate
that these models offer a high level of accuracy and
are capable of providing reliable price predictions for
used cars. However, the research has some limitations
at the present stage. Firstly, the car market is a
sophisticated system and the detailed information on
models involves complicated terms. The dataset
selected focused on a single manufacturer Ford and
simplified the issue. More work on data pre-
processing is acquired to predict data of a much larger
scale, such as annual domestic used car trading. Apart
from that, more features involved will inevitably lead
to the Multi-collinearity problem. In that case
additional machine learning methods need to be
implemented to handle that issue.
REFERENCES
Chen, T., Guestrin, C., 2016. XGBoost: A scalable tree
boosting system. arXiv preprint arXiv:1603.02754.
Chicco, D., Warrens, M. J., Jurman, G., 2021. The
coefficient of determination R-squared is more
informative than SMAPE, MAE, MAPE, MSE and
RMSE in regression analysis evaluation. PeerJ
Computer Science, 7, e623.
Cui, B., Ye, Z., Zhao, H., Renqing, Z., Meng, L., Yang, Y.,
2022. Used car price prediction based on the iterative
framework of XGBOOST + LightGBM. Electronics,
11(18), 2932.
Dahal, R., 2023. Used car price prediction using Linear
regression. https://www.researchgate.net/publication/
375697258_Used_car_price_prediction_using_Linear
_ regression.
Fawagreh, K., Gaber, M. M., Elyan, E., 2014. Random
forests: from early developments to recent
advancements. Systems Science & Control
Engineering, 2(1), 602–609.
Huang, J., Saw, S. N., Feng, W., Jiang, Y., Yang, R., Qin,
Y., Seng, L. S., 2023. A Latent Factor-Based Bayesian
Neural Networks Model in Cloud Platform for Used
Car Price Prediction. IEEE Transactions on
Engineering Management, 1–11.
Jin, C., 2021. Price prediction of used cars using machine
learning. In 2021 IEEE International Conference on
Emergency Science and Information Technology
(ICESIT) (pp. 223-230). Chongqing, China.
https://doi.org/10.1109/ICESIT53460.2021.9696839.
Manheim., 2023. Summary Methodology for Manheim
Used Vehicle Value Index. https://site.manheim.
com/wp-content/uploads/sites/2/2023/07/Used-
Vehicle-Summary-Methodology.pdf.
Mead, W. R., Brinkley, D., 2003. Wheels for the World:
Henry Ford, his Company, and A Century of Progress,
1903-2003. Foreign Affairs, 82(5), 176.
Yang, Q., He, K., Zheng, L., Wu, C., Yu, Y., Zou, Y., 2023.
Forecasting crude oil futures prices using Extreme
Gradient Boosting. Procedia Computer Science, 221,
920–926.