Menu
Predicting bike prices accurately is essential for buyers and sellers alike in the dynamic market of biking. This study presents a practical
approach utilizing machine learning techniques to forecast bike prices based on various aƩributes such as brand, model, kilometer,
owner, condition, and city.
The methodology involves preprocessing the data to handle missing values and categorical variables, followed by the application of
regression algorithms including random forest, decision tree, linear regression, and gradient boosting. Model performance is
evaluated using common metrics like error or mean square and R-squared to assess prediction accuracy.
Future directions involve refining the models and incorporating additional data sources for improved predictive capabilities. We use
the KNN and Naïve Bayes Algorithm and have developed a Hybrid model for predicting the price of bike easily. To predict the output or
model of the dataset which can give a beƩ er accuracy from the existing model. The algorithms are Naïve Bayes, KNN (k-Nearest
Neighbours) by comparing various algorithms results, Hybrid model is providing best accuracy.
[1] Bukvić, L., Pašagić Škrinjar, J., Fratrović, T. and
Abramović, B., 2022. Price prediction and classiĕcation
of used-vehicles using supervised machine learning.
Sustainability, 14(24), p.17034.
[2] Chen, C., Hao, L. and Xu, C., 2017, May.
Comparative analysis of used car price evaluation
models. In AIP
Conference Proceedings (Vol. 1839, No. 1). AIP
Publishing.
[3] Louppe, G., 2014. Understanding random forests.
Cornell University Library, 10.
[4] Yin, Y.C., Lee, C.S. and Wong, Y.P., 2012. Demand
prediction of bicycle sharing systems. URL http://cs229.
stanford. edu/proj2014/YuchunYin, ChiShuenLee, Yu
PoWong, DemandPredictionofBicycleSharingSystems.
pdf.
[5] Ileberi, Emmanuel, Yanxia Sun, and Zenghui Wang.
“A machine learning based credit card fraud detection
using the GA algorithm for feature selection.” Journal of
Big Data 9.1 (2022): 24.
[6] Wang, B. and Kim, I., 2018. Short-term prediction
for bike-sharing service using machine learning.
Transportation research procedia, 34, pp.171-178.
[7] Kim, T.Y., Park, M.J., Shin, J. and Oh, S., 2022.
Prediction of Bike Share Demand by Machine Learning:
Role of Vehicle Accident as the New Feature.
International Journal of Business Analytics (IJBAN),
9(1), pp.1-16.
[8] Prada, S.J., Sri, A.G., Venkateswarlu, B., Vineesha, C.
and Teja, P.L., 2020. Bike Buyer Prediction. International
Journal of Computer Engineering and Technology,
11(3).
[9] Bhagirath, Mittal, N. and Kumar, S., 2021. Online
Resale Bike Price Prediction in Indian Market. In
Innovations in Cyber Physical Systems: Select
Proceedings of ICICPS 2020 (pp. 157-167). Springer
Singapore.
[10] Yang, R.R., Chen, S. and Chou, E., 2018. AI blue
book: vehicle price prediction using visual features.
arXiv preprint arXiv:1803.11227.
Desh Bhagat University,
Off to NH-44, Amloh Road, Mandi Gobindgarh,
District Fatehgarh Sahib, Punjab- 147301, India