Reduction of Information Asymmetry in the Used Car Market Using the Random Forest Method

Bies, Milosz; Gryncewicz, Wiesława; Kozina, Agata; Hernes, Marcin; Rot, Artur; Zygała, Ryszard

doi:10.1109/acit52158.2021.9548466

Cited by 2 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For category features with high base such as city and urban coding, the use of one-hot encoding generates a large number of sparse matrices, requires large memory, and takes a long training time [8]. In this paper, we choose to use mean encoding, which is a Bayesian framework that uses the target variables to be predicted and supervises the identification of the most appropriate qualitative features for that.…”

Section: Feature Encodingmentioning

confidence: 99%

Prediction of used car prices using back propagation neural network model based on mean encoding

Kan¹,

Jiang²,

Liu³

et al. 2023

Third International Conference on Intelligent Computing and Human-Computer Interaction (ICHCI 2022)

View full text Add to dashboard Cite

With the growth of the used car market and the development of e-commerce platforms, the need for accurate valuation of used car prices is becoming more urgent. Accuracy of price evaluation is the key to the success of used car transactions. At present, the common methods are manual experience method, Monte Carlo method, etc. Among them, manual experience method and multi-attribute decision method are more mature and widely used in traditional pricing method, but they have some disadvantages such as large computation amount and low accuracy. Aiming at the above problems, a BP neural network model based on mean encoding is designed in this paper. After extracting the features of the model, BP neural network is used to study the pre-processing data to predict the price for the network output. In this paper, a real used car trading dataset was used to test the model. The 2 R error is 0.976. Compared with the SVM and the decision tree model, this model is more accurate.

show abstract

Section: Feature Encodingmentioning

confidence: 99%

Prediction of used car prices using back propagation neural network model based on mean encoding

Kan¹,

Jiang²,

Liu³

et al. 2023

Third International Conference on Intelligent Computing and Human-Computer Interaction (ICHCI 2022)

View full text Add to dashboard Cite

show abstract

“…The second part is about using other models to explore and analyze the pricing factors in the used car market, and we summarize that: some literatures propose an iterative framework combining XGBoost and LightGBM (Cui et al 2022) [6]; some literatures utilizes the random forest method to reduce the information asymmetry in the used car market (Bies et al 2021, September) [7]; and some literatures have proposed random forest prediction model, GBDT prediction model and SVM prediction model that predict and compare used car prices (Xu et al 2023, March) [8]; some literature uses python, flask, and HTML as well as linear regression and lasso regression to create models that utilize machine learning to predict used car prices (Mukharjee et al 2023) [9]; and others identify the best predictive model through heuristic algorithms (Bilen 2021) [10].…”

Section: Literature Reviewmentioning

confidence: 99%

Research and Analysis Based on Pricing of Used Sailboats in the World and Hong Kong

Ding,

Wang,

Sun

2023

HBEM

View full text Add to dashboard Cite

In order to better complete the evaluation of used sailboat prices, this article succeeded in having a system that can predict the prices of used sailboats and combined various analytical methods to realize the prediction of Hong Kong sailboat prices. This article focuses on the following issues: identifying mathematical models for rational pricing, explaining the effect of regional variables on prices, and simulating the regional impact of sailboat prices. This article consists mainly of the following: First, neural networks and deep learning related models are developed to measure the impact of sailboat characteristics on their pricing from multiple perspectives, and predictions are made for the used sailboats based on these models. Second, a variety of geographical factors are taken into account to analyze the correlation of regions, and regional variables with strong correlation analysis are added and combined with BiLSTM-AT model to explain the influence of regions on listing prices. Then, data on the corresponding variables in Hong Kong were collected, and cluster analysis was performed on regionally relevant factors to construct a multi-regional cluster price model. Last, sensitivity analysis and robustness analysis are performed on the completed model.

show abstract

Reduction of Information Asymmetry in the Used Car Market Using the Random Forest Method

Cited by 2 publications

References 12 publications

Prediction of used car prices using back propagation neural network model based on mean encoding

Prediction of used car prices using back propagation neural network model based on mean encoding

Research and Analysis Based on Pricing of Used Sailboats in the World and Hong Kong

Contact Info

Product

Resources

About