Data Pricing Model Integrating Beluga Whale Optimization with XGBoost and SHAP Explainability Analysis

Evolutionary and Institutional Economics Review · Springer Nature · 2026-11-07 · DOI: 10.1007/s10614-026-11469-7

Аннотация

Data pricing plays a key role in promoting the efficient circulation of data elements in the market. However, existing methods still have limitations in terms of targeting, dynamics, and comprehensiveness. This study proposes a data price prediction model based on Beluga Whale optimized XGBoost to provide scientific support for data market pricing decisions. First, we collect transaction data from the API zone of the Youyi Data platform and perform data cleaning and sample screening. Second, we preprocess the data using methods such as outlier treatment, one-hot encoding, and logarithmic transformation. Lasso regression is used for feature selection to construct a data price prediction model containing 19 features. Finally, the BWO algorithm is used to optimize the hyperparameters of XGBoost to improve the model’s predictive performance. Experimental results show that the BWO-XGBoost model improves the R 2 metric by 2.3% to 23.8% compared to five comparison models: XGBoost, GBDT, LightGBM, DT, and RF. It significantly outperforms the comparison models in five evaluation metrics: MSE, RMSE, MAE, MAPE, and RMSPE, verifying the model’s advantages in predictive accuracy and stability. In addition, based on SHAP interpretability analysis, the impact mechanism of key features on data prices is further clarified, providing theoretical support for pricing decisions.

Читать у издателя →

Похожие статьи