HCEG: A heterogeneous clustering ensemble learning approach with gravity-based strategy for data assets intelligent pricing

Data pricing plays a pivotal role in fostering the growth of data markets, enhancing the efficiency of data utilization, and realizing the full potential of data value. Nevertheless, the intricate nature and specificity of data assets render accurate pricing a formidable challenge. To tackle this challenge, we adopt the "divide and conquer" approach and introduce a heterogeneous ensemble pricing model grounded in clustering strategies to enhance the precision of data asset pricing. Initially, our study generates 15 diverse pricing models as potential candidates, leveraging clustering strategies to achieve an adaptive aggregation of data assets. Notably, we introduce an innovative weight generation strategy based on the concept of universal gravitational force to integrate the pricing results. To validate the effectiveness of our Heterogeneous Clustering Ensemble Gravity-based pricing model (HCEG), we conduct computational experiments on transaction platform data assets. The results unequivocally demonstrate the superiority of the proposed HCEG pricing model in data asset pricing. Furthermore, our study delves deeper into the impact of clustering centers, feature selection, and integration strategies on the performance of the pricing model. This comprehensive analysis provides valuable insights for optimizing and enhancing the precision of data asset pricing.