Textual semantics and machine learning methods for data product pricing

2025-11-27

AI Summary

This study addresses the underutilization of semantic features in data product pricing by proposing a dual-path pricing framework that integrates textual semantics with machine learning. Methodologically, it systematically compares five text representation techniques—Word2Vec, Bag-of-Words (BoW), TF-IDF, GloVe, and BERT—and evaluates six predictive models—including linear regression, XGBoost, and neural networks—for two complementary tasks: continuous price prediction and price classification. The framework incorporates minimum-redundancy-maximum-relevance (mRMR) feature selection and SHAP-based interpretability analysis. Results show that Word2Vec achieves highest regression accuracy, whereas BoW and TF-IDF perform best for classification; semantic features exhibit strong explanatory power for price trends. The key contributions are: (1) the first empirical demonstration of differential efficacy across text representations under distinct pricing paradigms, and (2) a breakthrough in attribution-based interpretability for data product pricing via SHAP, providing both theoretical foundations and practical tools for market-oriented pricing of data as a production factor.

Technology Category

• Machine Learning: Feature Construction/Reformulation
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.
• Data Mining & Knowledge Management: Semantic Web

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Reasonable pricing of data products enables data trading platforms to maximize revenue and foster the growth of the data trading market. The textual semantics of data products are vital for pricing and contain significant value that remains largely underexplored. Therefore, to investigate how textual features influence data product pricing, we employ five prevalent text representation techniques to encode the descriptive text of data products. And then, we employ six machine learning methods to predict data product prices, including linear regression, neural networks, decision trees, support vector machines, random forests, and XGBoost. Our empirical design consists of two tasks: a regression task that predicts the continuous price of data products, and a classification task that discretizes price into ordered categories. Furthermore, we conduct feature importance analysis by the mRMR feature selection method and SHAP-based interpretability techniques. Based on empirical data from the AWA Data Exchange, we find that for predicting continuous prices, Word2Vec text representations capturing semantic similarity yield superior performance. In contrast, for price-tier classification tasks, simpler representations that do not rely on semantic similarity, such as Bag-of-Words and TF-IDF, perform better. SHAP analysis reveals that semantic features related to healthcare and demographics tend to increase prices, whereas those associated with weather and environmental topics are linked to lower prices. This analytical framework significantly enhances the interpretability of pricing models.

Problem

• Investigates textual semantics' impact on data product pricing
• Uses machine learning to predict prices via regression and classification
• Enhances pricing model interpretability with feature importance analysis

Innovation

• Word2Vec captures semantic similarity for continuous price prediction
• Bag-of-Words and TF-IDF used for price-tier classification tasks
• SHAP analysis interprets feature impact on data product pricing