Reproduce “Theory-guided relational learning for data product pricing: An interpretable meta-path-guided graph neural network approach” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Ruize Gao, Feng Xiao, Jinpu Li, Ke Tang, Shaoze Cui
The authors introduce MPGNN, a heterogeneous graph model that encodes relationship paths between data products and combines them to predict five price tiers and log-transformed prices. On time-based subscriptions, it reaches 0.729 classification accuracy, versus 0.613 for Qwen, and 0.994 regression RMSE, versus 1.175 for KG. Its results support predictive value from paths, not causal conclusions about suppliers.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.