A modified GraphSAGE for link prediction on the Amazon co-purchasing graph is reported to outperform a random forest baseline, but the evaluation never tests the stated problem of recommending isolated new products.
Random forests,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SI 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Building a Recommendation System Using Amazon Product Co-Purchasing Network
A modified GraphSAGE for link prediction on the Amazon co-purchasing graph is reported to outperform a random forest baseline, but the evaluation never tests the stated problem of recommending isolated new products.