Demographic-Aware Product Recommendation through Heterogeneous Graph Neural Networks
Bibliographic record
Abstract
Given their key position in modern-day online infrastructure, deployment-ready recommendation systems are required to be both scalable and accurate. Conventional methods such as collaborative filtering and matrix factorization techniques often face limitations when faced with sparse and temporally dynamic datasets. This paper introduces a demographic-aware recommendation system by leveraging Heterogeneous Graph Neural Networks (HGNN) trained for link prediction. The study systematically assesses the performance of 4 distinct HGNN architectures in a single unified pipe, constructed with: Graph Sampling and Aggregation (SAGE), Graph Attention (GAT), Relational Graph Convolution (RGCN), and Spectral GraphConv operators. Furthermore, the study constructs a heterogeneous graph with directed edges, and distinct node types for products and customers, where customer demographic information, in addition to product attribute information, is embedded as first-order features. Evaluated on a real-world retail dataset, the models show up to a 94% link prediction accuracy, F1-score, and AUC in addition to an average precision of 88%. Overall, the champion model shows exceptional performance in link prediction while resolving the cold-start issue often faced in recommendation systems.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".