Revisiting N2DCG: Empirical Reformulation for Carousel Recommendation
_reachsumit · x · 2026-08-25
The study identifies limitations in the standard N2DCG metric for carousel recommendations: its ideal ranking violates carousel constraints and its discount function mismatches user behavior. The authors propose a reformulation that normalizes by respecting constraints and uses an empirically grounded discount function. Validated with eye-tracking data, the new metric better reflects user behavior and predicts carousel layout comparisons.
More from Research
- AAAI 2027 review debate: Should empirical papers without code be auto-rejected? — SimpleObvious4048 · 2026-08-25
- Study asks: Are LLM agents time-aware and budget-conscious? — maksym_andr · 2026-08-25
- SA-RSQ: Sparse Representation Framework for Multi-modal Recommender Systems — _reachsumit · 2026-08-25
- RAG collapse: LLM answers converge when retrieving self-authored content, 79.6% simulations collapse — _reachsumit · 2026-08-25
- Semantic subword tokenization improves generative recommenders by reducing intra-item attention overload — _reachsumit · 2026-08-25
- Spotify study: better reasoning traces can hurt recommender effectiveness — _reachsumit · 2026-08-25