Abstract
Routing decisions in recommender systems are typically framed as a difficulty problem: sending hard cases to the expensive large language model (LLM). However, this framing is incomplete because difficulty and business value are distinct axes—difficult cheap items and difficult costly items do not share the same cost of error.
We present Value Router, a fully synthetic simulation of a retail merchandising pipeline that routes items using only estimated difficulty and estimated value, never relying on ground truth.
Research Stages
-
A value-weighted threshold router is compared with a difficulty-only router and a random baseline on a synthetic catalog with an inverse correlation between category volume and value. Results show that value-weighting matches the difficulty-only baseline's recall of true high-value items (60%) while achieving substantially higher precision (98.3% vs. 94.3%).
-
A decision logger and monitor expose a hidden failure mode, indicating that the aggregate result is driven almost entirely by between-category differences rather than per-item discrimination.
-
A simulated Black Friday demand surge (2.5x volume with a shift toward higher-value categories) compares a static router, a seasonally tuned router, and two slow-path budget policies. All results are from a controlled synthetic simulation, illustrating design principles for cost-aware routing systems rather than validated real-world claims.
Blogger's Review: This paper introduces the concept of value-weighting, challenging traditional difficulty-based routing decisions and providing new insights for optimizing recommender systems. Particularly in the face of seasonal demand fluctuations, adopting dynamic routing strategies becomes crucial, and future research could explore the practical application of these theories in real-world scenarios.