Building an expert matching recommender
La forma del problema Un directorio es una superficie: el miembro lo abre y adivina. Un recomendador es una superficie de empujar: el sistema propone y tiene que justificarse. La justificación es la parte difícil, y es donde vive la estadística. Tres restricciones hicieron esto distinto de un recomendador de contenido: El item es una persona con capacidad finita. Un hilo se le puede recomendar a…
A team has developed a recommendation system to match experts with people requesting help, addressing the challenge of suggesting suitable experts with limited capacity. The system combines three independent retrievers using Reciprocal Rank Fusion, which merges ranked lists of expert IDs based on their ranking, disregarding the scale of each retriever.
The scoring system uses a weighted compound of factors, including expert quality, semantic fit, and fairness, with weights assigned to each factor. The system also addresses the issue of assigning experts to requests, using a global greedy allocation approach to ensure that experts' capacity is not overwhelmed.
Written by urgent.news from Dev.to's report — not a translation of it. Machine-written — may contain errors; check the original before relying on it.
