← All talks · Keynote

Search, Recommenders and Co-pilots: Evolution of Evaluation Strategies in the Industry

FIRE 2023 — Industrial Track Keynote ·Goa, India ·December 15, 2023

Abstract

Industrial-track keynote at the Forum for Information Retrieval Evaluation. Traced the evolution of evaluation methodology across search, recommendation, and emerging LLM-assisted co-pilot products — from offline relevance metrics to online multi-objective optimization and, increasingly, hybrid evaluation regimes for generative systems. Drew on production experience scaling recommenders at ShareChat from 1M to 200M users.

Slides

Open slides in a new tab →

Links & tags

recsysevaluationindustry

Notes:

  • Audience: information-retrieval and recsys research community + industry practitioners attending FIRE.
  • Argument: evaluation is the most underrated lever in production ML systems. As systems shift from ranking to generation, the measurement substrate has to shift with them — not just new metrics but new experiment shapes.
  • Companion resources: the slide deck linked above.