Model Selection for Production System via Automated Online Experiments


A challenge that machine learning practitioners in the industry face is the task of selecting the best model to deploy in production. As a model is often an intermediate component of a production system, online controlled experiments such as A/B tests yield the most reliable estimation of the effectiveness of the whole system, but can only compare two or a few models due to budget constraints. We propose an automated online experimentation mechanism that can efficiently perform model selection from a large pool of models with a small number of online experiments. We derive the probability distribution of the metric of interest that contains the model uncertainty from our Bayesian surrogate model trained using historical logs. Our method efficiently identifies the best model by sequentially selecting and deploying a list of models from the candidate set that balance exploration-exploitation. Using simulations based on real data, we demonstrate the effectiveness of our method on two different tasks.


September 2022 | RecSys

Identifying New Podcasts with High General Appeal Using a Pure Exploration Infinitely-Armed Bandit Strategy

Maryam Aziz, Jesse Anderton, Kevin Jamieson, Alice Wang, Hugues Bouchard, Javed Aslam

September 2022 | Interspeech

Unsupervised Speaker Diarization that is Agnostic to Language Overlap Aware and Free of Tuning

M Iftekhar Tanveer, Diego Casabuena, Jussi Karlgren, Rosie Jones

July 2022 | SIGIR

What Makes a Good Podcast Summary?

Rezvaneh Rezapour, Sravana Reddy, Ann Clifton, Rosie Jones