Personalized Execution Time Optimization for the Scheduled Jobs

TL;DR

This paper presents a machine learning-based approach for optimizing execution times of scheduled batch jobs across multiple product domains, improving user engagement and resource efficiency at an industrial scale.

Contribution

It introduces a novel ensemble learning method combined with a best time policy for personalized job scheduling in large-scale industrial environments.

Findings

Significant improvements in product metrics like notifications and content generation.

Effective handling of user peak time conflicts through a coordination system.

Validated on production traffic serving billions of users daily.

Abstract

Scheduled batch jobs have been widely used on the asynchronous computing platforms to execute various enterprise applications, including the scheduled notifications and the candidate pre-computation for the modern recommender systems. It is important to deliver or update the information to the users at the right time to maintain the user experience and the execution impact. However, it is challenging to provide a versatile execution time optimization solution for the user-basis scheduled jobs to satisfy various product scenarios while maintaining reasonable infrastructure resource consumption. In this paper, we describe how we apply a learning-to-rank approach plus a "best time policy" in the best time selection. In addition, we propose an ensemble learner to minimize the ranking loss by efficiently leveraging multiple streams of user activity signals in our scheduling decisions of the execution time. Especially, we observe the cannibalization cross use cases to compete the user's peak time slot and introduce a coordination system to mitigate the problem. Our optimization approach has been successfully tested with production traffic that serves billions of users per day, with statistically significant improvements in various product metrics, including the notifications and content candidate generation. To the best of our knowledge, our study represents the first ML-based multi-tenant solution of the execution time optimization problem for the scheduled jobs at a large industrial scale cross different product domains.