Driving Engagement in Daily Fantasy Sports with a Scalable and Urgency-Aware Ranking Engine

TL;DR

This paper presents a scalable, urgency-aware ranking engine for daily fantasy sports that improves match recommendations by incorporating real-time urgency and recency features, validated on a large industrial dataset.

Contribution

The authors adapt the Deep Interest Network architecture with temporal features and develop a multi-GPU training system, achieving significant ranking improvements over baseline models.

Findings

+9% lift in nDCG@1 over baseline

Validated on over 650k users and 100B interactions

Effective real-time, urgency-aware recommendations

Abstract

In daily fantasy sports (DFS), match participation is highly time-sensitive. Users must act within a narrow window before a game begins, making match recommendation a time-critical task to prevent missed engagement and revenue loss. Existing recommender systems, typically designed for static item catalogs, are ill-equipped to handle the hard temporal deadlines inherent in these live events. To address this, we designed and deployed a recommendation engine using the Deep Interest Network (DIN) architecture. We adapt the DIN architecture by injecting temporality at two levels: first, through real-time urgency features for each candidate match (e.g., time-to-round-lock), and second, via temporal positional encodings that represent the time-gap between each historical interaction and the current recommendation request, allowing the model to dynamically weigh the recency of past actions. This approach, combined with a listwise neuralNDCG loss function, produces highly relevant and urgency-aware rankings. To support this at industrial scale, we developed a multi-node, multi-GPU training architecture on Ray and PyTorch. Our system, validated on a massive industrial dataset with over 650k users and over 100B interactions, achieves a +9% lift in nDCG@1 over a heavily optimized LightGBM baseline with handcrafted features. The strong offline performance of this model establishes its viability as a core component for our planned on-device (edge) recommendation system, where on-line A/B testing will be conducted.