AutoGen: An automated dynamic model generation framework for recommender system
Considering the balance between revenue and resource consumption for industrial
recommender systems, intelligent recommendation computing has been emerging recently …
recommender systems, intelligent recommendation computing has been emerging recently …
Adaptive Neural Ranking Framework: Toward Maximized Business Goal for Cascade Ranking Systems
Cascade ranking is widely used for large-scale top-k selection problems in online
advertising and recommendation systems, and learning-to-rank is an important way to …
advertising and recommendation systems, and learning-to-rank is an important way to …
Hydrus: Improving Personalized Quality of Experience in Short-form Video Services
Traditional approaches to improving users' quality of experience (QoE) focus on minimizing
the latency on the server side. Through an analysis of 15 million users, however, we find that …
the latency on the server side. Through an analysis of 15 million users, however, we find that …
Improve ROI with Causal Learning and Conformal Prediction
M Ai, Z Chen, J Wang, J Shang, T Tao, Z Li - arXiv preprint arXiv …, 2024 - arxiv.org
In the commercial sphere, such as operations and maintenance, advertising, and marketing
recommendations, intelligent decision-making utilizing data mining and neural network …
recommendations, intelligent decision-making utilizing data mining and neural network …
Computation resource allocation solution in recommender systems
Recommender systems rely heavily on increasing computation resources to improve their
business goal. By deploying computation-intensive models and algorithms, these systems …
business goal. By deploying computation-intensive models and algorithms, these systems …
PCDF: A Parallel-Computing Distributed Framework for Sponsored Search Advertising Serving
H Xu, H Qi, Y Wang, P Wang, G Zhang, C Liu… - … Conference on Machine …, 2023 - Springer
Traditional online advertising systems for sponsored search follow a cascade paradigm with
retrieval, pre-ranking, ranking, respectively. Constrained by strict requirements on online …
retrieval, pre-ranking, ranking, respectively. Constrained by strict requirements on online …
Cache-Aware Reinforcement Learning in Large-Scale Recommender Systems
X Chen, G Zhang, Y Wang, Y Wu, S Su… - … Proceedings of the …, 2024 - dl.acm.org
Modern large-scale recommender systems are built upon computation-intensive
infrastructure and usually suffer from a huge difference in traffic between peak and off-peak …
infrastructure and usually suffer from a huge difference in traffic between peak and off-peak …
Data-Driven Real-time Coupon Allocation in the Online Platform
Traditionally, firms have offered coupons to customer groups at predetermined discount
rates. However, advancements in machine learning and the availability of abundant …
rates. However, advancements in machine learning and the availability of abundant …
GreenFlow: a computation allocation framework for building environmentally sound recommendation system
Given the enormous number of users and items, industrial cascade recommendation
systems (RS) are continuously expanded in size and complexity to deliver relevant items …
systems (RS) are continuously expanded in size and complexity to deliver relevant items …
A Multi-agent Reinforcement Learning Based CR Allocation Approach For Multi-Scenario Advertising Systems
C Liu, Y Ye, L Zhang, R Fan, Y Chen… - 2024 IEEE 6th …, 2024 - ieeexplore.ieee.org
The goal of a recommender system is to recommend the most suitable items to a user from a
large number of candidate items. The computational cost increases with the number of user …
large number of candidate items. The computational cost increases with the number of user …