Scheduling on a budget: Avoiding stale recommendations with timely updates
Recommendation systems usually create static models from historical data. Due to concept drift and changes in the environment, such models are doomed to become stale, which causes their performance to degrade. In live production environments, models are therefore typically retrained at fixed time-in...
Main Authors: | Robin Verachtert, Olivier Jeunen, Bart Goethals |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-03-01
|
Series: | Machine Learning with Applications |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2666827023000087 |
Similar Items
-
Time-Aware Explainable Recommendation via Updating Enabled Online Prediction
by: Tianming Jiang, et al.
Published: (2022-11-01) -
Recommendation in the Age of Digital Communication: a Proposal for Business, Education, Social, Private Life Recommendation Scale (BESP-L) for Human Resources Communication
by: Barış Uçar, et al.
Published: (2023-02-01) -
A distributed real-time recommender system for big data streams
by: Heidy Hazem, et al.
Published: (2023-08-01) -
Research on Algorithm Recommended by Online Education for Big Data
by: Feng Tao, et al.
Published: (2015-01-01) -
IESR: Instant Energy Scheduling Recommendations for Cost Saving in Smart Homes
by: Muhammad Zaman Fakhar, et al.
Published: (2022-01-01)