This item is a Paper in the Data Mining track.
- Agarwal, Deepak - Yahoo! Laboratories
- Chen, Bee-Chung - Yahoo! Laboratories
- Elango, Pradheep - Yahoo! Laboratories
Published Version
| PDF (2303Kb) |
Abstract
We propose novel spatio-temporal models to estimate clickthrough rates in the context of content recommendation. We track article CTR at a fixed location over time through a dynamic Gamma-Poisson model and combine information from correlated locations through dynamic linear regressions, significantly improving on per-location model. Our models adjust for user fatigue through an exponential tilt to the firstview CTR (probability of click on first article exposure) that is based only on user-specific repeat-exposure features. We illustrate our approach on data obtained from a module (Today Module) published regularly on Yahoo! Front Page and demonstrate significant improvement over commonly used baseline methods. Large scale simulation experiments to study the performance of our models under different scenarios provide encouraging results. Throughout, all modeling assumptions are validated via rigorous exploratory data analysis.
Export Record As...
- HTML Citation
- ASCII Citation
- Resource Map
- OpenURL ContextObject
- EndNote
- BibTeX
- OpenURL ContextObject in Span
- MODS
- DIDL
- EP3 XML
- JSON
- Dublin Core
- Reference Manager
- Eprints Application Profile
- Simple Metadata
- Refer
- METS