Summary of On a Scale-invariant Approach to Bundle Recommendations in Candy Crush Saga, by Styliani Katsarou et al.
On a Scale-Invariant Approach to Bundle Recommendations in Candy Crush Saga
by Styliani Katsarou, Francesca Carminati, Martin Dlask, Marta Braojos, Lavena Patra, Richard Perkins, Carlos Garcia Ling, Maria Paskevich
First submitted to arxiv on: 13 Aug 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper introduces attentive models for producing item recommendations in a mobile game scenario, specifically focusing on Candy Crush Saga. The authors combine supervised and unsupervised approaches to create user-level recommendations, introducing a novel scale-invariant approach to prediction. They apply this methodology to bundle recommendation, highlighting the impact of degenerate feedback loops and novelty effects. The evaluation focuses on understanding engagement, click-and-take rates, recommendation diversity, and diminishing effects of accuracy on engagement. Results show a 30% increase in click rate and over 40% in take rate, demonstrating enhanced user engagement. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Mobile games like Candy Crush Saga can be more engaging when the game suggests relevant items to play. This paper uses special models that understand what players like and dislike to recommend new things to try. They tested these recommendations on real players and found that it increased how much people played (click rate) by 30% and how often they took a recommended action by over 40%. The authors also studied how the quality of the recommendations affects player engagement. |
Keywords
» Artificial intelligence » Supervised » Unsupervised
