Game Recommendations for Casino

Understanding Amplifier AI’s Game Recommendations API: How to Integrate and Optimise AI-Driven Player Engagement

Overview

Amplifier AI’s Game Recommendations engine delivers personalised game recommendations that boost player engagement, broaden content discovery and drive measurable revenue growth for casino operators.

Recommendation Categories

The Game Recommendations engine provides a wide range of recommendations to meet different use cases, with each category tailored to serve a specific carousel or feature on-site.

The full list of recommendation categories are detailed in this Swagger API documentation, which requires an API key to access. Each category is explained in more detail below.

• Recommended For You: Top recommendations for each player, curated from Amplifier AI’s various models. This category showcases a diverse set of games tailored to each player’s preferences.
• New Games: Newly released titles, re-ordered for each player based on similarity to their favourite games.
• Because You Played: 
  • Recommendations that are based on the similarity to a player’s favourite games, using Amplifier AI's game similarity model, which utilises metadata.
  • For each set of recommendations, the favourite game on which they are based is provided as "context" in the response.
  • In the below example, game id 000049 is the player’s favourite which the "Because You Played" recommendations are based on, hence can be used as “Because You Played game 000049…”
  
  Players with multiple favourites can trigger multiple recommendation sets — ideal for multi-carousel personalisation.
• Players Like You: Recommendations based on players who have similar favourite games, powered from Amplifier AI’s collaborative filtering model.
• Game Discovery: Designed to break the routine, these recommendations highlight games that differ from a player’s usual choices - perfect for a "try something different" carousel. They encourage experimentation and help unearth hidden gems within your gaming portfolio.
• Popular Games: Recommendations of the most popular games on-site. Popularity is determined by the theoretical revenue generated during a configurable time window (the past 7 days by default). These recommendations help surface proven content that consistently drives engagement and results.
• Trending Games: These recommendations highlight titles with the biggest recent surge in activity - great for surfacing high-momentum content. Amplifier AI identifies trending games by analysing the week-on-week change in theoretical revenue over the past 3 days. To ensure quality, the model blends this uplift with overall game popularity and only games above a defined staking threshold are considered.
• Default/Fallback APIs: 
  
  • New Players Recommendations: Recommendations for new players which are optimised against best converting games. These will be returned automatically if recommended_for_you is called with an unknown player id, or a player id with no significant activity.
  • New Players Conversion: Personalised recommendations for players in early lifecycle – these will automatically be returned if recommended_for_you is called for a player in early lifecycle. 

• • Other categories in the default section map to the ‘recommendation’ section, and will be returned where the player id is unknown. 

• A player’s favourite games based on Amplifier AI’s significant activity model. 

• Typically, these would be used instead of Recently Played as a more accurate version of a player’s recent favourites. 

Site Personalisation: 

• It is recommended to call categories independently and employ lazy loading. 
• However, this category will consolidate all categories into a single payload.

Recommendations can also be customised based on data availability to ensure compliance with local jurisdictions and game type specifications (e.g., slots-only recommendations where applicable).

Still have questions? Check out our FAQs for further assistance.