Skip to content
  • There are no suggestions because the search field is empty.

Game Recommendations - Feature Guide

How Amplifier AI’s recommendation engine increases engagement, boosts revenue, and expands content discovery for online casinos.

Overview

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

 

Key Benefits

  • Increase player engagement with personalised recommendations.
  • Drive incremental revenue by surfacing games aligned with player preferences.
  • Expand game discovery and reduce content fatigue.
  • Improve new player conversion and early lifecycle retention.

 

Key Metrics

  • Uplift in active players engaging with recommended games.
  • Average number of games played per player.
  • Increase in player session frequency and duration.
  • Incremental stakes per player compared to control groups.
  • Conversion rates for new players.

 

Use Cases

The game recommendation engine integrates seamlessly with operator platforms to enable personalised player journeys. Below are key ways the product can be applied:

On-Site Personalisation

Recommendations can be surfaced across multiple areas of the casino front-end or CMS to guide player discovery and engagement:

  • Homepage & Lobby: Personalise key carousels so every player sees content most relevant to them the moment they log in.
  • Category & Subpages: Tailor sections such as “New,” “Trending,” or “Recommended” to highlight the most engaging content for each player segment.
  • Next Game Suggestions: Encourage continued play by surfacing relevant titles at natural decision points, such as when a player finishes or exits a game.
  • Metadata-Driven Carousels: Use attributes such as theme, volatility or features to create rich discovery paths unique to each player.

 

CRM & Marketing Campaigns

Recommendations can also be embedded into CRM systems to enhance outbound communications:

  • Targeted Offers: Include personalised game recommendations in bonus or free spin campaigns to boost engagement and conversion.
  • Reactivation Journeys: Deliver “We think you’ll love…” recommendations to re-engage lapsed players with content aligned to their past behaviour.
  • Lifecycle Nurturing: Support new player journeys by automatically highlighting the best converting games in their early sessions.
  • Weekly Game Picks: Provide a digest of recommended titles via email, push, or in-app messages to keep players returning.

 

Recommendation Categories

The system offers a diverse set of recommendation types, each designed to support specific use cases and align with targeted on-site carousels or features.

A complete list of recommendation categories is available in the Swagger API documentation, which requires a docs key for access and an API key for making requests. Each category is described in more detail below.

  • Your Favourites: 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.
  • 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 released in the last 30 days (timeframe configurable) 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 our game similarity model, which utilises metadata.
    • 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…”
    • For each set of recommendations, the favourite game on which they are based is provided as "context" in the response.
    • 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 our 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.
  • Your 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, but are also re-ordered for each player based on similarity to favourite games
  • 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. They are also re-ordered for each player based on similarity to favourite games
  • New Players
    • If a player has no transaction history, they receive the new player recommendations. These are games optimised for conversion, based on recent site activity (i.e. all new players get the same recommendations) that are designed to active brand new players who have no prior activity.
    • The API provides new player recommendations across all categories, so that you can serve the same structure to everyone – if you call the API with an unknown player ID, it will automatically return new player recommendations.
    • You can also use these for categories like Popular and Trending, if you want to return the standard versions of these categories, rather than re-ordered for individual players
    • 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.
  • New Games: Newly released titles released in the last 30 days (timeframe configurable) optimised for new players
  • Because You Played: The most popular ‘because you played’ recommendations
  • Players Like You: The most popular ‘Players like You’ recommendations
  • Game Discovery: The most popular ‘Game Discovery’ recommendations
  • 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.

 

Metadata Driven Personalisation

  • This feature enables operators to deliver highly tailored experiences through recommendation carousels powered by game metadata.
  • Configurable Carousels: Each carousel is built around a specific attribute such as theme, volatility, mechanics or features. Operators can pre-define which attributes to use, creating dedicated carousels for different player journeys.
  • Player-Specific Ranking: Within each carousel, games are ranked according to each player’s preferences. The order of the carousels themselves is also personalised for every player.
  • Fully Metadata-Driven: Game classification is based on the metadata you provide. Operators select which attributes to focus on, with guidance from Amplifier AI based on data quality and coverage. Typical attributes include:
      • Theme-based → “Egyptian Adventures,” “Sports Slots,” “Fantasy Worlds”
      • Volatility-based → “High Volatility Thrills,” “Low Volatility Relaxed Play”
      • Provider-based → “New from Pragmatic Play,” “NetEnt Favourites”
      • New Releases → “Hot Off the Press” (using launch date)
      • Feature-based → “Games with Free Spins,” “Megaways™ Mechanics”
      • Jackpots → “Progressive Jackpots,” “Daily Drops”

 

Site Personalisation

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

 

Multi-brand & multi-jurisdiction support

Recommendations are based on the games that are live for each brand or site. We also support multi-brand and multi-jurisdiction setups, so local rules are respected and players only see titles permitted in their region.

For more information:

 

How do I get support or make a feature suggestion?

Visit our 'here to help' form and we will respond accordingly.