1. Knowledge Base
  2. Retain
  3. Game Recommendations (Casino)

Game Recommendations - Measuring & Reporting

Target and Control Groups

The performance of game recommendations is analysed by comparing two groups:

  • Target Group: Receiving Amplifier AI’s recommendations.
  • Control Group: Receiving alternative recommendations, Amplifier AI can accommodate Popular, Random and even Empty recommendation, depending on an operator’s decision.

Amplifier AI’s Approach

Rather than relying on a historical comparison of time periods which can be skewed by growth, Amplifier AI employs comparative analysis between target and control groups. This analysis is based on an agreed selection of player KPI’s.

Where data is provided, there will be a stratification between different player samples, such as new and retained players.

gamerecc

Performance metrics (e.g., stakes, NGR, spins) are evaluated to understand the impact of recommendations on player engagement and revenue.

Reporting Dashboards (v1.3)

    Understanding the "Group Comparison" Dashboard

    Overview

    This dashboard provides a comparative analysis between target and control groups for game recommendations, allowing operators to evaluate the effectiveness of Amplifier AI recommendation engine.

    Filter Options:
    Use these filters to narrow down your analysis and tailor the report to your specific needs

    • Time Period: Set a custom date range to view the data over a specific period.
    • Player Group: Select multiple player segments for comparison (defaulted selected on Target & Recommended played vs. Control group)

    Key Sections of the Dashboard

    Active Player Count for Target vs. Control Groups (Top Chart):

    This chart compares the daily active player count for the target and control groups.

    • Control Group: Represents Active players who did not receive game recommendations.
    • Target & Recommended Played: Represents players in the target group who received and engaged with the recommended games.
    • Target & Recommended Not Played: Represents players in the target group who received but not engaged with the recommended games.

    <KPI> Per Player: Target vs. Control Groups (Bottom Chart)

    This chart displays the average number of games played per player in the target and control groups over time.

    Available Metrics Buttons (Right Side)

    • Stakes/Player: Displays the average stakes per player for target and control groups.
    • Spins/Player: Shows the average number of spins per player.
    • Sessions/Player: Represents the average number of sessions per player.
    • Games/Player: The default view, showing the average number of games played per player in each group.

    Interpreting the Data

    • Higher Engagement in Target Group: A consistently higher active player count and games per player in the target group compared to the control group indicate that game recommendations positively impact engagement.
    • Impact of Recommendations on Game Variety: If the target group shows a higher average number of games per player, this suggests that recommendations encouraging players to explore a broader range of games.

    Best Practices for Using This Dashboard

    • Monitor Player Engagement Trends: Track how engagement metrics evolve over time to evaluate the ongoing effectiveness of personalized recommendations.

    Understanding the "Group Table" Report

    Overview

    This report provides a breakdown of player engagement metrics by player groups, showing differences in activity levels and engagement with recommended and non-recommended games. The metrics highlight daily player averages, total spins, total sessions, and engagement levels within different player types, helping operators assess the impact of game recommendations and player segments on overall player behaviour.

    Player Group and Player Type Breakdown

    The report categorises players into distinct groups based on their interaction with recommended content:

    • Control: Represents Active players from the Control group (didn’t receive recommendations)
      This group serves as a baseline to compare against other player segments which served with recommendations.
    • Target & Rec Not Played: Consists of Active targeted players who were shown game recommendations but didn’t engage with any.
    • Target & Rec Played: Consists of Active targeted players who were shown and engaged with recommended games.  

    Key Metrics in the Report

    The following metrics provide insights into player behaviour across each group and player type:

    • Daily Average Players: The average number of active players per day within each group.
    • Total Spins: The total number of spins recorded for each group, providing insight into the overall engagement and play volume.
    • Total Sessions: The cumulative number of sessions per group.
    • Spins Per Player (Daily Average): The average number of spins per player per day, showing how frequently players engage with games on average.
    • Sessions Per Player (Daily Average): The average number of sessions per player per day, reflecting engagement intensity.
    • Games Played Per Player (Daily Average): The average number of different games played by each player per day, highlighting player variety in game selection.

    Interpreting the Data

    • Control Group as Baseline: The Control group serves as a reference point, providing insight into typical engagement levels when no recommended games are played.
    • Higher Engagement in Target & Rec Played: Players who engaged with recommendations show significantly higher values in metrics such as Spins Per Player and Sessions Per Player. This suggests that recommendations enhance player engagement when they are acted upon.

    Best Practices for Using This Report

    • Evaluate Recommendation Effectiveness: Compare metrics between the Control and Target groups to assess whether game recommendations are driving additional engagement. Higher engagement in Target & Rec Played players suggests positive recommendation impact.
    • Focus on Targeted Players: Use insights from the Target & Rec Not Played group to identify potential reasons why recommended games were not chosen 

    Understanding the "Network Analysis" Graph

    Overview

    The Network Analysis graph provides insights into the relationship between recommended games. This visualization displays the connections between games frequently recommended to active players in the last 7 days, helping operators identify clusters of games with shared player interest and recommendation overlap.

    Filter Options:
    Use these filters to tailor the graph to your specific needs

    • Time Period: Set for Last 7 days, as a single option.
    • Favorite Game: Focus on recommendations related to a specific game, showing how it connects with other games. The favorite game is the centred node in the graph.
    • Ranking: Filter the network by recommendation ranking to focus on top-ranked games. There are 2 options: Ranked 1-5 and ranked 1-10.
    • Frequency: Set a minimum and maximum frequency threshold to focus on games with certain levels of recommendation frequency and filter out games with weaker relationships.

    Key Metrics in the Network Analysis

    • Game Name: Each node represents a game (e.g., Game 1097, Game 2426) in the recommendation network.
    • Frequency: The thickness of the connection lines between games represents the recommendation frequency. Higher frequency indicates more shared recommendations between games, while thinner lines represent less common recommendation patterns. Remember that you can filter out lower frequency by using the filter.
    • Recommendation Clusters: Clusters of games closely connected indicate sets of games often recommended together, suggesting shared player preferences.

    Interpreting the Data

    • Core Game: Game at the center of the network with multiple connections (e.g., Game 1097) is the one you filtered Favorite Game.
    • Peripheral Games: Games with fewer connections or that are on the outer edge of the network may have niche appeal or limited overlap with other games.
    • Recommendation Overlap: Strong connections between games indicate that players often receive recommendations for these games together. This insight can guide bundling or thematic promotion strategies.

    Best Practices for Using This Dashboard

    • Identify Core and Niche Games: Focus on core games with high connectivity for widespread promotion, and use peripheral games for targeted recommendations based on specific player interests.

    Understanding the "Recommendation Engagement" Dashboard

     

    Overview

    The Recommendation Engagement dashboard focuses on how well game recommendations perform, specifically measuring player engagement with recommended games. It includes two primary metrics: Recommendation Hit Rate Over Time and Recommendation Hit Rate by Game.

    • Recommendation Hit Rate: This is the percentage of players who engaged with (played) a recommended game. A higher hit rate indicates stronger alignment between recommendations and player interests.

    Key Sections of the Dashboard

    Recommendation Hit Rate Over Time for All Active Players (top chart)

    • This chart tracks the hit rate percentage for recommended games across weekly intervals (e.g., Week 41 to Week 46). It shows fluctuations in player engagement with recommended games over time.
    • Interpreting Trends: Consistent or increasing hit rates over time indicate effective recommendation strategies, while sharp dips may suggest a need to review the relevance or timing of recommendations.

    Recommendation Hit Rate by Game

    • This section displays the hit rate per game, illustrating how effective each game recommendation is in terms of player engagement.
    • Interpreting High vs. Low Hit Rates: Games with higher hit rates (e.g., Game 1499, Game 1497) are better aligned with player interests and might be prioritised in recommendation algorithms. Games with lower hit rates may need additional testing or repositioning to boost engagement.

    How to Use This Dashboard

    • Identify Trends: Observe hit rate changes over time to determine the effectiveness of ongoing recommendation strategies and refine them based on seasonal trends or player behaviour changes.

    Optimise Game Recommendations: Games with consistently high hit rates represent strong recommendation candidates. Consider increasing their exposure in recommendations to maximise engagement.

     

    Understanding the "Recommendation Impact" Dashboard

    Overview

    This Recommendations Impact dashboard provides a detailed view of how recommendation frequency correlates with player stakes for a specific game over a selected time period. By examining metrics like total stakes and recommendation count, operators can assess how effectively recommendations are driving player engagement, and make data-driven decisions to optimise future recommendations.

    Filter Options

    Use these filters to narrow down your analysis and tailor the report to your specific needs

    • Time Period: Define a custom date range to view recommendations and stakes data over a specific timeframe.
    • Recommendation Ranking: Filter the data by recommendation rank (e.g., Rank 1 – Rank 5) to focus on the top-ranked recommendations.

     Key Sections of the Dashboard

    <Game Title> Total Stakes vs. Number of Times Recommended (Top Chart)

    This metric visualises the relationship between the total stakes placed on a game and the number of times it was recommended. It allows operators to assess if recommendations are positively impacting stakes over time.

    You can select any game from the drop-down list on the right side and see the results.

    Top Games by Stakes (Bottom Chart)

    Displays stakes for multiple games over the selected period, enabling a comparison of the game selected on the top chart against other games in terms of player engagement and spend.

    The bottom chart should be filtered either by specific Game, or top 5/10 Games.
    *for now the only KPI for comparison is Stakes.

    Interpreting the Data

    • High Recommendation Frequency & High Stakes: Games with high recommendation frequency and significant stakes (e.g., Game 1000) are likely to be well-aligned with player interests and should continue to feature prominently in recommendations.
    • High Recommendation Frequency but Lower Stakes: Games that are frequently recommended but do not generate high stakes may need further adjustment.

    Understanding "Top Recommendations" Dashboard

    Overview

    This dashboard provides insights into the top games recommended to Active players over a selected time period. It ranks games based on both total recommendations and stake value, helping operators identify which games are most often recommended and generate the highest player engagement through stakes.

    Filter Options:
    Use these filters to narrow down your analysis and tailor the report to your specific needs

    • Time Period: Set a custom date range to view recommendation data over a specific period.
    • Game: Filter results by specific games you wish to focus.
    • Recommended Ranking: Filter the results on selected ranking (defaulted to Rank1 – Rank5 to focus the results based on the top ranking).
    • Site: Select specific casino sites if you operate across multiple brands or domains.
    • Jurisdiction: Filter by geographical regions to analyse engagement across different jurisdictions.

    Key Metrics in the Dashboard

    • Game Name: The name of each recommended game.
    • Rank by Stake: Indicates the rank of each game based on the total amount staked
    • Total Times Recommended: Shows the number of times the game was recommended to players within the selected time period (recommended in any Rank, regardless of your filter).
    • Number of times recommended within the selected rank: Shows the number of times the game was recommended to players within the selected time period and the Ranks filtered

    Interpreting the Data

    • High Rank & High Stake: Games that rank high in both recommendation frequency and stake amount (e.g., Game 1001) indicate popular titles that drive significant player spending. These are core games for engagement.
    • High Recommendation but Lower Stake: Games that are frequently recommended but show a lower stake amount might indicate good visibility but limited appeal in terms of high stakes.
    • Optimising Recommendations: Use these insights to adjust recommendation strategies. For example, frequently recommended games with lower stakes may benefit from promotional boosts to increase player interest and spending.

    Best Practices for Using This Dashboard

    • Focus on Top Performers: Identify the highest-performing games and ensure they continue to receive prominent placement in recommendations.
    • Test New Games: Monitor recently added games and see how often they appear in recommendations versus established titles.