Skip to main content

Simple Gaming Recommendations

Blair Matheson
  • Updated

The Simple Gaming Recommendations feature recommends one of multiple personalization types of game recommendations based on user behavior and preference models.

Functionality

  • Identifies active users based on their gaming activity.
  • Uses a data-driven approach to suggest relevant games users may enjoy.
  • Recommends a variety of games tailored to user preferences based on behavioral models:
    • Favorite game
    • Recommended game
    • Popular game

How it Works

  1. Identify Audience:
    • Select users who have played a minimum number of unique games in the past n_days_lookback days.
    • Exclude users who have already played today to focus on new engagement opportunities.
    • Optionally include new players who registered in the last n_days_lookback days.
  2. Determine Recommended Games: Analyze user gameplay patterns and engagement scores; use predictive models to recommend a game aligned with the user’s preferences.
  3. Determine Favorite Games: Analyze gameplay history and engagement scores; extract each user’s highest‑ranked game.
  4. Determine Popular Games: Identify the most played games from recent trends, filter by category if applicable, and select the top game by unique players.
  5. Personalized Recommendations: Based on the chosen recommendation type, deliver one game recommendation per user, including game codes, names, and images.

Configurable Parameters & Terminology

  • Activity Window: Number of days to analyze for gaming activity.
  • Min Games Played: Minimum number of unique games played to qualify as an active user.
  • Trending Window: Number of days to look back for trending games.
  • Game Category: Filter for game categories to recommend.
  • Include New Players?: Option to include recently joined users.
  • Recommendation Model: options for game recommendation types.

Outputs & Data Points

When a recommendation is generated, the system produces the following outputs:

  • userid: Identifier of the recipient
  • game_code: Game identifier
  • game_name: Name of recommended game
  • imageurl: Recommended game’s image URL (JSON format for optiXtra)

Data Integration Requirements

For proper operation, this feature integrates with the following data sources:

  • GAME_PLAY events (Mandatory): Key fields: userid, game_code, game_name, imageurl, event_datetime.
  • REGISTRATION events (Mandatory): Key fields: userid, event_datetime.
  • Inventory (Mandatory): Key fields: game_name, gamecode, imageurl.
  • Reference File (Mandatory): Key fields: game_name, gamecode, game_category.

Related articles