Opendatabay APP

Gaming Behaviour Prediction Dataset

Data Science and Analytics

Tags and Keywords

Gaming

Player

Engagement

Retention

Behaviour

Trusted By
Trusted by company1Trusted by company2Trusted by company3
Gaming Behaviour Prediction Dataset Dataset on Opendatabay data marketplace

"No reviews yet"

Free

About

This dataset captures key metrics and demographics related to player behaviour in online gaming environments. It includes variables such as player demographics, game-specific details, and engagement metrics. The dataset's primary purpose is to explore player retention, with a target variable, 'EngagementLevel', categorised into 'High', 'Medium', or 'Low' levels of engagement. It is a synthetic dataset, ideal for educational purposes and suitable for various data science and machine learning projects, particularly for developing models to predict player engagement.

Columns

  • PlayerID: A unique identifier assigned to each player in the dataset. (Range: 9,000 to 49,000, Mean: 29,000, Valid entries: 40,000)
  • Age: The age of the player. (Range: 15 to 49 years, Mean: 32 years, Valid entries: 40,000)
  • Gender: The reported gender of the player, with categories including Male (60%) and Female (40%). (Valid entries: 40,000)
  • Location: The geographic location of the player, including USA (40%), Europe (30%), and Other regions (30%). (Valid entries: 40,000)
  • GameGenre: The genre of the game the player is engaged in, such as Sports (20%), Action (20%), and Other genres (60%). (Valid entries: 40,000)
  • PlayTimeHours: The average number of hours a player spends playing per session. (Range: 0 to 24 hours, Mean: 12 hours, Valid entries: 40,000)
  • InGamePurchases: A binary indicator (0 = No, 1 = Yes) showing whether the player makes in-game purchases. (Mean: 0.2, Valid entries: 40,000)
  • GameDifficulty: The difficulty level of the game, categorised as Easy (50%), Medium (30%), or Other (20%). (Valid entries: 40,000)
  • SessionsPerWeek: The number of gaming sessions a player engages in per week. (Range: 0 to 19 sessions, Mean: 9.47 sessions, Valid entries: 40,000)
  • AvgSessionDurationMinutes: The average duration of each gaming session in minutes. (Range: 10 to 179 minutes, Mean: 94.8 minutes, Valid entries: 40,000)
  • PlayerLevel: The current level attained by the player within the game. (Range: 1 to 99 levels, Mean: 49.7 levels, Valid entries: 40,000)
  • AchievementsUnlocked: The total number of achievements unlocked by the player. (Range: 0 to 49 achievements, Mean: 24.5 achievements, Valid entries: 40,000)
  • EngagementLevel: The target variable indicating player engagement, categorised as 'High' (26%), 'Medium' (48%), or 'Low' (26%). (Valid entries: 40,000)

Distribution

The dataset is provided in a CSV format, named online_gaming_behavior_dataset.csv. It has a file size of 2.85 MB and consists of 13 columns. The dataset contains 40,000 records.

Usage

This dataset is well-suited for a variety of analytical tasks and machine learning applications. It can be used for predictive modelling of player retention and engagement patterns, and for analysing factors that influence player behaviour and game performance. It is also valuable for optimising game design, refining marketing strategies, and enhancing the overall player experience. Researchers can utilise it for studies in gaming analytics, while data scientists and machine learning engineers will find it beneficial for developing and testing models related to player dynamics.

Coverage

The dataset covers player demographics including Age (ranging from 15 to 49 years) and Gender (60% Male, 40% Female). Geographic scope is indicated by Location data, with players predominantly from the USA (40%) and Europe (30%), alongside other regions (30%). A specific time range for the data collection is not detailed, but engagement metrics represent average patterns.

License

Attribution 4.0 International (CC BY 4.0)

Who Can Use It

This dataset is intended for data scientists, machine learning engineers, game developers, marketing strategists, and academic researchers. It is particularly useful for those looking to:
  • Develop machine learning models for predicting player engagement and retention.
  • Analyse the impact of various game features and player demographics on engagement.
  • Inform decisions related to game design and marketing efforts.
  • Conduct academic research in the field of gaming analytics and user behaviour.

Dataset Name Suggestions

  • Online Gaming Player Engagement Dataset
  • Gaming Behaviour Prediction Dataset
  • Player Retention Analytics Data
  • Online Game Metrics Dataset
  • Gaming Session & Engagement Data

Attributes

Listing Stats

VIEWS

3

DOWNLOADS

1

LISTED

22/07/2025

REGION

GLOBAL

Universal Data Quality Score Logo UDQSQUALITY

5 / 5

VERSION

1.0

Free

Download Dataset in CSV Format