Bot Score

The Bot Score API OpenAPI specification is available for download here. Explore the API endpoints here.

The Bot Score API is a machine-learning model from Sportradar's Insight Tech Services, designed to identify and evaluate accounts exhibiting automated betting behaviours. It returns a probabilistic score that indicates the likelihood of a customer being a bot – an account run by scripts or automated tools rather than a human.

Bots can exploit market timing, abuse standard validation, and distort betting dynamics. The Bot Score model helps operators proactively identify these risks and maintain a level playing field for legitimate users.

What it does

The Bot Score model assigns a score between 0.01 and 1.00 to each profiled account, reflecting the probability that the account is not human-operated. It uses behavioural and ticket-level indicators to detect automation patterns, with a particular focus on the pre-match betting closing odds.

In addition to closing odds, the model considers stake size, frequency of bet placements, and other behavioural anomalies. A high score signals that the account may be programmatic or fraudulent in nature.

When it’s triggered

The Bot Score model runs on a regular cadence, profiling accounts with sufficient historical data. It targets active players with recent betting activity, especially those placing numerous bets in a structured or high-frequency manner. Once the model evaluates an account, its score becomes available via API.

Input requirements

To access the Bot Score through the API, the following parameters are required:

• bookmaker – the assigned Insight Tech or MTS bookmaker ID

• sub-bookmaker – the sub-entity of the bookmaker (use * to retrieve all sub-entities)

• customer - customer's uniqueID

Some endpoints also support range filters (lower, higher) or pagination using startKey. A full breakdown of all accepted parameters is available in the Endpoints section.

Output schema

A typical response includes the list of items, and each object under responseItem contains:

• srcId: compound source identifier for internal tracking

• bscore: A decimal value between 0.00 and 1.00 representing the Bot Score

• id: entity identifier

Interpretation guidance

• Scores above 0.90 generally indicate high confidence that an account exhibits automated behaviour and may require further investigation or restriction.

• Scores between 0.70 and 0.89 suggest moderate risk, potentially warranting monitoring.

• Scores below 0.70 are typical of human-like betting patterns and are generally low risk.

• If a score is missing, it may indicate a newly created or inactive account with insufficient historical data for evaluation.

The Bot Score model is often used in tandem with other Insight Tech Services models like Late Bet Score or Customer Confidence Factor (CCF) to build a comprehensive profile of player behaviour.

Operators can configure automated responses or embed the scores into monitoring dashboards to support fraud prevention, market fairness, and regulatory compliance.

For integration details, schema definitions, and implementation tips, refer to the Bot Score API .