> For the complete documentation index, see [llms.txt](https://docs.sportradar.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.sportradar.com/itservices/models/event-profiling-api/faqs.md).

# FAQs

<figure><img src="/files/Tygvy3qu5wzIzgNnXdtq" alt=""><figcaption></figcaption></figure>

### ❓ What is the Event Profiling API?

The Event Profiling API is an AI-driven service within Sportradar’s Insight Tech Services. It provides real-time recommendations for Live Time Delay (LTD) and Event Rating for active events, enabling data-driven risk and liability management during live betting.

### ❓ What is the difference between `ltd` and `sLtd`?

* `ltd` is the static live time delay value derived from Unified Odds feed types (TV, umpire, venue, etc.).
* `sLtd` is the AI-generated suggested delay calculated by the Event Data Latency (EDL) model, dynamically adjusted based on historical performance and event-specific dynamics.

Use `sLtd` and `ltd` to optimise latency settings and reduce exposure.

### ❓ What is `sEr`?

`sEr` is the Suggested Event Rating, on a scale from 1 (high risk) to 10 (low risk). It helps operators:

* Identify volatile or low-confidence events
* Adjust bet validation settings
* Apply stricter business rules on higher-risk matches

### ❓ When does the API provide data?

* Once the first live bet is placed on an event, suggested LTD model outputs become available.
* The API evaluates and updates scores in real time throughout the match.

### ❓ How can I use the API effectively?

Use it:

* Before or during a match to assess event-level risk
* As input for real-time validation systems
* In combination with player-level scoring models (LBS, sCCF, Bot Score)
* To fine-tune cash-out, staking, or bet rejection logic during high-risk matches

### ❓ What does a high `sEr` value mean?

A score near 10 indicates:

* Higher confidence in data and coverage
* Lower volatility and market manipulation risk
* Safer to accept larger bets or enable faster cash-outs

A score near 1 means:

* Riskier event (e.g. volatile, poor data, high variance)
* Consider applying limits, manual review, or delay enforcement

### ❓ Can I submit multiple events in one request?

Yes. Submit an array of event IDs to the `POST /fetch` endpoint to retrieve delay and rating data in bulk.

### ❓ What if the response contains null values?

This usually means:

* Incorrect path (sport/category/tournament/event combination).
* Event is not currently covered by Sportradar feeds.&#x20;

You can retry later or fall back to default configuration logic.

### ❓ What are the API rate limits?

| Limit Type      | Value            |
| --------------- | ---------------- |
| Requests/second | 10               |
| Daily quota     | 200,000 requests |
| Minute quota    | 500 requests     |

If you exceed the rate limit:

* You will receive `HTTP 429 Too Many Requests`
* Use exponential backoff for retries
* Keep request volumes efficient and cache results when possible

### ❓ How is this different from Tournament Profiling?

* Tournament Profiling gives average risk/delay settings for tournaments (macro-level)
* Event Profiling provides event-specific, real-time risk/delay settings (micro-level)

### ❓ Who can I contact for help?

For access issues, integration help, or data questions, contact:

* Your OAM
* Your assigned CI engineer
* Or submit a ticket via Sportradar support.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.sportradar.com/itservices/models/event-profiling-api/faqs.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
