# Machine Learning with Tensor Flow

One of the issues ORAO was created to solve is earlier oracle platforms' reliance on reputation systems that trust data providers until they are actually caught supplying false information. While these systems do require providers to stake tokens which they may lose, there is always the risk of an attacker who invests some time into securing a good reputation, then lies in wait for an opportunity to trick for example a smart contract into making the wrong decision, allowing the attacker to steal funds of greater value than the stake they lose as a penalty for lying.

ORAO's solution is the introduction of Machine Learning. Using TensorFlow we are able to maintain neural nets that calculate trust scores based in part on past performance, but also on the trustworthiness of the data provided on its own merit, judged against a backdrop of similar data provided in the past, both by that particular data provider and recent data provided by others.

ORAO's neural nets are initially trained by our developers, using historical data and trusted sources. This allows the neural nets to rate data providers fairly from day 1, including providers for new Data Protocols who may not yet have competitors. Note that this is not an oracle service provided by ORAO itself, it merely serves as a backbone for ensuring reliability and trust on a platform where new Data Protocols are expected to to appear over time.


---

# Agent Instructions: 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://wiki.orao.network/the-orao-implementation/machine-learning-with-tensor-flow.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.