> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mathfi.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# FAQ

> Frequently asked questions about MathFi.ai covering implementation time, supported problem types, data security, pricing, and API integration.

<AccordionGroup>
  <Accordion title="How long does implementation take?">
    Getting your first prediction typically takes under an hour once you have labelled CSV data ready. Training runs in minutes to a few hours depending on dataset size and complexity. Integration into existing workflows via the [REST API](/developers/api-overview) can be completed in a day by a developer familiar with HTTP.
  </Accordion>

  <Accordion title="What types of problems can MathFi.ai solve?">
    MathFi.ai is designed for **classification** problems on tabular data — both binary (e.g. fraud / not fraud) and multi-class (e.g. categorising outcomes into three or more groups). Regression problems can also be solved by converting continuous targets into discrete classes, as described in the [Training guide](/guides/training-guide). Real-world examples are available in the [Use Cases](/use-cases/healthcare) section.
  </Accordion>

  <Accordion title="How does pricing work?">
    Pricing is usage-based and tailored to your organisation's needs. [Request access](https://mathfi.ai/get-access/) or contact us at `support@mathfi.ai` to discuss pricing for your use case.
  </Accordion>

  <Accordion title="How technical do we need to be to use the API?">
    The [web dashboard](/quickstart) requires no coding — you upload a CSV, configure a few settings, and download predictions. To integrate via the [REST API](/developers/api-overview), basic familiarity with HTTP requests (e.g. `curl` or any HTTP client) is sufficient. A [Python SDK](/developers/python-sdk) is also available for teams that prefer a programmatic interface.
  </Accordion>

  <Accordion title="Does MathFi.ai integrate with our existing data infrastructure?">
    MathFi.ai uses CSV as its input and output format, which is compatible with virtually every data tool and database. The [REST API](/developers/api-overview) allows programmatic integration into existing pipelines, and the [Python SDK](/developers/python-sdk) makes it straightforward to embed MathFi.ai into Python-based workflows.
  </Accordion>

  <Accordion title="How is data security handled?">
    All datasets and trained models are stored securely in the cloud under your account. Access is protected by bearer token authentication with a 1-hour expiry. Contact `support@mathfi.ai` for questions about data retention, compliance, or enterprise security requirements.
  </Accordion>

  <Accordion title="What is the difference between training performance and test performance?">
    When you upload a labelled CSV, MathFi.ai automatically splits it: 90% is used for training and 10% is held back as an unseen test set. **Training performance** measures accuracy on the 90% the model learned from; **test performance** measures accuracy on the 10% it has never seen. A healthy model has training and test performance that are close together — a large gap signals overfitting. See the [Glossary](/glossary) for detailed metric definitions.
  </Accordion>

  <Accordion title="What does 'balanced-class learning' mean?">
    MathFi.ai evaluates model performance using a balanced metric that averages accuracy across each class, rather than counting overall correct predictions. This means a model must perform well on every class — not just the dominant one — which is critical for imbalanced datasets such as fraud detection or rare disease diagnosis. The platform automatically generates a balanced test set from your labelled data to ensure fair evaluation. See the [Glossary](/glossary) for the full formula.
  </Accordion>

  <Accordion title="Can analysts build models without data science training?">
    Yes. The [MathFi.ai dashboard](/quickstart) is designed for non-technical users: upload a labelled CSV, configure three plain-language settings, and the platform handles the rest. No knowledge of machine learning algorithms or statistics is required to run predictions. Data scientists can go deeper via [hyperparameter tuning](/guides/hyperparameter-tuning) and the [REST API](/developers/api-overview) when needed.
  </Accordion>

  <Accordion title="What are the three hyperparameters and what do they control?">
    MathFi.ai exposes exactly three hyperparameters:

    | Hyperparameter            | What it controls                                                                                                                                         | Default           |
    | ------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------- |
    | **Number of Buckets**     | How the dataset is divided into bins for training. A higher value can improve accuracy but may cause NaN predictions if set too high for small datasets. | 20 (range: 4–100) |
    | **Scaling Factor**        | The number of search cells explored during training — higher values search more broadly.                                                                 | 19 (range: 8–499) |
    | **Performance Threshold** | The minimum accuracy a model must achieve to be accepted as a champion.                                                                                  | 0.8 (range: 0–1)  |

    See the [Hyperparameter tuning guide](/guides/hyperparameter-tuning) for a step-by-step approach to optimising these values.
  </Accordion>
</AccordionGroup>