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

# Introduction

> Learn what OIPD is and how its four core objects work together to extract market-implied probability distributions from options chains.

OIPD (Options Implied Probability Distribution) is a Python library that turns raw options chain data into risk-neutral probability distributions over future asset prices. It fits SVI volatility smiles to listed options, links maturities with total-variance interpolation, and transforms the fitted volatility into a full price-implied distribution.

## Capabilities

OIPD provides two tightly integrated capabilities in a single library:

* **Probability extraction** — compute the full risk-neutral PDF and CDF over future asset prices, query tail probabilities (`prob_below`, `prob_above`), quantiles, skew, and kurtosis.
* **Volatility modeling** — fit single-expiry SVI smiles and multi-expiry total-variance surfaces for pricing and risk work, evaluate implied volatilities, price options, and compute Greeks.

## Core objects

OIPD organises everything around four classes, arranged by scope (single expiry vs. a time horizon) and layer (volatility vs. probability):

| Scope               | Volatility layer | Probability layer |
| ------------------- | ---------------- | ----------------- |
| Single future date  | `VolCurve`       | `ProbCurve`       |
| Future time horizon | `VolSurface`     | `ProbSurface`     |

Use `VolCurve` and `ProbCurve` when you care about one expiry date. Use `VolSurface` and `ProbSurface` when you want to reason across multiple maturities simultaneously — for example, to build a probability fan chart over the next 12 months.

## Workflow

OIPD is similar to a scikit-learn workflow. Every OIPD estimator follows the same three-step lifecycle:

1. **Configure** — instantiate the estimator object with any model parameters.
2. **Fit** — call `.fit(chain, market)` (or the convenience factory `from_chain`) to calibrate the model to your data.
3. **Query** — call methods on the fitted object to extract implied volatilities, probabilities, quantiles, plots, and diagnostics.

You never need to manage intermediate state manually; each fitted object is self-contained and queryable.

## Next steps

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Compute your first market-implied probability distribution in under five minutes using live options data from yfinance.
  </Card>

  <Card title="Installation" icon="download" href="/installation">
    Install OIPD with pip and understand the standard vs. minimal dependency sets.
  </Card>

  <Card title="Core concepts" icon="book" href="/concepts/mental-model">
    Dive deeper into the four core objects, the volatility-to-probability pipeline, and the warning diagnostics system.
  </Card>

  <Card title="API reference" icon="code" href="/reference/prob-curve">
    Full reference for every public method on OIPD's classes, including parameters, return types, and examples.
  </Card>
</CardGroup>