oipd 2.0.4

Generate probability distributions on the future price of publicly traded securities using options data

Overview

OIPD computes the probabilities of an asset's future price as implied by the options market.

It does this by taking listed options data, fitting an arbitrage-free implied volatility surface, and then transforming that fitted object into a probability distribution over future asset prices. In practice, that provides two core capabilities in one library:

• Volatility modeling: fit single-expiry smiles and multi-expiry volatility surfaces, and compute greeks.
• Probability extraction: compute market-implied probability distributions, and distribution statistics.

Read the docs · Use the web interface

Quick install

The standard install includes the built-in yfinance data connection.

pip install oipd

One quick example

Fetch GameStop options across the next twelve months, fit a VolSurface, derive a ProbSurface, and plot the fan chart.

import matplotlib.pyplot as plt

from oipd import MarketInputs, VolSurface, sources

ticker = "GME"
chain, snapshot = sources.fetch_chain(
    ticker,
    horizon="12m",  # fetch all listed expiries inside the next 12 months
)

market = MarketInputs(
    valuation_date=snapshot.asof,
    underlying_price=snapshot.underlying_price,
    risk_free_rate=0.04,
)

vol_surface = VolSurface().fit(chain, market)
surface = vol_surface.implied_distribution()

fig = surface.plot_fan()
plt.show()

surface.plot_fan() visualizes the market-implied price distribution across fitted option expiries.

You can also take one expiry from the surface and query it as a ProbCurve.

curve = surface.slice(surface.expiries[-1])  # take the last expiry

print(curve.prob_below(25))  # P(GME price < 25) at that expiry
print(curve.quantile(0.50))  # median implied price at that expiry

fig = curve.plot()
fig.axes[0].set_xlim(0, 100)
plt.show()

A surface slice returns a ProbCurve, so you can inspect one expiry as a standalone probability distribution.

Example Notebooks

See more examples for demos.

Community

Pull requests welcome! Reach out on GitHub issues to discuss design choices.

Join the Discord community to share ideas, discuss strategies, and get support. Message me with your feature requests, and let me know how you use this.

Contributors

Thanks to everyone who has contributed code:

And special thanks for support on theory, implementation, or advisory:

• NewMark Risk
• integral-alpha
• Vivek Rao, Jannic H., Chun H. H., and Melanie C.
• and others who prefer to go unnamed