book
Checkout our new book! Hands on AI Trading with Python, QuantConnect, and AWS Learn More arrow

ExtractAlpha

Cross Asset Model

Introduction

The Cross Asset Model by ExtractAlpha provides stock scoring values based on the trading activity in the Options market. Since the Options market has a higher proportion of institutional traders than the Equities market, the Options market is composed of investors who are more informed and information-driven on average. The data covers a dynamic universe of over 3,000 US Equities, starts in July 2005, and is delivered on a daily frequency. This dataset is created by feature engineering on the Options market put-call spread, volatility skewness, and volume.

This dataset depends on the US Equity Security Master dataset because the US Equity Security Master dataset contains information on splits, dividends, and symbol changes.

For more information about the Cross Asset Model dataset, including CLI commands and pricing, see the dataset listing.

About the Provider

ExtractAlpha was founded by Vinesh Jha in 2013 with the goal of providing alternative data for investors. ExtractAlpha's rigorously researched data sets and quantitative stock selection models leverage unique sources and analytical techniques, allowing users to gain an investment edge.

Getting Started

The following snippet demonstrates how to request data from the Cross Asset Model dataset:

Select Language: 
from QuantConnect.DataSource import *

self.aapl = self.add_equity("AAPL", Resolution.DAILY).symbol
self.dataset_symbol = self.add_data(ExtractAlphaCrossAssetModel, self.aapl).symbol

Data Summary

The following table describes the dataset properties:

PropertyValue
Start DateJuly 2005
Asset CoverageOver 3,000 US Equities
Data DensitySparse
ResolutionDaily
TimezoneUTC

Example Applications

The Cross Asset Model dataset by ExtractAlpha enables you to utilize Options market information to extract alpha. Examples include the following strategies:

  • Predicting price and volatility changes in Equities.
  • Signaling arbitrage opportunities between Options and underlying assets.
  • Using it as a stock selection indicator.

For more example algorithms, see Examples.

Data Point Attributes

The Cross Asset Model dataset provides ExtractAlphaCrossAssetModel objects, which have the following attributes:

ExtractAlphaCrossAssetModel Select Language:
    Spread component of the cross-asset model. This value is the percentile rank bounded between [1, 100]. The closer the value is to the upper bound, the more likely the stock will outperform according to this component.
  • spread: Int32
    • Skew component of the cross-asset model. This value is the percentile rank bounded between [1, 100]. The closer the value is to the upper bound, the more likely the stock will outperform according to this component.
  • skew: Int32
    • The volume component of the cross-asset model. This value is the percentile rank bounded between [1, 100]. The closer the value is to the upper bound, the more likely the stock will outperform according to this component.
  • volume_component: Int32
    • Cross-asset model score. This value is bounded between 1 and 100, with 100 signaling that the stock is most likely to outperform, according to this component.
  • score: Int32
    • Moving average of Cross-Asset model score. This value is the percentile rank bounded between [1, 100]. The closer the value is to the upper bound, the more likely the stock will outperform according to this component.
  • score_slow: Int32
    • The time that the data became available to the algorithm
  • end_time: DateTime
    • Market Data Type of this data - does it come in individual price packets or is it grouped into OHLC.
  • data_type: MarketDataType
    • True if this is a fill forward piece of data
  • is_fill_forward: bool
    • Current time marker of this data packet.
  • time: DateTime
    • Symbol representation for underlying Security
  • symbol: Symbol
    • Value representation of this data packet. All data requires a representative value for this moment in time. For streams of data this is the price now, for OHLC packets this is the closing price.
  • value: decimal
    • As this is a backtesting platform we'll provide an alias of value as price.
  • price: decimal

Requesting Data

To add Cross Asset Model data to your algorithm, call the add_data method. Save a reference to the dataset Symbol so you can access the data later in your algorithm.

Select Language: 
class ExtractAlphaCrossAssetModelDataAlgorithm(QCAlgorithm):
    def initialize(self) -> None:
        self.set_start_date(2019, 1, 1)
        self.set_end_date(2020, 6, 1)
        self.set_cash(100000)

        self.aapl = self.add_equity("AAPL", Resolution.DAILY).symbol
        self.dataset_symbol = self.add_data(ExtractAlphaCrossAssetModel, self.aapl).symbol

Accessing Data

To get the current Cross Asset Model data, index the current Slice with the dataset Symbol. Slice objects deliver unique events to your algorithm as they happen, but the Slice may not contain data for your dataset at every time step. To avoid issues, check if the Slice contains the data you want before you index it.

Select Language: 
def on_data(self, slice: Slice) -> None:
    if slice.contains_key(self.dataset_symbol):
        data_point = slice[self.dataset_symbol]
        self.log(f"{self.dataset_symbol} score at {slice.time}: {data_point.score}")

To iterate through all of the dataset objects in the current Slice, call the get method.

Select Language: 
def on_data(self, slice: Slice) -> None:
    for dataset_symbol, data_point in slice.get(ExtractAlphaCrossAssetModel).items():
        self.log(f"{dataset_symbol} score at {slice.time}: {data_point.score}")

Historical Data

To get historical Cross Asset Model data, call the history method with the dataset Symbol. If there is no data in the period you request, the history result is empty.

Select Language: 
# DataFrame
history_df = self.history(self.dataset_symbol, 100, Resolution.DAILY)

# Dataset objects
history_bars = self.history[ExtractAlphaCrossAssetModel](self.dataset_symbol, 100, Resolution.DAILY)

For more information about historical data, see History Requests.

Remove Subscriptions

To remove a subscription, call the remove_security method.

Select Language: 
self.remove_security(self.dataset_symbol)

If you subscribe to Cross Asset Model data for assets in a dynamic universe, remove the dataset subscription when the asset leaves your universe. To view a common design pattern, see Track Security Changes.

Example Applications

The Cross Asset Model dataset by ExtractAlpha enables you to utilize Options market information to extract alpha. Examples include the following strategies:

  • Predicting price and volatility changes in Equities.
  • Signaling arbitrage opportunities between Options and underlying assets.
  • Using it as a stock selection indicator.

For more example algorithms, see Examples.

You can also see our Videos. You can also get in touch with us via Discord.

Did you find this page helpful?

Contribute to the documentation: