Implementation of On-Line Moving Average Reversion (OLMAR) More...

Inheritance diagram for QuantConnect.Algorithm.Framework.Portfolio.MeanReversionPortfolioConstructionModel:

Public Member Functions
	MeanReversionPortfolioConstructionModel (IDateRule rebalancingDateRules, PortfolioBias portfolioBias=PortfolioBias.LongShort, decimal reversionThreshold=1, int windowSize=20, Resolution resolution=Resolution.Daily)
	Initializes a new instance of the MeanReversionPortfolioConstructionModel class More...

	MeanReversionPortfolioConstructionModel (Resolution rebalanceResolution=Resolution.Daily, PortfolioBias portfolioBias=PortfolioBias.LongShort, decimal reversionThreshold=1, int windowSize=20, Resolution resolution=Resolution.Daily)
	Initializes a new instance of the MeanReversionPortfolioConstructionModel class More...

	MeanReversionPortfolioConstructionModel (TimeSpan timeSpan, PortfolioBias portfolioBias=PortfolioBias.LongShort, decimal reversionThreshold=1, int windowSize=20, Resolution resolution=Resolution.Daily)
	Initializes a new instance of the MeanReversionPortfolioConstructionModel class More...

	MeanReversionPortfolioConstructionModel (PyObject rebalance, PortfolioBias portfolioBias=PortfolioBias.LongShort, decimal reversionThreshold=1, int windowSize=20, Resolution resolution=Resolution.Daily)
	Initializes a new instance of the MeanReversionPortfolioConstructionModel class More...

	MeanReversionPortfolioConstructionModel (Func< DateTime, DateTime > rebalancingFunc, PortfolioBias portfolioBias=PortfolioBias.LongShort, decimal reversionThreshold=1, int windowSize=20, Resolution resolution=Resolution.Daily)
	Initializes a new instance of the MeanReversionPortfolioConstructionModel class More...

	MeanReversionPortfolioConstructionModel (Func< DateTime, DateTime?> rebalancingFunc, PortfolioBias portfolioBias=PortfolioBias.LongShort, decimal reversionThreshold=1, int windowSize=20, Resolution resolution=Resolution.Daily)
	Initializes a new instance of the MeanReversionPortfolioConstructionModel class More...

override void	OnSecuritiesChanged (QCAlgorithm algorithm, SecurityChanges changes)
	Event fired each time the we add/remove securities from the data feed More...

Public Member Functions inherited from QuantConnect.Algorithm.Framework.Portfolio.PortfolioConstructionModel
	PortfolioConstructionModel (Func< DateTime, DateTime?> rebalancingFunc)
	Initialize a new instance of PortfolioConstructionModel More...

	PortfolioConstructionModel (Func< DateTime, DateTime > rebalancingFunc=null)
	Initialize a new instance of PortfolioConstructionModel More...

virtual IEnumerable< IPortfolioTarget >	CreateTargets (QCAlgorithm algorithm, Insight[] insights)
	Create portfolio targets from the specified insights More...

Static Public Member Functions
static IEnumerable< double >	CumulativeSum (IEnumerable< double > sequence)
	Cumulative Sum of a given sequence More...

static double[]	SimplexProjection (IEnumerable< double > vector, double total=1)
	Normalize the updated portfolio into weight vector: v_{t+1} = arg min \|\| v - v_{t+1} \|\| ^ 2 More...

Protected Member Functions
override Dictionary< Insight, double >	DetermineTargetPercent (List< Insight > activeInsights)
	Will determine the target percent for each insight More...

virtual double[]	GetPriceRelatives (List< Insight > activeInsights)
	Get price relatives with reference level of SMA More...

Protected Member Functions inherited from QuantConnect.Algorithm.Framework.Portfolio.PortfolioConstructionModel
void	SetPythonWrapper (PortfolioConstructionModelPythonWrapper pythonWrapper)
	Used to set the PortfolioConstructionModelPythonWrapper instance if any More...

virtual List< Insight >	GetTargetInsights ()
	Gets the target insights to calculate a portfolio target percent for More...

virtual bool	ShouldCreateTargetForInsight (Insight insight)
	Method that will determine if the portfolio construction model should create a target for this insight More...

void	SetRebalancingFunc (PyObject rebalance)
	Python helper method to set the rebalancing function. This is required due to a python net limitation not being able to use the base type constructor, and also because when python algorithms use C# portfolio construction models, it can't convert python methods into func nor resolve the correct constructor for the date rules, timespan parameter. For performance we prefer python algorithms using the C# implementation More...

virtual bool	IsRebalanceDue (Insight[] insights, DateTime algorithmUtc)
	Determines if the portfolio should be rebalanced base on the provided rebalancing func, if any security change have been taken place or if an insight has expired or a new insight arrived If the rebalancing function has not been provided will return true. More...

void	RefreshRebalance (DateTime algorithmUtc)
	Refresh the next rebalance time and clears the security changes flag More...

Additional Inherited Members
Static Protected Member Functions inherited from QuantConnect.Algorithm.Framework.Portfolio.PortfolioConstructionModel
static Insight[]	FilterInvalidInsightMagnitude (IAlgorithm algorithm, Insight[] insights)
	Helper class that can be used by the different IPortfolioConstructionModel implementations to filter Insight instances with an invalid Insight.Magnitude value based on the IAlgorithmSettings More...

Protected Attributes inherited from QuantConnect.Algorithm.Framework.Portfolio.PortfolioConstructionModel
PortfolioConstructionModelPythonWrapper	PythonWrapper
	This is required due to a limitation in PythonNet to resolved overriden methods. When Python calls a C# method that calls a method that's overriden in python it won't run the python implementation unless the call is performed through python too. More...

Properties inherited from QuantConnect.Algorithm.Framework.Portfolio.PortfolioConstructionModel
virtual bool	RebalanceOnSecurityChanges = true `[get, set]`
	True if should rebalance portfolio on security changes. True by default More...

virtual bool	RebalanceOnInsightChanges = true `[get, set]`
	True if should rebalance portfolio on new insights or expiration of insights. True by default More...

IAlgorithm	Algorithm `[get]`
	The algorithm instance More...

Detailed Description

Implementation of On-Line Moving Average Reversion (OLMAR)

Li, B., Hoi, S. C. (2012). On-line portfolio selection with moving average reversion. arXiv preprint arXiv:1206.4626. Available at https://arxiv.org/ftp/arxiv/papers/1206/1206.4626.pdf

Using windowSize = 1 => Passive Aggressive Mean Reversion (PAMR) Portfolio

Definition at line 35 of file MeanReversionPortfolioConstructionModel.cs.

Constructor & Destructor Documentation

◆ MeanReversionPortfolioConstructionModel() [1/6]

QuantConnect.Algorithm.Framework.Portfolio.MeanReversionPortfolioConstructionModel.MeanReversionPortfolioConstructionModel	(	IDateRule	rebalancingDateRules,
		PortfolioBias	portfolioBias = `PortfolioBias.LongShort`,
		decimal	reversionThreshold = `1`,
		int	windowSize = `20`,
		Resolution	resolution = `Resolution.Daily`
	)

Initializes a new instance of the MeanReversionPortfolioConstructionModel class

Parameters

rebalancingDateRules	The date rules used to define the next expected rebalance time in UTC
portfolioBias	Specifies the bias of the portfolio (Short, Long/Short, Long)
reversionThreshold	Reversion threshold
windowSize	Window size of mean price
resolution	The resolution of the history price and rebalancing

Definition at line 53 of file MeanReversionPortfolioConstructionModel.cs.

◆ MeanReversionPortfolioConstructionModel() [2/6]

QuantConnect.Algorithm.Framework.Portfolio.MeanReversionPortfolioConstructionModel.MeanReversionPortfolioConstructionModel	(	Resolution	rebalanceResolution = `Resolution.Daily`,
		PortfolioBias	portfolioBias = `PortfolioBias.LongShort`,
		decimal	reversionThreshold = `1`,
		int	windowSize = `20`,
		Resolution	resolution = `Resolution.Daily`
	)

Initializes a new instance of the MeanReversionPortfolioConstructionModel class

Parameters

rebalanceResolution	Rebalancing frequency
portfolioBias	Specifies the bias of the portfolio (Short, Long/Short, Long)
reversionThreshold	Reversion threshold
windowSize	Window size of mean price
resolution	The resolution of the history price and rebalancing

Definition at line 70 of file MeanReversionPortfolioConstructionModel.cs.

◆ MeanReversionPortfolioConstructionModel() [3/6]

QuantConnect.Algorithm.Framework.Portfolio.MeanReversionPortfolioConstructionModel.MeanReversionPortfolioConstructionModel	(	TimeSpan	timeSpan,
		PortfolioBias	portfolioBias = `PortfolioBias.LongShort`,
		decimal	reversionThreshold = `1`,
		int	windowSize = `20`,
		Resolution	resolution = `Resolution.Daily`
	)

Initializes a new instance of the MeanReversionPortfolioConstructionModel class

Parameters

timeSpan	Rebalancing frequency
portfolioBias	Specifies the bias of the portfolio (Short, Long/Short, Long)
reversionThreshold	Reversion threshold
windowSize	Window size of mean price
resolution	The resolution of the history price and rebalancing

Definition at line 87 of file MeanReversionPortfolioConstructionModel.cs.

◆ MeanReversionPortfolioConstructionModel() [4/6]

QuantConnect.Algorithm.Framework.Portfolio.MeanReversionPortfolioConstructionModel.MeanReversionPortfolioConstructionModel	(	PyObject	rebalance,
		PortfolioBias	portfolioBias = `PortfolioBias.LongShort`,
		decimal	reversionThreshold = `1`,
		int	windowSize = `20`,
		Resolution	resolution = `Resolution.Daily`
	)

Initializes a new instance of the MeanReversionPortfolioConstructionModel class

Parameters

rebalance	Rebalancing func or if a date rule, timedelta will be converted into func. For a given algorithm UTC DateTime the func returns the next expected rebalance time or null if unknown, in which case the function will be called again in the next loop. Returning current time will trigger rebalance. If null will be ignored
portfolioBias	Specifies the bias of the portfolio (Short, Long/Short, Long)
reversionThreshold	Reversion threshold
windowSize	Window size of mean price
resolution	The resolution of the history price and rebalancing

Definition at line 107 of file MeanReversionPortfolioConstructionModel.cs.

Here is the call graph for this function:

◆ MeanReversionPortfolioConstructionModel() [5/6]

QuantConnect.Algorithm.Framework.Portfolio.MeanReversionPortfolioConstructionModel.MeanReversionPortfolioConstructionModel	(	Func< DateTime, DateTime >	rebalancingFunc,
		PortfolioBias	portfolioBias = `PortfolioBias.LongShort`,
		decimal	reversionThreshold = `1`,
		int	windowSize = `20`,
		Resolution	resolution = `Resolution.Daily`
	)

Initializes a new instance of the MeanReversionPortfolioConstructionModel class

Parameters

rebalancingFunc For a given algorithm UTC DateTime returns the next expected rebalance UTC time. Returning current time will trigger rebalance. If null will be ignored

will trigger rebalance. If null will be ignored

Parameters

portfolioBias	Specifies the bias of the portfolio (Short, Long/Short, Long)
reversionThreshold	Reversion threshold
windowSize	Window size of mean price
resolution	The resolution of the history price and rebalancing

Definition at line 127 of file MeanReversionPortfolioConstructionModel.cs.

◆ MeanReversionPortfolioConstructionModel() [6/6]

QuantConnect.Algorithm.Framework.Portfolio.MeanReversionPortfolioConstructionModel.MeanReversionPortfolioConstructionModel	(	Func< DateTime, DateTime?>	rebalancingFunc,
		PortfolioBias	portfolioBias = `PortfolioBias.LongShort`,
		decimal	reversionThreshold = `1`,
		int	windowSize = `20`,
		Resolution	resolution = `Resolution.Daily`
	)

Initializes a new instance of the MeanReversionPortfolioConstructionModel class

Parameters

rebalancingFunc	For a given algorithm UTC DateTime returns the next expected rebalance time or null if unknown, in which case the function will be called again in the next loop. Returning current time will trigger rebalance.
portfolioBias	Specifies the bias of the portfolio (Short, Long/Short, Long)
reversionThreshold	Reversion threshold
windowSize	Window size of mean price
resolution	The resolution of the history price and rebalancing

Definition at line 147 of file MeanReversionPortfolioConstructionModel.cs.

Member Function Documentation

◆ DetermineTargetPercent()

override Dictionary<Insight, double> QuantConnect.Algorithm.Framework.Portfolio.MeanReversionPortfolioConstructionModel.DetermineTargetPercent ( List< Insight > activeInsights )

protectedvirtual

Will determine the target percent for each insight

Parameters

activeInsights list of active insights

<return>dictionary of insight and respective target weight</return>

Reimplemented from QuantConnect.Algorithm.Framework.Portfolio.PortfolioConstructionModel.

Definition at line 169 of file MeanReversionPortfolioConstructionModel.cs.

Here is the call graph for this function:

◆ GetPriceRelatives()

virtual double [] QuantConnect.Algorithm.Framework.Portfolio.MeanReversionPortfolioConstructionModel.GetPriceRelatives ( List< Insight > activeInsights )

protectedvirtual

Get price relatives with reference level of SMA

Parameters

activeInsights list of active insights

<return>array of price relatives vector</return>

Definition at line 231 of file MeanReversionPortfolioConstructionModel.cs.

Here is the caller graph for this function:

◆ OnSecuritiesChanged()

override void QuantConnect.Algorithm.Framework.Portfolio.MeanReversionPortfolioConstructionModel.OnSecuritiesChanged	(	QCAlgorithm	algorithm,
		SecurityChanges	changes
	)

virtual

Event fired each time the we add/remove securities from the data feed

Parameters

algorithm	The algorithm instance that experienced the change in securities
changes	The security additions and removals from the algorithm

Reimplemented from QuantConnect.Algorithm.Framework.Portfolio.PortfolioConstructionModel.

Definition at line 256 of file MeanReversionPortfolioConstructionModel.cs.

◆ CumulativeSum()

static IEnumerable<double> QuantConnect.Algorithm.Framework.Portfolio.MeanReversionPortfolioConstructionModel.CumulativeSum ( IEnumerable< double > sequence )

static

Cumulative Sum of a given sequence

Parameters

sequence sequence to obtain cumulative sum

<return>cumulative sum</return>

Definition at line 284 of file MeanReversionPortfolioConstructionModel.cs.

Here is the caller graph for this function:

◆ SimplexProjection()

static double [] QuantConnect.Algorithm.Framework.Portfolio.MeanReversionPortfolioConstructionModel.SimplexProjection	(	IEnumerable< double >	vector,
		double	total = `1`
	)

static

Normalize the updated portfolio into weight vector: v_{t+1} = arg min || v - v_{t+1} || ^ 2

<remark>Duchi, J., Shalev-Shwartz, S., Singer, Y., and Chandra, T. (2008, July). Efficient projections onto the l1-ball for learning in high dimensions. In Proceedings of the 25th international conference on Machine learning (pp. 272-279).</remark>

Parameters

vector	unnormalized weight vector
total	regulator, default to be 1, making it a probabilistic simplex

<return>normalized weight vector</return>

Definition at line 304 of file MeanReversionPortfolioConstructionModel.cs.

Here is the call graph for this function:

Here is the caller graph for this function:

The documentation for this class was generated from the following file:

Algorithm.Framework/Portfolio/MeanReversionPortfolioConstructionModel.cs

Public Member Functions

Static Public Member Functions

Protected Member Functions

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ MeanReversionPortfolioConstructionModel() [1/6]

◆ MeanReversionPortfolioConstructionModel() [2/6]

◆ MeanReversionPortfolioConstructionModel() [3/6]

◆ MeanReversionPortfolioConstructionModel() [4/6]

◆ MeanReversionPortfolioConstructionModel() [5/6]

◆ MeanReversionPortfolioConstructionModel() [6/6]

Member Function Documentation

◆ DetermineTargetPercent()

◆ GetPriceRelatives()

◆ OnSecuritiesChanged()

◆ CumulativeSum()

◆ SimplexProjection()