PortfolioEffectHFT (version 1.7)

optimization_forecast: Porfolio Optimization - Set Optimization Forecast

Description

Sets user-defined forecasted values for a given metric and returns modified optimizer object. By default value of the metric at time "t" is used as a forecast for "t+1".

Usage

optimization_forecast(optimizer, 				   metricType,
				   forecast)

Arguments

optimizer

Optimizer object created using optimization_goal( ) function

metricType

Choose forecast metric type: "Beta" - position beta, "Variance" - position variance, "ExpReturn" - position expected return, "Cumulant3" - position 3-th cumulant, "Cumulant4" - position 4-th cumulant

forecast

Object of class metric-class( ) or forecast-class( )

Value

Examples

## Not run: 
# dateStart = "2014-11-17 09:30:00"
# dateEnd = "2014-12-17 16:00:00"
# portfolio=portfolio_create(dateStart,dateEnd)
# 
# # Add position AAPL and GOOG to portfolio
# positionAAPL=position_add(portfolio,"AAPL",100)
# positionGOOG=position_add(portfolio,"GOOG",200)
# portfolio_settings(portfolio,inputSamplingInterval='30m',resultsSamplingInterval='1d')
# 
# forecastVarianceAAPL=forecast_builder(variance(positionAAPL),model="HAR",step ='1d')
# forecastVarianceGOOG=forecast_builder(variance(positionGOOG),model="HAR",step ='1d')
# 
# optimizer=optimization_goal(variance(portfolio),"min")
# optimizer=optimization_constraint(optimizer,log_return(portfolio),">=",0)
# optimizer=optimization_forecast(optimizer, "Variance", forecastVarianceAAPL)
# optimizer=optimization_forecast(optimizer, "Variance", forecastVarianceGOOG)
# optimalPortfolioWithHAR=optimization_run(optimizer)
# 
# optimizer=optimization_goal(variance(portfolio),"min")
# optimizer=optimization_constraint(optimizer,log_return(portfolio),">=",0)
# optimalPortfolioWithoutHAR=optimization_run(optimizer)
# 
# plot(variance(optimalPortfolioWithHAR),variance(optimalPortfolioWithoutHAR),title="Variance",
# legend=c("With HAR Forecast","Without HAR Forecast"))
# ## End(Not run)