org.akutan.optimization
Class InteriorPointsReturn

java.lang.Object
  extended by org.akutan.optimization.InteriorPointsSolver
      extended by org.akutan.optimization.InteriorPointsReturn
All Implemented Interfaces:
Solver

public class InteriorPointsReturn
extends InteriorPointsSolver
implements Solver


Field Summary
 
Fields inherited from class org.akutan.optimization.InteriorPointsSolver
_er, _path, _savePath, _V, df
 
Constructor Summary
InteriorPointsReturn(cern.colt.matrix.DoubleMatrix1D er, cern.colt.matrix.DoubleMatrix2D V)
          Constructs
 
Method Summary
 java.util.List<SolvedPoint> solve(java.util.List<Constraint> extraConstraints, org.akutan.optimization.ProgressIndicator progress)
          Given a list of additional constraints (beyond budget and no shorts) solves for the list of points along the efficient frontier by fixing the return and solving for the minimal variance portfolio at each return level.
 cern.colt.matrix.DoubleMatrix1D solveForReturn(double _er_step, java.util.List<Constraint> extraConstraints)
          Solves the problem for the asset weights which generate the return specified while minimizing the objective function, which here is the variance of the solution portfolio.
 
Methods inherited from class org.akutan.optimization.InteriorPointsSolver
addPoint, algorithm, computeAlpha, formatOutput, generate_b, generate_d, getEqualityConstraints, getInequalityConstraints, initialGuess, make2D, maxReturn, prettyPrint, savePath, solvePoint
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Constructor Detail

InteriorPointsReturn

public InteriorPointsReturn(cern.colt.matrix.DoubleMatrix1D er,
                            cern.colt.matrix.DoubleMatrix2D V)
Constructs

Parameters:
er - Vector of expected returns for the assets
V - Matrix of asset covariances
Method Detail

solve

public java.util.List<SolvedPoint> solve(java.util.List<Constraint> extraConstraints,
                                         org.akutan.optimization.ProgressIndicator progress)
Given a list of additional constraints (beyond budget and no shorts) solves for the list of points along the efficient frontier by fixing the return and solving for the minimal variance portfolio at each return level.

Specified by:
solve in interface Solver
Parameters:
extraConstraints - Additional constraints the user applies to the problem
Returns:
List of points on the efficient frontier.

solveForReturn

public cern.colt.matrix.DoubleMatrix1D solveForReturn(double _er_step,
                                                      java.util.List<Constraint> extraConstraints)
Solves the problem for the asset weights which generate the return specified while minimizing the objective function, which here is the variance of the solution portfolio.

Parameters:
_er_step - The expected return to match.
extraConstraints - Any additional constraints (Beyond budget and no shorts)
Returns:
The vector of weights which solves the problem.