quantlab.portfolio.predefined.approximate.mean_variance.PanelProblem#

class quantlab.portfolio.predefined.approximate.mean_variance.PanelProblem(low_rank, expected_return, selectable, predicted, reference=None)[source]#

Bases: object

What every bar’s decision reads but its holdings: mu, the covariance and the candidates.

What a posterior passed to decide receives and returns.

expected_return#: [bars, symbols]: mu, 0.0 where there is no prediction.

low_rank#: Each bar’s covariance on the expected-return label’s span.

predicted#: [bars, symbols]: selectable with a finite prediction, a candidate whatever is held (a posterior may widen it to selectable symbols without one).

reference = None#: [bars, symbols]: the reference book b the risk term prices w - b against (the active-risk rule’s benchmark weights, NaN as 0), or None for total risk.

selectable#: [bars, symbols]: tradable and covered, so a holding there is a candidate.