quantlab.model.evaluation.cross_sectional_rank_ic

quantlab.model.evaluation.cross_sectional_rank_ic(pred, target)

Return the cross-sectional IC computed on per-row ranks.

The mean of cross_sectional_rank_ic_series over the rows it does not skip, or NaN when every row is skipped.

Parameters:

predarray_like

A 2-D [T, S] panel of predictions.

targetarray_like

A 2-D [T, S] panel of realised values.

Raises:

ValueError

If the inputs are not 2-D or differ in shape.

Examples

The panel from cross_sectional_ic orders every row the same way on both sides, so its rank correlation is exactly 1:

>>> cross_sectional_rank_ic(pred, target)
1.0