Walk-Forward Efficiency

Problem

Compute walk-forward efficiency as 1 - mean(oos_errors) / mean(is_errors).

Return 0.0 when either list is empty or the in-sample mean is zero. Negative values mean out-of-sample performance degraded relative to in-sample.

Hint

A value near 0 means performance held up out of sample.

case 1

in: [[1,1,1],[1.2,1.2,1.2]]

expected: -0.19999999999999996

case 2

in: [[2,2],[2,2]]

expected: 0

case 3

in: [[1,2],[3]]

expected: -1

case 4

in: [[],[]]

expected: 0

Starter codePython

def walk_forward_efficiency(is_errors, oos_errors):
    # Your code here
    pass

4 test cases · run your code against them in the editor