Bradley-Terry Likelihood

Problem

Compute the Bradley-Terry probability that the first item is preferred: sigmoid(r1 - r2) = 1 / (1 + exp(-(r1 - r2))).

Hint

Equal rewards give a fifty-fifty preference.

case 1

in: [0,0]

expected: 0.5

case 2

in: [2,0]

expected: 0.8807970779778823

case 3

in: [0,2]

expected: 0.11920292202211755

Starter codePython

import math
def bradley_terry_likelihood(r1, r2):
    # Your code here
    pass

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