Bayesian Model Averaging Prediction

Problem

Bayesian model averaging predicts with the posterior-weighted mean of the model predictions: the sum over models of posteriors[m] * predictions[m]. Return 0.0 for empty or mismatched lists or a negative posterior weight.

Hint

Weight each model prediction by its posterior probability and add them up.

Test cases

case 1

in: [[0.7,0.3],[10,20]]

expected: 13

case 2

in: [[0.5,0.5],[0,1]]

expected: 0.5

case 3

in: [[1],[5]]

expected: 5

case 4

in: [[0.2,0.3,0.5],[1,2,3]]

expected: 2.3

case 5

in: [[],[]]

expected: 0

Starter codePython

def bayesian_model_averaging(posteriors, predictions):
    # Your code here
    pass

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