Skip to main content
. 2021 Feb 10;8(2):201795. doi: 10.1098/rsos.201795

Table 5.

Accuracy of different algorithms across five spatial and non-spatial models with outcome variable diweek. For comparison, naive prediction of the majority class would achieve accuracy of 0.56 for New York and 0.603 for Los Angeles. The respectively best performing learning algorithm (LM, RF, GB, GP) is highlighted in bold.

New York
Los Angeles
NS1 NS2 S1 S2 S3 NS1 NS2 S1 S2 S3
LM 0.671 0.671 0.672 0.672 0.669 0.676 0.679 0.681 0.670 0.669
RF 0.670 0.668 0.625 0.618 0.599 0.676 0.665 0.630 0.616 0.612
GB 0.668 0.663 0.628 0.655 0.626 0.676 0.661 0.612 0.647 0.619
GP 0.667 0.676