Classification model with multiple thresholds

Question

A model usually has one threshold, for example 0.5, if anything is greater than 0.5 we predict it as 1 vice versa.

However, there are some features that impacts the output probability. Let's say feature a can equal to either 0 or 1. If we split the output results between 0 and 1, the thresholds gathered for 0 greatly differs from 1, meaning that the thresholds can be much greater than the probabilities that occurs in 0. Hence that anything predicted with 0 is automatically equal to 0 class, but in reality that is not true.

Is it logical to create two separate thresholds for the 0 and 1 input variable or maybe just create two individual models instead?

Answer 1

Use model(s) that output class probabilities. Whether you should use an omnibus model or separate models should be guided by which approach yields better probabilistic predictions. Use proper scoring-rules to assess this.

Use as many thresholds as required when you use your predictions to make decisions. Note that even if there are only two classes (sick/healthy), there may be more than two decisions (treat as sick/run more tests/treat as healthy).

More here.