OTLP: Output Thresholding Using Mixed Integer Linear Programming

Almost all classification methods such as XGBoost [1], Random Forest [2], Logistic Regression [3] are able to produce probability estimates. Output thresholding is a process to tune the decision threshold which is later used to assign class predictions based on a model's probability estimates for instances during inference [4]. For binary classification tasks, instances with probability estimates higher than or equal to the threshold are assigned positives class, otherwise as negative which is depicted in Table 1. Adjusting the threshold is particularly important for imbalanced classification problems where the train datasets have a smaller number of samples in the minority classes compared to the other classes. Output thresholding is one of the methods to address class imbalance problem [5]. Since the distribution of classes is skewed and probability estimates often favor the majority class, using a default classification threshold of 0.5 may not be the most effective approach for such problems [6]. Therefore it is essential to perform a search for the threshold to use during inference. Output thresholding is also considered to address class imbalance problem for convolutional neural networks [7].