Predicting accurate probabilities with a ranking loss
This work addresses the need for reliable probability predictions in real-world applications, offering a semi-parametric method that improves upon standard approaches like logistic regression.
The paper tackles the problem of predicting accurate class probabilities in machine learning by proposing a technique that combines ranking loss optimization with isotonic regression, achieving both good ranking and regression performance while modeling a richer set of probability distributions than logistic regression.
In many real-world applications of machine learning classifiers, it is essential to predict the probability of an example belonging to a particular class. This paper proposes a simple technique for predicting probabilities based on optimizing a ranking loss, followed by isotonic regression. This semi-parametric technique offers both good ranking and regression performance, and models a richer set of probability distributions than statistical workhorses such as logistic regression. We provide experimental results that show the effectiveness of this technique on real-world applications of probability prediction.