Selective classification for trading strategy design

What is it about?

Binary classifiers that try to predict if the price of an asset will increase or decrease naturally gives rise to a trading strategy that follows the prediction and thus always has a position in the market. In this paper, we apply selective classification for trading strategy design. Selective classification extends a binary or many-class classifier to allow it to abstain from making a prediction for certain inputs, thereby allowing a trade-off between the accuracy of the resulting selective classifier against coverage.

Featured Image

Why is it important?

The application of selective classification to trading strategy design is important as it helps binary or many-class classifiers abstain when they are uncertain about making a prediction.