Reader small image

You're reading from  Practical Guide to Applied Conformal Prediction in Python

Product typeBook
Published inDec 2023
PublisherPackt
ISBN-139781805122760
Edition1st Edition
Right arrow
Author (1)
Valery Manokhin
Valery Manokhin
author image
Valery Manokhin

Valeriy Manokhin is the leading expert in the field of machine learning and Conformal Prediction. He holds a Ph.D.in Machine Learning from Royal Holloway, University of London. His doctoral work was supervised by the creator of Conformal Prediction, Vladimir Vovk, and focused on developing new methods for quantifying uncertainty in machine learning models. Valeriy has published extensively in leading machine learning journals, and his Ph.D. dissertation 'Machine Learning for Probabilistic Prediction' is read by thousands of people across the world. He is also the creator of "Awesome Conformal Prediction," the most popular resource and GitHub repository for all things Conformal Prediction.
Read more about Valery Manokhin

Right arrow

The concept of PIs in forecasting applications

PIs are vital tools in forecasting, providing a range of plausible values within which a future observation is likely to occur. Unlike point forecasts, which give a single best estimate, PIs communicate the uncertainty surrounding that estimate.

This section explores the fundamental concepts behind PIs and their significance in various forecasting applications.

Definition and construction

PIs are constructed around a point forecast to represent the range within which future observations are expected to lie with a given confidence level. For example, a 95% PI implies that 95 of 100 future observations are expected to fall within the defined range.

PIs can take several forms, depending on the approach used to generate them. Two key distinguishing factors are as follows:

  • Symmetric versus asymmetric intervals: PIs can be symmetric, where the bounds are equidistant from the point forecast, or asymmetric, reflecting differing...
lock icon
The rest of the page is locked
Previous PageNext Page
You have been reading a chapter from
Practical Guide to Applied Conformal Prediction in Python
Published in: Dec 2023Publisher: PacktISBN-13: 9781805122760

Author (1)

author image
Valery Manokhin

Valeriy Manokhin is the leading expert in the field of machine learning and Conformal Prediction. He holds a Ph.D.in Machine Learning from Royal Holloway, University of London. His doctoral work was supervised by the creator of Conformal Prediction, Vladimir Vovk, and focused on developing new methods for quantifying uncertainty in machine learning models. Valeriy has published extensively in leading machine learning journals, and his Ph.D. dissertation 'Machine Learning for Probabilistic Prediction' is read by thousands of people across the world. He is also the creator of "Awesome Conformal Prediction," the most popular resource and GitHub repository for all things Conformal Prediction.
Read more about Valery Manokhin