skip to content

Cambridge Service Alliance

At the forefront of service transformation in the digital era
 
High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach

February Paper on High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach by Tim Pearce, Mohamed Zaki, Alexandra Brintrup, Andy Neely

[Paper]

Deep neural networks (NNs) have caused great excitement due to the step-changes in performance they have delivered in a variety of applications. However, their appeal in industry can be inhibited by an inability to quantify the uncertainty of their predictions. To take a prognostics example, a typical NN might predict that a machine will fail in 60 days. It is unclear from this point prediction whether the machine should be repaired immediately, or whether it can be run for another 59 days. However, if the NN could output a prediction interval (PI) of 45-65 days with 99% probability, timing of a repair could easily be scheduled. In this paper, we develop a method for doing exactly this - the quantification of uncertainty in deep learning using PIs. We derive a method based on the assumption that high-quality PIs should be as narrow as possible, whilst still capturing a given proportion of data. The method is general, applicable to any data-driven task where a continuous value needs to be predicted, and it is important to know the uncertainty of that prediction. Examples include the forecasting of precipitation, energy load, financial metrics, and traffic volume. The method is tested on ten real-world, open-source datasets. The proposed method is shown to outperform current state-of-the-art uncertainty quantification methods, reducing average PI width by around 10%.

Cambridge Service Alliance

Welcome to the Cambridge Service Alliance…

  • a unique global alliance between leading businesses and universities;
  • bringing together the world's leading firms and academics;
  • all of whom are devoted to delivering today the tools, education and insights needed for the complex service solutions of tomorrow.

LinkedIn

Follow us on Twitter

Latest news

Bouygues Construction joins the Cambridge Service Alliance

27 May 2021

We are delighted to announce that Bouygues Construction has joined the Cambridge Service Alliance, Institute for Manufacturing (IfM), University of Cambridge as a new industry member alongside our existing partners HCL Technologies , Caterpillar Inc. , Perkins Engines Company Limited and CEMEX . Press release

'Using AI to Track How Customers Feel — In Real Time' published in the Harvard Business Review

13 May 2021

The paper 'Using AI to Track How Customers Feel — In Real Time' by Mohamed Zaki, Janet R. McColl-Kennedy and Andy Neely has been published in Harvard Business Review.

Industry Day 2020 | What we learnt

6 December 2020

What is the future of services in the new pandemic-driven era? This was the topic explored at our 2020 Industry Day by senior executives from L'Oréal, Microsoft Research, Manchester United and start-up, Fairjungle.