The Yuan requests your support! Our content will now be available free of charge for all registered subscribers, consistent with our mission to make AI a human commons accessible to all. We are therefore requesting donations from our readers so we may continue bringing you insightful reportage of this awesome technology that is sweeping the world. Donate now
Four combos of ML-based predictive, prescriptive analytics optimize results
By Nikolaj van Omme  |  Jan 24, 2024
Four combos of ML-based predictive, prescriptive analytics optimize results
Image courtesy of and under license from
Mixing ML with operations research maximizes the power of both while offsetting their weaknesses. Nikolaj van Omme, CEO of AI startup Funartech, which blends ML and applied math to solve complex problems, gives the lowdown in this second in a series on new ways of making AI work.

MONTREAL - A previous article described several analytical approaches and highlighted the mutual benefit of combining a predictive approach with a prescriptive one. This piece goes into greater detail as to how to combine machine learning (ML) with operations research (OR) in four efficient but varying methods.

First, one should recall that, given a certain scenario, predictive analytics are used to answer the question ‘What is likely to happen?’ while prescriptive analytics reply to ‘What is the optimal action?’ to obtain a desired aim. Both approaches are necessary to solve complex problems. With radiology as an example, the first approach detects tumors on X-rays - i.e., What does the system detect from a given X-ray image? - while the second helps health professionals make decisions - i.e., What is the best option to treat a patient given the tumor detected on an X-ray image? 

Four ML, OR combos

The fundamental strength of ML is to predict and detect, while OR’s forte lies in making decisions and optimizing. Combining the two is an art, and at least four ways are available to do so efficiently. 

ML, OR as separate black boxes

As ever more research teams opt for this combo with very effective results, it is quickly becoming a well-established technique. The most common method is to use ML to detect and predict - and once its detections and predictions are obtained, to use OR to optimize these results as input data. In radiology, deep learning (DL) detects tumors and their types on X-rays.1 Once tumors have been detected and identified as benign or malignant, medical professionals must spring into ac

The content herein is subject to copyright by The Yuan. All rights reserved. The content of the services is owned or licensed to The Yuan. Such content from The Yuan may be shared and reprinted but must clearly identify The Yuan as its original source. Content from a third-party copyright holder identified in the copyright notice contained in such third party’s content appearing in The Yuan must likewise be clearly labeled as such.
Continue reading
Sign up now to read this story for free.
- or -
Continue with Linkedin Continue with Google
Share your thoughts.
The Yuan wants to hear your voice. We welcome your on-topic commentary, critique, and expertise. All comments are moderated for civility.