Machine Learning Times
Machine Learning Times
EXCLUSIVE HIGHLIGHTS
Survey: Machine Learning Projects Still Routinely Fail to Deploy
 Originally published in KDnuggets. Eric Siegel highlights the chronic...
Three Best Practices for Unilever’s Global Analytics Initiatives
    This article from Morgan Vawter, Global Vice...
Getting Machine Learning Projects from Idea to Execution
 Originally published in Harvard Business Review Machine learning might...
Eric Siegel on Bloomberg Businessweek
  Listen to Eric Siegel, former Columbia University Professor,...
SHARE THIS:

3 years ago
Wise Practitioner – Predictive Analytics Interview Series: Benjamin Arias-Gálvez at Foresta.IO

 

By: Jeff Deal, Conference Chair, Predictive Analytics World for Healthcare

In anticipation of his upcoming presentation at Predictive Analytics World for Healthcare Livestream, May 24-28, 2021, we asked Benjamin Arias-Gálvez, Co-Founder and Head of Consultancy at Foresta.IO, a few questions about their deployment of predictive analytics. Catch a glimpse of his presentation, Value Extraction from complexity in operations with algorithms & AI, and see what’s in store at the PAW Healthcare conference.

Q: In your work with predictive analytics, what behavior or outcome do your models predict?

A: It depends on the industry. The three most common are the prediction of processing rates for queueing and scheduling resources, the future performance of products based on conditions at the moment of their production and the prediction of future anomalies in the last-mile delivery processes that will cause physical losses or delivery delays.

Q: How does predictive analytics deliver value at your organization – what is one specific way in which it actively drives decisions or operations?

A: We raise the standard of what it is possible by increasing the performance of physical assets by helping to make better, real time, non trivial decisions.

Q: Can you describe a quantitative result, such as the predictive lift of your model or the ROI of an analytics initiative?

A: An average of 20% reduction in waiting time for patients at Emergency Rooms in complex hospitals, using the same assets and personnel.

Q: What surprising discovery or insight have you unearthed in your data?

A: Customers tend to minimize the value of their current data. They believe their data is noisy, incomplete and sometimes incoherent, and that a lengthy path to cleanse it is a prerequisite for any analytics improvement. And in most cases their data is noisy, incoherent or incomplete to some extent. But it doesn’t mean they can not use it as is. We have been able to draw strong conclusions even from noisy, incomplete data, so the benefits can be obtained earlier than expected. That’s the beauty of this field.

Q: Sneak preview: Please tell us a take-away that you will provide during your talk at Predictive Analytics World.

A: It is possible to improve the performance of current assets without changing them, but by changing some real time decisions, like cars in heavy traffic: the cars equipped with GPS will reach their destination earlier, no matter how powerful or luxurious they might be. In operations, predictive models let us make better decisions, allowing us to increase the performance of existing assets without investing in the physical world but by using better the existing information.

—————————–

Don’t miss Benjamin’s presentation, Value Extraction from complexity in operations with algorithms & AI, at PAW Healthcare on Tuesday, May 25, 2021 from 11:30 AM to 12:15 PM. Click here to register for attendance.

By: Jeff Deal, Conference Chair, Predictive Analytics World for Healthcare

Leave a Reply