Oscar Porto and Fábio Ferraretto at DHAUZ « Machine Learning Times

Ahead of their upcoming presentation at Predictive Analytics World Industry 4.0, Las Vegas, June 19-24, 2022, we asked Oscar Porto, Founding Partner at DHAUZ, and Fábio Ferraretto, Business Analytics Senior Executive at DHAUZ, a few questions about their deployment of predictive analytics. Discover their presentation, Stockout Predictions Using Machine Learning in a Building Material Multinational Company and find out what awaits you at the Predictive Analytics World Industry 4.0 conference.

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

A: A predictive algorithm to identify out-of-stock risks for each SKU/CD combination for the next 7 and 14 days for Saint-Gobain’s Brazilian operation.

Saint-Gobain is a company that designs, manufactures and distributes materials and services for the construction and industrial markets and is present in 75 countries.

Q: How does predictive analytics bring value to your organization? What is a specific way in which it actively guides decisions or operations?

A: We are an advanced analytics company that works on all of our projects with an integrated view of data science, business process, and technology insights.

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

A: +80% accuracy and 0.7 F1 for major SKUs and major CDs. When we compare the model output with the inventory-based business rules, for example, we get an accuracy of 1-(0.82 / 0.6) = 36%. In terms of F1: 1 – (0.67 / 0.45) = 48%.

Q: What surprising discovery or idea did you find in your data?

A: Out of stock predictions on SKUs that haven’t been watched so closely.

Q: Sneak Peek: Please let us know one takeaway that you will provide during your presentation at Predictive Analytics World.

A: Predictive analytics is able to solve the problem of predicting out-of-stock situations, generating visibility for the next 14 days, allowing the business to take action to minimize them and, therefore, generate revenue additional.

Don’t miss Oscar and Fábio’s presentation, Stockout Predictions Using Machine Learning in a Building Material Multinational Company at Predictive Analytics World Industry 4.0, Wednesday, June 22, 2022, 2:15-3:00 p.m. Click here to register.

About Jason Norton

Check Also

With Twitter Delisted, Put Your Money Into These Stocks Instead

It’s official, Twitter is no longer available to the general public. With Elon Musk already …