Blue Yonder‘s patent involves a system and method for explainable supervised machine learning cyclic boosting to predict future customer demand quantities. The computer receives historical sales data, trains a model, and predicts demand quantities based on supply chain data, providing a visualization of demand prediction features. GlobalData’s report on Blue Yonder gives a 360-degree view of the company including its patenting strategy. Buy the report here.

According to GlobalData’s company profile on Blue Yonder, was a key innovation area identified from patents. Blue Yonder's grant share as of February 2024 was 69%. Grant share is based on the ratio of number of grants to total number of patents.

Explainable supervised machine learning cyclic boosting for demand prediction

Source: United States Patent and Trademark Office (USPTO). Credit: Blue Yonder Inc

A recently granted patent (Publication Number: US11922442B2) outlines a computer-implemented method for explainable supervised machine learning cyclic boosting to predict and explain future customer demand quantities. The method involves receiving historical sales data, binning categorical and continuous features, training a cyclic boosting model, and predicting demand quantities during a specified period. The model calculates factors for each feature and bin, generates partial factors for target values, and aggregates factors to predict demand. A user interface displays a demand prediction feature explanation visualization, showcasing predicted demand and influential features identified during model training.

Additionally, the patent describes the system's ability to stop training based on specific criteria, render interactive graphical elements for user selection of items and stores, retrieve factors influencing predicted demand, and allow modification of future feature states. The system bins continuous features, ensures predicted values follow a Poisson distribution, and categorizes, ranks, and evaluates features of the cyclic boosting prediction. The patent also includes a non-transitory computer-readable medium with software for executing the method, further enhancing the system's capabilities. Overall, the patent details a comprehensive approach to utilizing machine learning for demand prediction and explanation, with a focus on transparency and user interaction through visualizations and feature modifications.

To know more about GlobalData’s detailed insights on Blue Yonder, buy the report here.

Premium Insights


The gold standard of business intelligence.

Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.


GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.

GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.