Kinaxis. has been granted a patent for a computer-implemented method of constraint-based optimization. This method utilizes an AI demand forecasting engine to analyze historical sales data and promotional designs, generating entities and plans while adhering to user-defined constraints to select the optimal promotional strategy. GlobalData’s report on Kinaxis gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on Kinaxis, Predictive modeling techniques was a key innovation area identified from patents. Kinaxis's grant share as of June 2024 was 24%. Grant share is based on the ratio of number of grants to total number of patents.
Constraint-based optimization using ai demand forecasting
The granted patent US12045851B2 outlines a computer-implemented method and system for constraint-based optimization in demand forecasting. The method begins with an AI demand forecasting engine that receives historical sales data and promotion design information. It employs a feature engineering pipeline to convert text-based promotion descriptions into numeric features, which are then used to train a machine learning model. This model predicts both baseline and promotion-specific item demands, with the baseline demand reflecting regular sales without promotions, while the promotion demand accounts for promotional activities. The engine generates multiple entities defined by the placement of sale items in promotional platforms and associated details, subsequently forecasting baseline and promotion forecasts for each entity.
The optimization process involves setting a linear equation based on the generated entities and their objectives, leading to the creation of various plans characterized by unique subsets of entities. Constraints are encoded as Boolean values and integrated into the linear equation. The optimization engine evaluates these plans to identify candidate solutions, eliminating those that do not meet the constraints. Ultimately, the engine selects an optimal plan aimed at maximizing the defined objective. The patent also specifies that the promotion design information can include various factors such as advertising details, store types, and loyalty programs, while the machine learning model can utilize diverse techniques, including deep learning and econometric models. This comprehensive approach aims to enhance the accuracy of demand forecasting and optimize promotional strategies.
To know more about GlobalData’s detailed insights on Kinaxis, buy the report here.
Data Insights
From
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.
