International Business Machines Corporation

Michael Yesudas

Arun Hampapur

Raghuveer Prasad Nagar

Xuan Liu

Ajay Ashok Deshpande

Saurabh Gupta

Ali Koc

Brian Leo Quanz

Christopher Scott Milite

Yingjie Li

Chek Keong Tan

Jagadesh Ramaswamy Hulugundi

Dahai Xing

Xiaobo Zheng

Ding Ding Lin

Pradyumnha Gopalkrishna Kowlani

Nithin Mathew

Vadiraja S Ramamurthy

Steve Igrejas

Sachin Sethiya

Sanjay E Cheeran

An embodiment of the present invention monitors a process across a plurality of systems associated with a supply chain. A context is determined for an order, where at least one of the features of the context includes information from a networked sensing device. One or more first machine learning models identify a plurality of orders of an order history having features corresponding to the order. A second machine learning model is trained with the identified plurality of orders to predict the monitoring interval for the order. The second machine learning model predicts the monitoring interval for the order based on the context of the order. The monitoring interval for the order is dynamically adjusted based on the predicted monitoring interval, and the order is monitored through an order fulfillment process across the plurality of systems associated with the supply chain in accordance with the adjusted monitoring interval.

Monitoring and adapting a process performed across plural systems associated with a supply chain

A predictive engine on a computer environment comprising a shared pool of configurable computing resources is executed to perform a predictive analysis on data pipelined into the computer environment, the data received from a plurality of sources and in a plurality of different formats, the predictive engine generating a network level cost information based on the predictive analysis on a dynamic and continuous basis. Asynchronous communication comprising the network level cost information from the predictive engine is received and a set of candidate nodes for order fulfillment is generated based on the network level cost information and a defined distance between the set of candidate nodes and a target destination. An optimization engine on the computer environment is invoked that filters the set of candidate nodes. A number of fulfillment nodes that meet one or more of a constraint and preconfigured rule is output.

Order sourcing with asynchronous communication and using optimization for large sourcing networks

Growing community of inventors

Plano, TX, United States of America

Michael Yesudas