Abstract: 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.

Abstract: A method and system optimizing source selection of an online order with the lowest fulfillment cost by considering multiple types of parameters, including shipping costs, backlog costs and markdown savings of the order. The method includes obtaining an order from the order retrieval subsystem of the OMS, selecting the candidate sources, and retrieving data from retailers or shipping companies of each selected candidate sources. The system then calculates the costs and savings parameters of the candidate sources from the retrieved data. The system identifies all possible candidate sourcing selections of the order and calculates the total fulfillment cost of each sourcing selection of the order by adding the shipping costs with the backlog costs, and subtracting the markdown savings of all candidate sources in each sourcing selection. The system identifies the optimized sourcing selection of the order with the lowest fulfillment cost and renders the selection to the OMS.

Abstract: 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.