Abstract: In an approach to improve computer-based supply chain management embodiments of the present invention receive a first order associated with a user, and determine, within predetermine range of confidence, that a second order associated with the user will be received within a predefined timeframe. Additionally, embodiments delay the shipment of the first order, for a predetermined amount of time, based on the determination the second order will be received and execute a hold command that withholds the first order from a distribution center for a predetermined amount of time. Further, responsive to receiving the second order within the predefined timeframe, embodiments consolidate the first order and second order into a consolidated order.

Abstract: A computer-implemented process for training a neural network includes the following operations. Return data received from a return channel is evaluated against a threshold. Based upon the threshold being satisfied, the return data is validated, and the return data is cognitive processed to generate a return insight. Using the neural network and based upon the return insight, a corrective action is generated. The neural network is trained using feedback generated based upon the corrective action. The threshold is then updated using the neural network.