International Business Machines Corporation
Dynamic Inventory Segmentation with Predicted Prediction Time Window

Abstract:

A machine learning system for dynamically segmenting inventory includes a memory having instructions therein, and at least one processor configured to execute the instructions to, using a reinforcement learning agent ("RLA"): determine, based at least in part on first inventory data corresponding to at least a portion of a first prediction time window for the RLA, a second prediction time window for the RLA; segment a first supply of inventory, based at least in part on the second prediction time window and at least a portion of the first inventory data; determine, based at least in part on second inventory data corresponding to at least a portion of the second prediction time window, a third prediction time window for the RLA; and segment a second supply of inventory, based at least in part on the third prediction time window and at least a portion of the second inventory data.