Optimizing Omnichannel Order Fulfillment with AI and Advanced Analytics
summary
Claims a >20% omnichannel efficiency gain and shows actual systems: a central inventory visibility layer integrated with IBM Sterling Commerce, forecasting with ARIMA/SARIMAX and exponential smoothing (reported MAE 1.84 vs 2.54 vs 4.16), order sourcing and predictive delivery using random forest regressor (n_estimators=100, random_state=42) and K-nearest neighbors (n_neighbors=5), demos that output predicted delivery dates, nearest-fulfilling store IDs, and concrete inventory targets (examples: predicted counts 23 and 41) on small sample datasets.
AI-written summary · about
chapters (10)
- 0:00Introduction
- 1:50Order management systems
- 3:57Central inventory visibility
- 4:38Central inventory with AI
- 8:56ARIMA model parameters
- 13:11Order sourcing with ML
- 18:26Predictive delivery results
- 21:17Dynamic inventory allocation
- 24:24Live demo and performance
- 26:08Retraining and Q&A
related talks
27mLeveraging AI for Resilient Supply Chains
23mArtificial Intelligence for Store Assistance
30mAI in Retail - Advancing Promo Demand Forecasting
26mRiddles in Supply Chain Management - How AI solves them?
16mGen AI For Retail Data Management
01h 00mAutomation: Amazon’s Supply Chain Optimization Technologies (SCOT)
35mBuilding a successful inventory planning solution with Amazon Forecast
38mOptimizing Retail Forecasting Through AI Models