Machine Learning for Bangladeshi Retailers
summary
Implements a time series algorithm to forecast SKU needs across 250+ locations with 100+ brands, mapping new items to similar products when history is missing and pushing results into Salesforce. Runs heavy background jobs in ERPNext/Frappe that generate ~2,500 sales orders per batch and merge thousands‑line sales invoices automatically. Produces per‑location transfer lists, reduces stockouts and excess, and demonstrably cuts manual reorder time and distribution cost while delivering location‑level recommendations.
AI-written summary · about
chapters (6)
related talks
23mMachine Learning with a Deep Dive into Automated Forecasting System
22mFrontiers of Machine Learning from the Lens of Retail
30mAI in Retail - Advancing Promo Demand Forecasting
31mFrom stockouts to happy customers: Proven solutions for time series forecasting in retail
27mManufacturing optimisation & planning using ML platform
21mAnalytics & Science for Customer Experience in E-commerce
27mOptimizing Omnichannel Order Fulfillment with AI and Advanced Analytics
26mRiddles in Supply Chain Management - How AI solves them?