Frontiers of Machine Learning from the Lens of Retail
summary
Company vision treats extreme sparsity as the central technical problem and claims accurate per-SKU, per-channel demand forecasts by stitching text, image and transaction data into a higher-order tensor with a low-rank latent model. Production software provides provenance for each prediction (e.g., similar shirt sold X times at Y price), targets buy optimization, assortment planning and fulfillment, exploits cross-product natural experiments to infer price elasticity, and is commercially deployed with multiple retail clients and growing revenue.
AI-written summary · about
chapters (4)
related talks
31mFrom stockouts to happy customers: Proven solutions for time series forecasting in retail
08mMachine Learning for Bangladeshi Retailers
30mAI in Retail - Advancing Promo Demand Forecasting
21mAnalytics & Science for Customer Experience in E-commerce
22mRonald Menich, Chief Data Scientist, Predictix, LLC
22mReal-world applications of machine learning: Beyond the hype
22mMachine Learning: The Engine Behind Modern E-commerce Search
56mMachine Learning in E‑commerce