Intermittent Demand Forecasting at Scale Using Meta-Modeling - Deep Auto-Regressive Linear Dynamic Systems
Offered By: Databricks via YouTube
Course Description
Overview
Explore a groundbreaking demand forecasting solution for intermittent time-series developed by Walmart in this 28-minute presentation. Discover how the meta-modeling approach combines linear dynamic systems and deep auto-regressive recurrent networks to address the challenges of predicting slow-moving item demand across Walmart stores. Learn about the solution's architecture, including explicit feature engineering, implicit feature modeling, and the Deep ARLDS network. Gain insights into scaling the model for accurate forecasts across approximately 35,000 SKUs and 250 Walmart stores. Examine the results and consider future applications of this innovative approach to granular demand predictions at scale.
Syllabus
Intro
Overview
Problem Statement
Meta Model Framework
Explicit Feature Engineering
Implicit Feature Modelling
Deep Learning Model
Deep ARLDS Network Architecture
Scaling
Results
Conclusion and Future Scope
Taught by
Databricks
Related Courses
Neural Networks for Machine LearningUniversity of Toronto via Coursera 機器學習技法 (Machine Learning Techniques)
National Taiwan University via Coursera Machine Learning Capstone: An Intelligent Application with Deep Learning
University of Washington via Coursera Прикладные задачи анализа данных
Moscow Institute of Physics and Technology via Coursera Leading Ambitious Teaching and Learning
Microsoft via edX