Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn how Nikon Corporation developed and deployed an automated, scalable demand forecasting solution for camera accessories using Databricks' unified data and AI platform in this 32-minute conference talk. Discover the unique challenges of forecasting camera accessories, including dependencies on parent products, sparse demand patterns, and managing predictions for thousands of items across global subsidiaries. Explore Nikon's hybrid approach that automatically selects the best algorithm from a suite of machine learning and time-series models, incorporating anomaly detection and specialized methods to handle sparse and low-demand scenarios. Understand how MLflow enables automated model logging and versioning for efficient management and scalable deployment. Examine the complete framework architecture covering data preparation, model selection and training, performance tracking, prediction generation, and output processing for downstream systems. Gain insights into how this solution addresses the critical need for timely availability of camera accessories to meet the diverse requirements of professional photographers worldwide. Presented by Heya Ouyang, Senior Associate Researcher at Nikon Corporation, this talk provides practical insights into implementing enterprise-scale demand forecasting solutions using modern data science and machine learning platforms.
