Reducing Demand Forecast Error with Deep Learning
For perishable food companies, demand is volatile and error is extremely expensive. As a result, food companies are pioneering cutting edge Machine Learning Demand Forecasting services to reduce spoilage and prevent stockouts. Learn how feature extraction with deep neural networks and gradient boosting methods significantly reduce forecast error.
Nima is co-founder of Deepnify, a MLaaS startup applying Deep Learning to help food companies achieve a zero-waste supply chain. He is a PhD Candidate in the Data Mining and Database Group at York University. Nima ranked 19th from over 1M data scientists on Kaggle, where he has won data mining competitions for Rossmann, Home Depot, and Two Sigma. He also ranked 7th in ICDM'16 and 5th in IEEE Big data 2016 competitions. He previously worked in big data analytics, specifically on Forex and Stock Market predictions.