Historical Product Demand for Forecasting with Warehouse and Category Data
arff
Available on 1 platform
Sign in to view source links and access this dataset
Description
Historical_Product_Demand is a dataset contributed by Charles Gaydon on OpenML. It contains five variables: Productcode, Warehouse, ProductCategory, Date, and Order_demand. The contributor demonstrated that simple models could achieve a mean average forecasting error of around 20 for 80% of the total ordered volume, indicating predictive potential.
Use Cases
Forecasting product order demand based on historical date and order_demand columns.
Incorporating warehouse location as a feature to improve regional demand predictions.
Using product category data to model demand patterns across different product groups.
Classifying normalized order demand categories instead of using linear regression models.
Strengths
The contributor demonstrated a mean average forecasting error of around 20 for 80% of total ordered volume using trivial models.
Contains key variables for demand forecasting: Productcode, Warehouse, ProductCategory, Date, and Order_demand.
Limitations
Row count and dataset size are unknown, which may limit suitability assessment.
Column-level documentation is absent; field semantics must be inferred after download.
Last update date is unknown; freshness unverified.