Large-scale demand forecasting¶
The notebooks listed below outline how to performed large-scale demand forecasting using DataRobot's Python package. No single model can handle extreme data diversity or forecast the complexity of human buying patterns at a detailed level. Complex demand forecasting typically requires deep statistical know-how and lengthy development projects around big data architectures. This notebook builds a model factory to automate this requirement by creating multiple projects "under the hood."
Follow the notebooks below in order to complete the demand forecasting workflow.
|Setup and upload data||Install and import the required libraries, connect to DataRobot, and curate the data for modeling.|
|Cluster data||Break a dataset up into smaller datasets that group similar items together.|
|Build models||Use segmented modeling to improve model performance and decrease time to deployment.|
|Get model insights and create feature lists||Review insights for the top-performing model and create new feature lists.|
|Deploy a model and make predictions||Test a model's prediction capabilities and deploy a model to a production environment to generate predictions.|