New Part Introduction Forecasting
This dashboard is a machine learning-based dashboard for New Part Introduction (NPI) forecasts. It provides demand forecasts for new parts during the selected the forecast horizon. It helps you understand key points such as the following:
• Identifying similar characteristics between a new part and corresponding matching parts through Machine Learning predictions that matches historical parts for each of the new parts.
• Providing intelligence in deriving the important Machine Learning model features that drive the NPI forecasts.
The model training results are expressed in terms of Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and Excess Units, Shortage Units, Total Demands, and Total Forecasts on the validation set.
The widgets on the New Part Introduction Forecasting dashboard are separated into three mini-dashboards:
Mini-Dashboard | Description |
|---|---|
A summary of Machine Learning model training results based on historical parts in validation set | |
Displays selected part features based on scores of all the inputs for the given Machine Learning model. The scores simply represent the “importance” of each feature. A higher score means that the specific feature will have a larger effect on the model that is being used to predict a NPI demand. | |
Displays part level important features along with total forecast, total forecast value and average monthly forecasts across the horizon selected. Click a Part Number hyperlink to open the New Part Introduction Forecasting Detail dashboard, populated with the details for the selected part number. |