The “Forecast” extension is introducing the forecasting capability as part of AI for Everyone offering on MindSphere, which offers an out-of-the-box model building to forecast your future time series data values, using advanced artificial intelligence and machine learning technologies.
The “Forecast” extension uses time series data from MindSphere asset as dataset and does easy configuration for forecast model building and execution.
The “Forecast” extension visualizes forecasting results which could be further utilized for your targeted use cases like comparing with threshold value, reviewing historic forecasting records for model selection.
User interface of the Forecast¶
The following figure shows the "Forecast" screen:
① Data visualization area
② Use case details of the forecast
③ Forecast Configuration settings
Generate the Forecast report¶
To generate the forecast report, proceed with the following steps:
- Open "AI for Everyone" in the "Analyze" section.
- Select the "Use Case", and click "Forecast Jobs".
- Select the targeted variable of your choice.
The forecast prediction is prepared for the selected target variable.
- Select the input variables of your choice.
- Configure the below settings to generate the forecast report.
- Prediction Horizon: Number of samples or time period in the future for forecasting
- Validation Length: Back-testing length from dataset for accuracy metrics generation
- Confidence Interval: A measurement of percentage to represent the confidence level
- Allow offset: A boolean value that decides whether to use offsets of predictors in model
- Click "Generate Forecast".
The generated forecast report can be used to predict the future data for the selected variables of the asset.
① Predictor importance indicators
② Data visualization area
③ Use case details of the forecast report
④ Forecast configuration settings
⑤ Forecasted executions
Compare the Forecast report¶
The "Forecast" extension allows you to predict the future data on multiple instances and compare them for analysis. This comparision of historic forecasting records assits in the better model selection.
Once the forecast report is generated, make the required changes in the "Forecast Configurations" and click "Regenerate Forecast" and compare the two reports.
To compare the forcasting reports, select the various forcasting reports and click "Compare".
The following figure shows the comparision of the two forecast reports:
Save the Forecast report¶
The Forecast Extension allows you to upload the generated reports to integrated Data Lake application.
To save the generated forecast reports, select the report and Click "Save".
Validate the Forecast Report¶
The Forecast Extension allows you to compare and validate the actual asset data with the forecast reports.
In order to compare the actual asset data with the forecase report, ensure the actual asset data is uploaded to MindSphere.
To compare and validate the forecast reports with Actual asset data, select the report and click "Validate".
Any questions left?
Except where otherwise noted, content on this site is licensed under the MindSphere Development License Agreement.