Regression: Demand estimation - [Retraining Exp.]
This experiment demonstrates setting up a retraining experiment for programmatic update of the Demand estimation model.
This is experiment builds on the [Regression: Demand estimation example][1] using a two-part sample.
In the first part, we create a retraining experiment (see image below) which we can deploy as a web service. To do that:
1. We add a web service input to receive data
2. We add a web service output to output the trained model
3. Deploy the experiment as a web service (not shown)
![Setting up retraining][2]
In the [second part][3], we will create a predictive experiment, and deploy it as a web service (operationalization).
With the the retraining and scoring web services in place, we will then use [C# code][4] to complete the retraining steps.
[1]: https://gallery.cortanaintelligence.com/Experiment/Regression-Demand-estimation-4
[2]: https://operationalizatio.blob.core.windows.net/publicimages/BikingSampleGalleryExperiment.PNG
[3]: https://gallery.cortanaintelligence.com/Experiment/Regression-Demand-estimation-Predictive-Exp-1
[4]: https://github.com/raymondlaghaeian/BikeRentalDemandEstimation