Regression: Demand estimation - [Retraining Exp.]

May 29, 2016
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