Bicycle demand forecasting from O'Reilly Media webcast and report; Data Science in the Cloud with Azure ML and R

February 12, 2015

Report Abuse
This experiment is developed in full in the O'Reilly Media report and webcast Data Science In the Cloud with Azure Machine Learning and R by Stephen Elston.
This experiment applies several non-linear regression methods to forecast bicycle rental demand using Microsoft's Azure Machine Learning cloud service and R. You can view an O'Reilly media [webcast]( discussing this experiment, and read the companion [O'Reilly media report]( The R code for this experiment can be downloaded from the [Git repo]( The data set can be found in Azure ML Studio, or you can load it from the .csv file provided [here]( Reference for these data is; Fanaee-T, Hadi, and Gama, Joao, 'Event labeling combining ensemble detectors and background knowledge', Progress in Artificial Intelligence (2013): pp. 1-15, Springer Berlin Heidelberg. ## Background If you are unfamiliar with using R with Azure ML first read my [Quick Start Guide to R in Azure ML Studio]( The code is available in this [Git repo]( Companion videos are available: * [Using R in Azure ML]( * [Time series model with R in Azure ML]( There is a [Git repo]( containing all of the code for the Quick Start Guide. ## R object serialization This example uses serialization and unserialization of R model objects. My tutorial and code for serialization and unserialization of R objects in Azure ML is [here]( . There is a companion video available on [YouTube](