Applications in energy, retail and shipping

[This article was first published on Revolutions, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here)
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.

The Solutions section of the Cortana Intelligence Gallery provides more than two dozen working examples of applying machine learning, data science and artificial intelligence to real-world problems. Each solution provides sample data, scripts for model training and evaluation, and reporting of predictions. You can deploy a complete stack in Azure to implement the solution with the click of a button, or follow instructions to deploy on your own hardware. The internals of each solution is fully documented and open source, so you can easily customize it to your needs.

Here's a brief overview of some solutions that have recently been posted to the Gallery. Click on the links in bold to be taken to the main solution page.

Customer Churn Prediction. This solution uses historical customer transaction data to identify new customers that are most likely to churn (switch to a competitor) in the near future. Azure Machine Learning is used to train a boosted decision tree model (with some Python scripts for data wrangling) on data stored in Azure SQL Data Warehouse; Azure Event Hub and Azure Stream Analytics are used to generate predictions on incoming data. Results are presented in interactive Power BI dashboards. Details in the Solution Guide on Github.

Demand Forecasting for Shipping and Distribution. This solution uses uses historical demand data (such as shipping or delivery records) to forecast future demand across customers, products and destinations. Forecasts are generated from data in Azure SQL Server using R functions within Azure ML and presented as a dashboard in Power BI. Developed in conjunction with New Zealand supply-chain company Kotahi. Details in the Solution Guide on Github.

Energy Supply Optimization. This solution determines the optimal mix of energy types (substation, battery cell, wind, solar, etc.) for efficient management of an energy grid. Azure Batch is used to manage a cluster of Data Science Virtual Machines, which run Pyomo (within Python) to solve complex numerical optimization problems. Results are presented in Power BI from data exported to Azure SQL Database. Details in the Solution Guide in Github.

Oil and Gas Tank Level Forecasting. This solution helps oil and gas storage facilities to anticipate problems that can lead to spills or emergency shutdowns. Data from supply sources combined with tank sensor data and outflow measurements are used to predict tank levels and flag anomalies. The zoo package for R is used to process the time series data and generate the forecasts, with are presented in a Power BI dashboard as shown below. Details in the Solution Guide on Github.


For more solutions in various industries, browse the Gallery at the link below.

Cortana Intelligence Gallery: Solutions

To leave a comment for the author, please follow the link and comment on their blog: Revolutions. offers daily e-mail updates about R news and tutorials about learning R and many other topics. Click here if you're looking to post or find an R/data-science job.
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.

Never miss an update!
Subscribe to R-bloggers to receive
e-mails with the latest R posts.
(You will not see this message again.)

Click here to close (This popup will not appear again)