Time series forecasting is the task of predicting future values in a time-ordered sequence of observations. It is a common problem and has applications in many industries. This example focuses on energy demand forecasting where the goal is to predict the future load on an energy grid. It is a critical business operation for companies in the energy sector. In this example, machine learning methods are applied to forecast time series. Although the context is energy demand forecasting, the methods used can be applied to many other contexts and use cases. Using Azure Machine Learning Workbench, you are guided through every step of the modeling process including: 1. Data preparation to clean and format the data; 2. Creating features for the machine learning models from raw time series data; 3. Training various machine learning models; 4. Evaluating the models by comparing their performance on a held-out test dataset; and, 5. Operationalizing the best model through a web service to generate forecasts on demand.
- The detailed documentation for this example includes the step-by-step walk-through: https://docs.microsoft.com/azure/machine-learning/preview/scenario-time-series-forecasting. - For code samples, click the View Project icon on the right and visit the project GitHub repository. - Key components needed to run this scenario: 1. An [Azure account](https://azure.microsoft.com/free/) (free trials are available). 2. An installed copy of Azure Machine Learning Workbench with a workspace created. 3. For model operationalization: - [Docker engine](https://www.docker.com/). - Azure Machine Learning Operationalization with a local deployment environment set up and a model management account created as described in this [guide](https://github.com/Azure/Machine-Learning-Operationalization/blob/master/documentation/getting-started.md). 4. This example could be run on any compute context. However, it is recommended to run it on a multi-core machine with at least of 8-GB memory.