The detailed documentation for this market campaign prediction example includes the step-by-step walk-through:
Following is the link to the public GitHub repository where all the codes are hosted:
https://github.com/Azure/MachineLearningSamples-MarketCampaign
In business, companies are commonly recruiting new customers through market campaign. As a result, marketing executives often find themselves trying to predict the likelihood of customer purchase and finding the necessary actions to maximize the purchase rate.
The aim of this solution is to demonstrate predictive market analytics using AML Workbench. This solution provides an easy to use template to develop market campaign predictive data pipelines for retailers. The template can be used with different datasets and different definitions of success of market campaign. The aim of this tutorial is to:
- Understand AML Workbench's Data Preparation tools to ingest and pre-process customer relationship data for market campaign prediction and customer review data for sentiment analysis.
- Perform feature transformation to handle noisy heterogeneous market data.
- Perform Unigrams TF-IDF feature extraction to convert unstructured text review data.
- Train and validate various machine learning models (such as Logistic Regression, Support Vector Machine, Decision Tree) with hyper-parameter sweeping for predicting the success of market campaign, as well as predicting the sentiment score of customer review.
- Model operationalization.
- An Azure account (free trials are available).
- An installed copy of Azure Machine Learning Workbench with a workspace created.
- This example could be run on any compute context.
MarketCampaign collects usage data and sends it to Microsoft to help improve our products and services. Read our privacy statement to learn more.
This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.microsoft.com.
When you submit a pull request, a CLA-bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., label, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.
This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.