Fraud Detection

For the IT Administrator

  • System Requirements
  • Cluster Maintenance
  • Workflow Automation
  • Data
    • Fraud detection is one of the earliest industrial applications of data mining and machine learning. This solution shows how to build and deploy a machine learning model for online retailers to detect fraudulent purchase transactions. View more information about the data.

    This solution demonstrates the code with approximately 200,000 transactions. Using HDInsight Spark clusters makes it simple to extend to very large data, both for training and scoring. As you increase the data size you may want to add more nodes but the code itself remains exactly the same.

    System Requirements

    This solution uses:

    Cluster Maintenance

    HDInsight Spark cluster billing starts once a cluster is created and stops when the cluster is deleted. See these instructions for important information about deleting a cluster and re-using your files on a new cluster.

    Workflow Automation

    Access RStudio on the cluster edge node by using the url of the form http://CLUSTERNAME.azurehdinsight.net/rstudio Run the script development_main.R followed by web_scoring_main.R to perform all the steps of the solution.

    Data Files

    The following data files are available in the Fraud/Data directory in the storage account associated with the cluster:

    File Description
    Account_Info.csv Customer account data
    Fraud_Transactions.csv Raw fraud transaction data
    Untagged_Transactions.csv Raw transaction data without fraud tag