microsoft / r-server-fraud-detection

This solution template demonstrates how to build and deploy a retail online fraud detection solution.

Fraud Detection

Predict if an online purchase transaction is fraudulent. This is an important scenario in many industries, including retail and finance.

Deploy to Azure on SQL Server

More samples and information

Discover more examples at Microsoft Machine Learning Server

For all documentation, visit the Fraud Detection website.

NOTE: Please don't use "Download ZIP" to get this repository, as it will change the line endings in the data files. Use "git clone" to get a local copy of this repository.

Contributing

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact [email protected] with any additional questions or comments.

r-server-fraud-detection's Issues

SQL 2017 error

Hi, i install demo in SQL Server 2017 RTM and recive this error when execute TrainModelR in setup

STDOUT message(s) from external script:
====== SQL2017 ( process 1 ) has started run at 2017-11-16 10:06:57.11 ======

The file or directory 'work\sample-ds1.xdf' cannot be found.
Error in doTryCatch(return(expr), name, parentenv, handler) :
The file or directory 'work\sample-ds1.xdf' cannot be found.
Calls: source ... tryCatch -> tryCatchList -> tryCatchOne -> doTryCatch -> .Call
Execution halted

This repo is missing important files

There are important files that Microsoft projects should all have that are not present in this repository. A pull request has been opened to add the missing file(s). When the pr is merged this issue will be closed automatically.

Microsoft teams can learn more about this effort and share feedback within the open source guidance available internally.

Merge this pull request

Lcrsetup Script Failure

Hello i'm getting the following error:

Cluster deployment failed due to an error in the custom script action. Failed Actions: 'lcrsetup',Please go to Ambari UI to further debug the failure.

I believe it's possibly because it's trying to run the script on the edge node whereas the options it gives us, if creating the HDInsight cluster directly from the portal is Head, Node, Worker. I"ll try to move the script action to the Head node to see if that improves. But any insight would be great.

merge procedure

Stuck on the merge procedure transactiondate/time tends to run out of range or fails to convert from varchar to datetime

* Install failing at Step 4 *

Greetings.
I am attempting to install this r-example on a Windows 10 Machine (Surface Studio 2) running SQL 2017 Dev edition.

I have installed VS2015 with R Tools. I am running the modeling_main.r script from inside VS .

The script stops at the same place, every time I have tried. Below is the screen error messages:

Error in rxCompleteClusterJob(hpcServerJob, consoleOutput, autoCleanup) :
No results available - final job state: failed
[1] "Step 4: Training, Scoring and Evaluating."
Error in .nextMethod(.Object = .Object, ... = ...) :
object 'column_info' not found
[1] TRUE
Warning message:
In .local(src, ...) :
The datasource is not open yet.

Any assistance would be appreciated. I did edit Step 1 with the ServerName and security creds. That is the only items I have changed. Would the "R" issue of having spaces in the working directory name account for this? Before I changed ANYTHING, I would like to hear from someone on here.

Thanks.

Insensitivty to recontactPeriod Variable

Problem : Changing the variable of recontactPeriod In the range of 0 to 10000000000 does not show any differences on ADR-AFPR or VDR-AFPR curves at all.

Data Input: output of the unit "Score Model" in Azure ML Studio Step 4: Model Training and Evaluation [1].

Code : ExecuteRScript in [1].

Image1: ADR with the x-axis between 0 and 10.
Image2: ADR with the x-axis between 0 and 200.
Image3: VDR with the x-axis between 0 and 10.
Image4: VDR with the x-axis between 0 and 100.
Image5: VDR with the x-axis between 0 and 200.

Result: The very same curves appear on all images.

Request: Please fix this bug to make ADR,VDR,AFPR curves vary according to different recontactPeriods.Thank you.

ExecuteRScript.zip

[1] https://gallery.azure.ai/Experiment/Online-Fraud-Detection-Step-4-of-5-train-and-evaluate-model-2

Don't Understand Code Output

colnames(perf.df) = c('ADR','PCT NF Acct','Dol Frd', 'Dol NF', 'VDR', 'Acct FP(recontact period)', 'PCT Frd', 'PCT NF','AFPR','TFPR' )

What do these columns name Acrynoms stand for? i.e What is PCT NF Acct?

Stuck at executing Power Shell Scripts

I have encountered issues while trying to execute the power shell scripts. It pops up some errors.
Not able to even install the import-module.
I have attached the log. Appreciate if someone could help!!

PS>TerminatingError(Import-Module): "Could not load type 'System.Management.Automation.PSSnapIn' from assembly 'System.Management.Automation, Version=6.0.2.0, Culture=neutral, PublicKeyToken=31bf3856ad364e35'."
Import-Module : Could not load type 'System.Management.Automation.PSSnapIn' from assembly 'System.Management.Automation, Version=6.0.2.0, Culture=neutral, PublicKeyToken=31bf3856ad364e35'.
At C:\SetupVM.ps1:52 char:5
setup_log.txt