Re: Fraud management system implementation

[Sandy Ryza <sa...@cloudera.com>]

+user list
bcc: dev list

It's definitely possible to implement credit fraud management using Spark.
 A good start would be using some of the supervised learning algorithms
that Spark provides in MLLib (logistic regression or linear SVMs).

Spark doesn't have any HMM implementation right now.  Sean Owen has a great
talk on performing anomaly detection with KMeans clustering in Spark -
https://www.youtube.com/watch?v=TC5cKYBZAeI

-Sandy


On Mon, Jul 28, 2014 at 7:15 AM, jitendra shelar <
jitendra.shelar410@gmail.com> wrote:

> Hi,
>
> I am new to spark. I am learning spark and scala.
>
> I had some queries.
>
> 1) Can somebody please tell me if it is possible to implement credit
> card fraud management system using spark?
> 2) If yes, can somebody please guide me how to proceed.
> 3) Shall I prefer Scala or Java for this implementation?
>
> 4) Please suggest me some pointers related to Hidden Markonav Model
> (HMM) and anomaly detection in data mining (using spark).
>
> Thanks,
> Jitendra
>

Re: Fraud management system implementation

["jitendra.shelar410" <ji...@gmail.com>]

Thanks Sandy.

Shall I prefer Java or Scala for implementing the fraud management
system using spark?
If I use Java, will there be any performance degradation issues?

Regards,
Jitendra



--
View this message in context: http://apache-spark-user-list.1001560.n3.nabble.com/Re-Fraud-management-system-implementation-tp10787p10839.html
Sent from the Apache Spark User List mailing list archive at Nabble.com.