Re: [Dev] deep neural network for detect frauds

2016-06-28 Thread Damith Wickramasinghe
Hi Tharindu, Related mail is for the analytics we did for IS authentication related scenarios. Relevant instrumentations are done in [1] in IS 5.2.0 to publish data to DAS side. You can check with pulashi/hasintha to get more insights of what has been done on those. Ill attach the basic UI design[

Re: [Dev] deep neural network for detect frauds

2016-06-27 Thread Asantha Thilina
Hi Nirmal, As tharindu mentioned i would be planning to gather user identity data through the AbstractEventListener then those data will be used to train my model Thanks, Asantha On Mon, Jun 27, 2016 at 9:26 AM, Tharindu Edirisinghe wrote: > Hi Nirmal, > > The data is not in hand right now.. b

Re: [Dev] deep neural network for detect frauds

2016-06-27 Thread Tharindu Edirisinghe
Hi Nirmal, The data is not in hand right now.. but we can assume we have data. Currently in Identity Server, it does not publish security related events such as login, logout, password change etc. What Asantha would do is write a Listener ( i.e extend AbstractUserOperationEventListener) and for

Re: [Dev] deep neural network for detect frauds

2016-06-27 Thread Nirmal Fernando
Seshika implemented a fraud detection toolbox using Markov chain models (using real-time siddhi queries) [1]. API-M Analytics product uses Markov chain model to detect abnormal resource access patterns. In WSO2 ML, we have implemented a clustering based anomaly detection algorithm [2]. [1] http:/

Re: [Dev] deep neural network for detect frauds

2016-06-27 Thread Tharindu Edirisinghe
+DamithN, Seshika, Nirmal @DamithN - I found the mail thread [1] bit similar. Are there any other reference to the work you've done for that ? @Seshika, Nirmal - Do you guys have any input for the work Asantha is trying to do ? He is a GSoC student that I mentor this year. Appreciate if you can