Timeline for Credit card fraud detection - anomaly detection based on amount of money to be withdrawn?
Current License: CC BY-SA 3.0
11 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Oct 18, 2015 at 15:29 | comment | added | Tasos | @Giovanrich For this, you should ask on the Open Data StackExchange site opendata.stackexchange.com | |
| Oct 18, 2015 at 11:34 | comment | added | CN1002 | @Tasos One other thing, where can I hook up a sample database of a credit card accounts - one that looks similar to that of a real bank's? | |
| Oct 18, 2015 at 11:30 | comment | added | CN1002 | @Tasos I have read on how to find the lat and long of ATMs. I could implement this in my project but because of time left I have decided to classify my ATMs according to provinces in the country. This is not not a good idea but since its final year project and there is little time left. | |
| Oct 4, 2015 at 12:58 | comment | added | Kenan Zahirovic | Forget about "Seconds spent on ATM": Keep in mind that inside ATM banks usually have plain old PC connected to network (VPN). Now, one can imagine all sorts of possible hiccups, delays etc. Also, keep in mind that ATM has to connect to processing center and check available balance. Where is that center located, and how busy is in that moment can significantly affect response time. And finally, not all ATM have the same interface: for some models it takes 7 'clicks' to get money, while some models requires 10 'clicks'. | |
| Oct 3, 2015 at 12:16 | comment | added | Tasos | @Giovanrich Keep in your mind this answer about finding ATM's coordinates opendata.stackexchange.com/q/5640/505 | |
| Oct 3, 2015 at 12:04 | comment | added | CN1002 | Let me work on that first and see if I can get hold of those coordinates, I will get back to you thanks. | |
| Oct 3, 2015 at 11:41 | comment | added | Tasos | @Giovanrich If you could find the lat and long of ATMs, I would probably made classes from a radius of 50km or 100km close to those coordinates. | |
| Oct 3, 2015 at 11:07 | comment | added | CN1002 | Now I am following, and thanks for quick response. As for grouping , I was thinking to consider city and a unique code (each ATM has a unique code that helps to identify it). I was thinking to "hard limit" the ATMs, say for a city I could have a map showing all the ATMs, then I divide the map say in chunks of some area. Then, these chunks become my classes of ATMs, but its not sounding quite intelligent! How would I go about it? | |
| Oct 3, 2015 at 10:46 | comment | added | Tasos | The time between two withdrawals: Let's say that I made one on Thursday and one on Saturday. I had about 48 hours between the two of them. The time spend on the ATM. The seconds that I needed from the time I inserted my card to the time I took it back. For example, I needed 35 seconds to fill all the details on the ATM. As for grouping, it depends of what details you have. If you have lat-long, city, unique code etc. | |
| Oct 3, 2015 at 10:38 | comment | added | CN1002 |
Well, that is a good explanation indeed. I had missed two attributes, time between two withdrawals and seconds spent on the ATM for each withdrawal. As for the first feature, I am still finding some way of grouping my ATMs - Say in a town A I have ATMs A1, A2, A3,..,An. Now suppose a user regularly withdraws his money from ATM A1 - "that is his behavior", then if that user were to withdraw money from ATM A7, I would allocate a high score of suspicion to that transaction. The challenge is on how to group the ATMs or is the approach wise?
|
|
| Oct 3, 2015 at 8:44 | history | answered | Tasos | CC BY-SA 3.0 |