Bank customer transactions

[Aleyasen]

I am wondering is there any public bank customers (anonymized) transaction data?

[aqibsaeed]

I am also looking for one, related to fake complaints about ATM transactions.

[Aleyasen]

There is a dataset, that has real transactions but it doesn't have any label for fraud detection. It is Berka dataset available as part of PKDD'99 Discovery Challenge. It is real anonymized data from Czech bank. http://sorry.vse.cz/~berka/challenge/pkdd1999/data_berka.zip Data description: http://lisp.vse.cz/pkdd99/berka.htm

UPDATE: It seems the link for data description doesn't work anymore, so please use this link from WebArchive: https://web.archive.org/web/20161019192412/http://lisp.vse.cz/pkdd99/berka.htm

Also, I found these Python Notebooks that did some analysis on the data that might be helpful: https://github.com/justinng1/berka

[aqibsaeed]

Awesome man! Thanks alot

[mcapelle]

It seems, a password is needed to decryt the data. Does one of you has (still) the decrypted data or the password?

[Aleyasen]

@elieArron1 That's great. Can you share the dataset?

[aqibsaeed]

@ElieArron1 Would you also highlight, what kind of modelling purpose it is useful for? Are there any annotations for fake transaction etc? What does MCC code represents?

[harrycheese]

@aqibsaeed

Mcc means merchant category code. Each code represents a category viz. Automobile, restaurant, convinience store etc. Depending on bank to bank / transaction processor the category varies

[RJDavie]

Thanks @harrycheese I wish everyone would use SIC codes though, they are standard pretty much across the world. #datawoes!

[harrycheese]

Credit card and debit card companies have been using it since ages. It's built in their legacy systems. Changes to it means cost :)

Anywhoo.. @ElieArron1 can u share this data, will be useful to mine it. Also which country's bank is it and is it a huge bank or mid size bank or small bank.

On 06-Feb-2018 5:40 PM, "Rob Davie" [email protected] wrote:

Thanks @harrycheese https://github.com/harrycheese I wish everyone would use SIC codes though, they are standard pretty much across the world. #datawoes!

— You are receiving this because you were mentioned.

Reply to this email directly, view it on GitHub https://github.com/awesomedata/awesome-public-datasets/issues/234#issuecomment-363403592, or mute the thread https://github.com/notifications/unsubscribe-auth/AiVOTwEr3xdwojfegF-VoLpsJBm1ou6mks5tSEEmgaJpZM4JGVnn .

[mcapelle]

@ElieArron1 I would be interested in a 10 customers sample of the (1) dataset to evaluate it. How can you send it to me? Thanks.

[kjmckenzie]

@ElieArron1

Can I also get a copy of the dataset?

Thanks!

[ayushsingh244617]

can i get the dataset too?

[qinbill]

@ElieArron1 [email protected] I am work on graph pattern mining in financial applications. Could you share me the data?

[LPalazzo]

@ElieArron1 can I also get a copy of it? I would like to use generalized linear methods in a time series framework to model transactions over time

[ayushsingh244617]

I need it for educational purpose.im trying to study the auditing system in banks and for that I need a data set

On Feb 28, 2018 3:25 PM, "L" [email protected] wrote:

@ElieArron1 https://github.com/eliearron1 can I also get a copy of it? I would like to use generalized linear methods in a time series framework to model transactions over time

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/awesomedata/awesome-public-datasets/issues/234#issuecomment-369186833, or mute the thread https://github.com/notifications/unsubscribe-auth/AhmAIjHY361hU7VR2wF-I3L8gI-yY1COks5tZSKLgaJpZM4JGVnn .

[ctacampado]

@ElieArron1 would also like to have a copy of your dataset to do prediction and classification for a prototype of a financial application. [email protected]

[leonardosapiras]

@ElieArron1

Hi, I am doing some academic researches in the university where I teach. Could you share this dataset with [email protected] ?

Thanks!

[ayushsingh244617]

This is my email

On Feb 28, 2018 9:04 PM, "ElieArron1" [email protected] wrote:

@LPalazzo https://github.com/lpalazzo @ayushsingh244617 https://github.com/ayushsingh244617

Give me your emails we can discuss it

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/awesomedata/awesome-public-datasets/issues/234#issuecomment-369276289, or mute the thread https://github.com/notifications/unsubscribe-auth/AhmAItTt7phnf457_srtGMkyZfUaEYA5ks5tZXGdgaJpZM4JGVnn .

[thatdeep]

@ElieArron1 Hi! I am starting a research on user behaviour modeling and graph-based approaches for finding customers with similar transaction patterns. Having real-life data would be good to play around and tune methods. Could you share your dataset with me too? My email is [email protected]

[LPalazzo]

@ElieArron1 [email protected]

[hyrahul]

Hey, I don't have any kind of dataset that you are looking for why don't you google it about that !!!

Thanks

On Tue, Mar 6, 2018 at 3:44 PM, L [email protected] wrote:

@ElieArron1 https://github.com/eliearron1 [email protected]

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/awesomedata/awesome-public-datasets/issues/234#issuecomment-370731829, or mute the thread https://github.com/notifications/unsubscribe-auth/Aix1m23xkX_1dhKD4erUjDTN6jM6kpodks5tbmFqgaJpZM4JGVnn .

[aayush209]

@ElieArron1 Can you share the dataset with me , I need it for fraud detection using vizualisation . Email - [email protected]

[ayushsingh244617]

My email Id is [email protected]

On Wed, Feb 28, 2018, 9:04 PM ElieArron1 [email protected] wrote:

@LPalazzo https://github.com/lpalazzo @ayushsingh244617 https://github.com/ayushsingh244617

Give me your emails we can discuss it

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/awesomedata/awesome-public-datasets/issues/234#issuecomment-369276289, or mute the thread https://github.com/notifications/unsubscribe-auth/AhmAItTt7phnf457_srtGMkyZfUaEYA5ks5tZXGdgaJpZM4JGVnn .

[Sergionethechamp]

Hello @ElieArron1 I would love to have access to the dataset as well Conducting research and building model on spending patterns and credit relations My email is [email protected] Happy to exchange in PM Thx!

[csywchen]

Hi @ElieArron1, I am conducting some research work on anomaly detection over customer transactions. Would you please share the dataset with me? My email is [email protected]. Thanks a lot!

[mcapelle]

@ElieArron1 Hi, I would like to study expenses patterns thanks to that dataset. Can you send it to [email protected]?

Thanks.

[alexjslessor]

Hello I am trying to build fraud detection models using RNN's in tensorflow could I have it as well please? You can send it to [email protected]

On Fri, Mar 16, 2018, 11:21 AM Maxime Capelle [email protected] wrote:

@ElieArron1 https://github.com/eliearron1 Hi, I would like to study expenses patterns thanks to that dataset. Can you send it to [email protected]?

Thanks.

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/awesomedata/awesome-public-datasets/issues/234#issuecomment-373746675, or mute the thread https://github.com/notifications/unsubscribe-auth/AVuZy8Js0SffbnSPa8uc0kHf0AXbj9_Eks5te9iBgaJpZM4JGVnn .

[theclanks]

Hi @ElieArron1, I am starting a research on debt collector scores, could you share your dataset with me too? My email is [email protected]

Thanks.

[Frank-Tsai]

HI @ElieArron1 I'm currently working on research about churn prediction, could you please share a copy with me? Here's my email [email protected]

Thanks a lot

[matheusalagia]

Hi @ElieArron1 I would love to have access to the dataset as well Conducting research and building model on spending patterns and credit relations My email is [email protected]

Thanks a lot!