Australian Bank Anonymizes and Releases Billions of Records
peoplelikeu.com.au
peoplelikeu.com.au
What is going on here? I am inclined to believe the data.
What this has really reinforced for me is the extent to which other people must spend their income as it comes in. It has also reinforced the importance of my friends, connections, values & personal knowledge. My friends who enable me to live a life that feels rich whilst, apparently, spending about 1/8th of what everybody else does.
I really am surprised. I was not raised frugally and if I want something and have the money, I generally buy it & I don't need more than I have.
- single does not mean no kids
- once you are in debt, you may have problems getting out of it (you spend a lot on credit repayment rates)
- does spending include investment? for example would a life insurance / retirement fund count towards "spending"?
Well, let's just call them, uh, Mr. X and Mrs. Y. So anyway, Mr.X would say, 'Marge, if this doesn't get your motor running, my name isn't "Homer J. Simpson."
Basically you just pick a few things like your age, salary and where you live, and then out of all of the people out there "like you", you're shown an average of where people like you tend to spend their money (travel, food, etc.).
Even if you spent a lot of time manipulating the data to try and get it to tell you one person's spending by category (assuming it were possible), the data would be relatively meaningless.
http://en.wikipedia.org/wiki/AOL_search_data_leak
Robust De-anonymization of Large Sparse Datasets http://www.cs.utexas.edu/~shmat/shmat_oak08netflix.pdf Regarding Netflix's competition: "We demonstrate that an adversary who knows only a little bit about an individual subscriber can easily identify this subscriber’s record in the dataset."
However after using the site and entering my demographics (all public properties) I could see that I was like 56 people in area; their base spending patterns did not reflect me at all and I felt like a snowflake. Sometimes big data makes you feel special.
At no time was I shown transactions, merely aggrigate figures in categories. No privacy issue here, keep being decent and ethical national bank!
- Name
- Phone
- Address
- Tax File Number (not unlike a US social security number)
I came to the same conclusion that its probably based on census data.
All identifying information had been removed/sanitised, they could tell from looking at the spending habits.
I disagree with your statement.
Ask that person to go and find my details, and they will surely fail. Because they know nothing about me, and the transaction history doesn't tell them anything... thus it is not 'identifying'.
We also took an extra step around setting a minimum uniqueness level of 'Less than 10' - so there won't ever be a scenario shown for 1/2/5 PeopleLikeU as queried in the comments below.
Hope you enjoy the experience - we really wanted to give the value of the data safely back to the people who created it to help you make more informed decisions on what, where and how much you spend.
Feel free to tweet me @jbewes or the team @Ubank, or even Facebook msg them facebook.com/ubank if you've any more queries.
Cheers, Jen :)
It says my expected house & home costs are $2000, which seems rather high for me. In London and here in Dublin, pretty much everyone my age (mid twenties) is in a houseshare, so we would pay that for the whole property, but split it three ways or so. Is housing just that much more expensive, or what?
Try using a 40?? postcode for Queensland.
They probably constructed a simple decision tree aggregate which is probably less than 10kb of data. I doubt anyone could extrapolate 10kb data into personalized details of an individual.