Hi!

My previous/alt account is yetAnotherUser@feddit.de which will be abandoned soon.

  • 1 Post
  • 208 Comments
Joined 1 year ago
cake
Cake day: June 1st, 2024

help-circle





  • The idea of anomaly detection is to project some input onto a (high dimensional), numeric output. From the training data alone, you can then see where the projections are clustered and develop a high dimensional “boundary” where everything within is known and good and everything outside is unknown and possibly bad. Since orders come in relatively slow, a human would be able to check for false positives and overwrite the computer decision.

    By the way, an ideal training set is preprocessed and has duplicates removed and new orders added by recombining parts of individual orders.

    For example, if we have 3 orders:

    • (Hamburger, Fries)
    • (Hamburger, Fries)
    • (Cheeseburger, Sandwich)

    We could then create the following set:

    • (Hamburger)
    • (Cheeseburger)
    • (Fries)
    • (Sandwich)
    • (Hamburger, Fries)
    • (Hamburger, Cheeseburger)
    • (Hamburger, Sandwich)

    And so on, and so forth. A naive variant is just taking the power set of all valid orders.



  • There are machine learning algorithms for anomaly detection though. They actually work decently well because exploits like this do in fact differ significantly from regular orders. Because they assume all anomalies are attempted exploits, their false negative rate is rather low while their false positive rate can be a bit higher.

    Taco Bell has the capability to create a decently large training set from all recorded orders (which must all be valid and non-malicious) so they shouldn’t have too many issues developing this model.

    If an anomaly is detected, make a human verify it is indeed an irregular order.






  • I would be very impressed if he surgically removed his own legs. I mean, there is a lot of tissue and bone to cut through. That’s not easy to do by yourself. But if that’s the case, that’s where the fraud aspect could come from.

    Also, is that a thing? “Disability by choice” so you get a lower payout? But even if, wouldn’t that be paid by some other insurance - like a specific disability insurance rather than your typical health insurance? At least in Germany the latter is very much different, health insurances only pay for treatments, recovery and prevention.

    The lie about the cause of the injury must somehow be related to the payout, otherwise I can’t believe how it would constitute fraud. Still, this is really confusing because private health insurances usually cannot decline/reduce claims due to intentional injury.



  • I don’t understand this story. It’s really badly presented:

    Hopper dishonestly made a false representation to Aviva and Old Mutual Health that his “legs had been amputated because of illness rather than self-inflicted injury”, the court heard

    Aviva is a private health insurance, Old Mutual Health doesn’t seem to operate in the UK, only in Kenya, Rwanda and South Africa? Either way, don’t insurance companies legally have to pay even for treating self-iflicted injuries requiring amputation?

    In April 2019, he used dry ice to freeze his legs to the extent they were no longer viable and required amputation.

    The amputation had to happen, else he would have died. Hell, I’d even argue the freezing occured due to mental illness so he misrepresented it only by claiming the amputation was physical illness. How is the cause even relevant for a health insurance?

    After the amputation, he made claims to the insurers that resulted in payouts of £466,653.81. He spent the money on a campervan, a hot tub, wood burner and building works.

    These are health insurances. Not life insurances or similar that would pay you for losing your legs. Don’t health insurances just cover the treatment (amputation), recovery and prosthetics? Sure they can get expensive - a six digit figure seems like a lot still but not fully implausible - but why would you get a “payout”? Health insurance would only cover bills.

    Surely it can’t be insurance fraud to harm yourself and then make an insurance claim for the recovery, right? Otherwise literally everyone who survived a suicide attempt would have to cover all associated expenses.

    So where did the fraud part come from?