Police in Spain Are Using Artificial Intelligence to Investigate Insurance Claims

[cageymaru]

The police force in Spain is using a tool with over 80% accuracy that can identify false insurance claims based on the description of the perpetrator, types of items listed, finer details of the incident and more. The Veripol software uses machine learning and artificial intelligence to identify false claims to keep the police from wasting their time and effort. Words such as iPhone and Samsung will alert the system of a possible false claim whereas bicycle and necklace are correlated with true crimes.

VeriPol is partly based on a process known as natural language processing -- a branch of artificial intelligence that helps computers understand, interpret and manipulate human language. For example, the computer tool uses algorithms to identify and quantify various features in text, such as adjectives, acronyms, verbs, nouns, punctuation marks and numbers and figures. Historical police reports that were known to be false have been fed through VeriPol so that it could code each one and begin to 'learn' the specific patterns.

 

[clockdogg]

We can be happy that the internet police don't use unnatural language processing on [H] forums. Yet. Until then... Nanoo Nanoo!

 

[masquap]

And cops will begin to believe this magical technology knows all and any time it pops out with a “no this isn’t a crime” they’ll go in with bias or not investigate at all because they don’t understand what AI is.

I don’t know what’s worse, sales people giving impossible views of technology (cloud, blockchain, AI), or the idiots who believe them and can’t see it for what it is (someone else’s computer, a slow database, an efficient algorithm).

Nuance is lost in an era of instantaneous information and split second attention spans

 

[seanreisk]

Huh. So, at least 20% of the time the police aren't going to bother investigating your stolen property. Statistically, that should be an improvement.

 

[theBrownLlama]

you know whats is the most often given advice by the police on stolen goods = you will probably never see it again.

and can you imagine if a victim bought a replacement, then the AI flagged the initial theft as a bogus insurance claim? And considering how things works,they will never inform you of that update.

 

[Tsumi]

California doesn't even want to bother investigating theft anymore. And they won't let you defend your property either.

 

[daglesj]

I worked in car insurance in the mid 90's. I can tell you Ray-Ban made their fortune not from people buying their products but people saying they had and insurance companies buying new pairs that were supposedly stolen from their cars.

 

[SvenBent]

80% accuracy that can identify false insurance claims
im not sure to be imrpessed or not about this number without somekind of bases

I can identify if criminals are going back to jail with 73% correctens just looking at picture of their mom pinky. ( You just say yes the will all the time then you will be 73% correct)
I hate how these kind of meaningless statics get thrown around in the media.