Can this computer tell if you will default on mortgage repayments?

[PTWhatAGreatForum]

After defeating an expert in Japanese chess, this computer program's next task is to figure out if you can make the payments on a new mortgage.
Heroz Inc., a small Japanese start-up whose engineers designed computer systems that were the first to defeat an active professional player of shogi, the Japanese version of chess, says it's now working on adapting its applications for the financial industry.
While Deep Blue became the first computer to beat a top chess player in 1997, the computer programming required to defeat a shogi master is even more complex than that required for conventional chess. That's mainly because the number of potential moves in Japanese chess is much higher, as shogi's rules on the reuse of captured pieces are more complicated.

http://www.nzherald.co.nz/business/n...ectid=11568550

[James.wu]

After defeating an expert in Japanese chess, this computer program's next task is to figure out if you can make the payments on a new mortgage.
Heroz Inc., a small Japanese start-up whose engineers designed computer systems that were the first to defeat an active professional player of shogi, the Japanese version of chess, says it's now working on adapting its applications for the financial industry.
While Deep Blue became the first computer to beat a top chess player in 1997, the computer programming required to defeat a shogi master is even more complex than that required for conventional chess. That's mainly because the number of potential moves in Japanese chess is much higher, as shogi's rules on the reuse of captured pieces are more complicated.

http://www.nzherald.co.nz/business/n...ectid=11568550

Hi MichaelNZ

First I have to say I am not an expert of AI or machine learning, but I have done a machine learning project at my own time just for fun. My project was simply using machine learning (neural network to be exact) to train my program to recognize numbers in an image.

I believe their machine is a lot faster than mine and their algorithm is a lot more advance than mine, but the principle is the same. To produce a reliable output, we need to feed in accurate inputs. And I think people's emotion / mindset play an important role in this. And I don't think there is a repeatable, reliable and scientific way to measure people's emotion / mindset. For this reason, I think this computer can do a OK estimate at the most.

James

[snobilo]

I agree with James, I'm half way through an Economics paper at university at the moment and one of the biggest things they stress is people are unreliable, you can do all the study and have all the stats but there's always a large fudge factor for people emotions.