The fault is not in Excel, which is an excellent piece of software. All the problems identified are the fault of poor math.
After the London Whale trade blew up, the Model Review Group discovered that the model had not been automated and found several other errors. Most spectacularly,
“After subtracting the old rate from the new rate, the spreadsheet divided by their sum instead of their average, as the modeler had intended. This error likely had the effect of muting volatility by a factor of two and of lowering the VaR . . .”
It's not like programmers are immune from making such errors. You can put the wrong equation into a page of C or Java as you can onto an Excel spreadsheet.
> It's not like programmers are immune from making such errors. You can put the wrong equation into a page of C or Java as you can onto an Excel spreadsheet.
The difference is that programmers know they will make such errors and thus have developed tools, techniques and a culture that acknowledges the necessity for testing to find and eliminate bugs.
In contrast, I'd wager that less than 0.01% of financial Excel sheets has automated tests, and less than 0.1% has a written test plan. If you confront your typical "work-hard-party-hard" hotshot trader with demands for such, the response is most likely "Testing? I wrote it, I know it works, do you think I'm stupid?"
"The difference is that programmers know they will make such errors and thus have developed tools, techniques and a culture that acknowledges the necessity for testing to find and eliminate bugs."
LOL, seriously? How much software do you use every day that doesn't have bugs? Especially software that only gets used every now and then?
Yes, and that's despite all those efforts to reduce bugs. Imagine all the bugs found by tests going into production...
Or were you jsut put off by the phrase "eliminate bugs"? That wasn't meant to imply eliminating all bugs, just those the tests have found. And we all know they don't catch 'em all.
> It's not like programmers are immune from making such errors.
Too true. It wasn't that long ago that the programmers at The Knight Capital Group nearly sent the company broke with their $430 million programming glitch.
Except that wasn't a programming glitch, it was an operations glitch. They accidentally deployed a test trading partner for their real trading app to the real world.
So when I accidentally enter the wrong rate into the spread sheet everyone calls me an idiot and tells me I should leave the programming to people who know what they are doing.
But when a programmer I accidentally promotes test code to production, it's just an accident.
That is exactly the point the OP that I replied to was trying to make.
When someone else fucks they are stupid and they don’t know what they are doing, but when the coders fuck up it's always someone else that is at fault. Please give me a break!
Given that most spreadsheets only have one enrivonment (PROD), this class of error isn't likely. However, as the grandparent says, this means testing is equally unlikely.
After the London Whale trade blew up, the Model Review Group discovered that the model had not been automated and found several other errors. Most spectacularly,
“After subtracting the old rate from the new rate, the spreadsheet divided by their sum instead of their average, as the modeler had intended. This error likely had the effect of muting volatility by a factor of two and of lowering the VaR . . .”
It's not like programmers are immune from making such errors. You can put the wrong equation into a page of C or Java as you can onto an Excel spreadsheet.