Mr. Bevis has a face book link where he claims to be a Labour supporter and have studied Social and Political Science at Cambridge!!

I wonder if that is where they taught him that “It is actually rather difficult to get into serious debt if you are only borrowing small amounts.” and “The social risks of “pay day loans” are low..”

BOLLOCKS!

So, is Mr. Bevis merely a false identity? Yet another pretend person who works for Wonga and is leaving messages to promote the company? Or, is he real and maybe did study politics but then copped out when he got a job for Wonga and started spouting nonsense to promote loan sharks?

Clearly hard times haven’t hit your household.

I’m sticking with http://www.lendingclub.com. My loan portfolio there is yielding close to 9% after defaults. Also, today http://kiva.org announced they are launching microlending in the US.

this company is encouraging bad financial practices. not cool. Accel, Greylock I’m looking at you

I frequently post technical information here at TC, just to share knowledge with other developers, but sometimes I frequently see unnovation startups (in Umair Haque’s words) and it is something that I am curious to know about in how those venture investors get to pour money into such startups.

Wonga developers may be interested in checking out the following paper (if it isn’t the decision engine that you’re currently have) on using FIS (fuzzy-logic inference system) in loan decision-making. Wonga’s use of slides (on their main page) to indicate variables as amount and duration fits perfectly with the paradigm of FIS. FIS is a universal approximator, exactly as ANN (artificial neural network) is and they’re structurally the same (ie, FIS & ANN), however computationally different. You can design a MIMO (multiple inputs multiple outputs) or MISO (multiple inputs single output), where the latter is the one I suspect that you’re adopting if not FIS but ANN or SVM (support vector machine). The advantage of FIS over ANN & SVM is that you know your decision rules as a priori.

Abstract:
——-
Credit risk has always been a major concern for banks and other financial intermediaries. The uncertain domain of risk assessment has long been in need of a reliable and consistent system to help simplify the decision making process. In recent years fuzzy logic technique has been in its wide-ranging use in modeling of uncertainties, vagueness, impreciseness and the human thought process. This paper attempts to develop a credit risk analysis system based on the fuzzy logic using two structures: traditional fuzzy reasoning of all inputs that map to one single output and stage-wise fuzzy reasoning of input parameters in accordance with their importance. The analysis of case studies shows the consistency and effectiveness of the second approach in making correct decision.

Title:
—-
Loan risk analyzer based on fuzzy logic

The authors of the paper cited above are from School of Informatics at Bradford University, so it would very convenient to ask them a question since they’re in the UK.

I have used both Mamdani & Sugeno inference algorithms in my FIS for various previous projects and I think that Mamdani is the one that best suits your application rather than Sugeno. There are other inference algorithms for FIS that have appeared in the literatures over recent years which are more advanced (ie, more accurate), but their application domain mainly for control systems, however I am sure that they can be used in other areas such as decision support system for online loan such as yours.

http://blogs.harvardbusiness.org/haque/2009/06/wonga.html

http://blogs.harvardbusiness.org/haque/2009/06/wonga.html

I guess it is applicable in this case too (you want money fast – because you might not have credit – you pay more).

It’s shocking how successful this start-up could be but not surprising.

The need is out there, but there again there’s also a need for web 2.0 sites that can help someone buy heroin find a prostitute. I would not want to work in either one. And I probably wouldn’t want to work with any VC who is willing to back usury.

Sad day for Accel – I would have expect more from them.