Cases of fraudsters illegally accessing digital loans from fintech platforms in Africa have been on the rise over the last couple of years. According to Mr. Chris Akolo, Regional Business Development Director at JuicyScore, online fraudsters are now using highly sophisticated software to access digital loans without the fintechs detecting them.
“We have recently noticed a significant increase in online fraud in the regions of our operation. For example, the number of randomizers has increased from 0,1% to 3,5%. Randomizers in one of the fastest-growing online fraud types and there is no way to detect it apart from using alternative data-based solutions.’’ Chris says.
‘’We are speaking about the use of special software by fraudsters, also known as randomizers. The purpose of such software is to thwart existing digital device fingerprints and pass off the same device from which the fraudster applies for a loan online as a new one every time. Thus, a fraudster can take out a loan from the same device an unlimited number of times, changing only the borrower’s data, while the financial organization’s security system will treat each application as unique.”
To cope with the identification of randomizers, Mr. Akolo notes that a set of technologies and algorithms for detecting various kinds of device anomalies will help to identify new high-risk devices and filter them out in the early stages of the loan pipeline.
“Clearly, digitalization allows us to conquer new heights, gain access to new customers and reduce operating costs. However, such a situation also creates rather a rich environment for fraudsters. Many financial industries have to face such problems and suffer from losses connected with fraud every year. We help not only to minimize fraud, reducing it to a trickle, but to help achieve better financial results – approve more loan applications and reduce risk applying our high-risk markers to decision making system.”
As a result, JuicyScore which entered the Kenyan market recently provides the access to the tools that help in preventing fraud, reducing risks, and increasing the availability of online financial products. The anti-fraud solutions provider does this via device authentication technologies and user behaviour analysis
“JuicyScore is an easy solution to detect payment fraud. In JuicyScore you can reduce risks in your online business easily and effectively. We do not utilize sensitive personal data or direct consumer identifiers. We analyze more than 50.000 data points and by using machine learning we provide an anti-fraud score along with a data vector of about 200 predictors important for anti-fraud and credit scoring via our API. JuicyScore is compliant with GDPR, current, and perspective regulating rules and security policies of browsers and operational systems. On top of the data vector provided by the API, we help clients to build customized scores and provide consulting on score modeling. If you implement our solution, you can expect a 10X ROI and a Gini increase of 5-20 points.”
Meanwhile, Mr. Akolo confirms that Credit Score is here to stay and it’s the only way for financial institutions to price risk.
“Credit score is the best prediction of a customer credit behavior, such as how likely a customer is going to pay a loan back on time, based on information from his/her credit reports. With JuicyScore parameters, you can create a basic range score, which may be used as an analogue of credit risk score, which adds more value to your decision engine. With JuicyScore parameters, we can complement your credit process by providing alternative data that will improve your decision-scoring engine.”
For basic range scores, which may be used as an analogue of credit risk score, Mr. Akolo says they can do that for thin files or new credit customers for whom they lack information and therefore increase their acceptance rate.