JuicyScore is a global leader in anti-fraud and risk management solutions company that is headquartered out of Moscow, Russia, and is currently expanding operations to India. Founded in 2016, JuicyScore came into existence with an aim to help businesses prevent fraudulent activities and reduce the risk of threat. As of today, it offers its services in over 21 countries and has over 80 clients, across the globe, from industries like banking, e-commerce, travel, insurance, etc.
Mikhail Marchenko is the Co-Founder & CEO of JuicyScore. He spared time to talk about the company’s vision and roadmap with Team IT-Voice in a recent interaction. He also answered questions related to digital lending frauds and related subjects. Here is the full interview:
Prateek: What are some of the trends observed in India vis-a-vis globally with respect to digital lending frauds?
Mikhail Marchenko: The recent spurt in the popularity of online lending platforms, either web or mobile occurred all over the globe and India is no exception. Many countries are facing problems connected with the increase of online fraud. However, there are a number of factors that make India stand out in this regard. According to the World Bank, India ranks as the second country in the world with an unbanked population: there are over 190 million people that do not have access to traditional credit sources. Also, there is a large number of people who live in rural areas where there are no banks or ATMs.
Nevertheless, well-organized digital infrastructure along with high-speed internet services make a remarkable effect. Microfinance institutions have their own position in the financial services of the Indian market and they have become a significant institution that is capable of solving many social and economic problems.
A large number of loans inevitably lead to an increase in online fraud due to personal data breaches and some other reasons, so it can become a serious problem for online lenders. Taking into account all these factors, we can say that the Indian market needs new risk-management solutions that will protect online businesses from fraud and massive data breaches in order to avoid repetitional risks.
Prateek: How is the Indian market different from the rest of the world?
Mikhail Marchenko: Digital lending in India is growing really fast: it reached 75 billion USD in 2018 and its value will increase to around 350 billion USD by 2023. Lending tech startups are innovating with models such as sachet credit and “buy now pay later” products for the Indian consumer. India’s digital lending wave is fueled by massive demand from the consumer side as income growth has been weak in the past year. The growing role of credit is best indicated by the fact that on average 5,6 million credit cards are being issued annually.
Additionally, the government is actively investing in transitioning from branch-based banking to digital banking. Therefore, the pandemic-fueled transition to digital lending in India’s technologically mature and person-focused market led to the need for various anti-fraud solutions as a part of the design architecture intending to detect the stemming attacks in real-time, rather than repairing the damage.
Prateek: What are some of the common practices to avoid online payments scams worth billions of dollars?
Mikhail Marchenko: Based on our experience in 21+ countries, we can say that there are over a thousand patterns of fraudulent behavior. However, there are a few key components that online companies should concentrate on to protect the business from online fraud:
- Protect your online infrastructure. Often this can be done simultaneously with the provider of this infrastructure – for example, when placing your website to data centers, ask for an effective solution that helps to prevent DDoS attacks
- Limit access to your client’s personal and sensitive data. Please note that often, personal data is not needed for vendors’ subtasks, you can always find the solution based on alternative user data
- Determine a plan of action in the case of a partial failure of the online infrastructure or a mass fraud attack (decrease in the level of approval, the introduction of additional methods of user verification, etc.)
- Expand your dataset and technological stack
- Don’t forget that it’s really important to train your risk-management specialists; they should be head and shoulders above the scammers they are fighting
Prateek: Please tell us more about JuicyScore’s cutting-edge anti-fraud tools and features like anti-fraud score and device fingerprinting.
Mikhail Marchenko: We believe that privacy is the key to next-generation internet products. Our core advantage is that we do not use, store, process, or deal with any kind of borrowers’ personal data, which has a certain positive impact on the clients’ reputation. We analyze data flow and our API provides an anti-fraud score along with a data vector of about 200 predictors. We analyze 50,000+ parameters such as behavioral data, device data, internet connection, and device software data to reduce the level of credit risk significantly.
As for the device fingerprinting technology, we identify the device and provide a stable fingerprint regardless of the channel the applicant used to apply for a loan, our device fingerprint is one of the most stable over time and resistant to various anomalies.
Practically online fraud consists of rare events which do not follow the Gaussian distribution, and therefore such events cannot be processed by ordinary statistical tools. But JuicyScore can work with rare events or the so-called “anomalies”. The basic feature of a rare event is not only that it has a low frequency of occurrence, but also the fact that the occurrence of such an event is usually accompanied by significant consequences. In the finance industry, this could be a case, when an event leads to a high risk of loan default or loss on the insurance contract. Being one of the risk assessment and fraud prevention solutions, JuicyScore uses deep machine learning algorithms to develop variables. Examples of such variables are Index variables (or variables of the IDX type in our standard data vector), which, on the one hand, extract useful information value from the factors underlying these Indexes, and, on the other hand, make it possible to level out data collection related issues and the insufficiency of useful values of each of these factors. Indexes allow using the synergy of many such factors that can be used as separate variables, reflecting the anomalies of one aspect of the Internet connection, for further research.
Prateek: How has the pandemic changed the landscape globally and in India?
Mikhail Marchenko: It’s true, the Covid-19 pandemic has had a crucial impact on the financial sector: it has become obvious that going online is an inevitable and essential condition for business development. Pandemic has affected all countries, increasing the development speed of many companies which have only started to do business online. The consequences of the pandemic in the context of online fraud are really well known. A lot of people choose online channels more often when using financial services, and, according to experts, many of them would not return to their previous habits and would use financial services online in the future, despite the end of strict measures connected with the lockdown.
The second change is also related to the fact that due to the pandemic a large number of users switched to the online channel as the main source of obtaining financial services. In fact, online channels allow companies to reduce operating costs significantly, as well as to gain access to a wider audience on the one hand, and not to risk one’s health speaking about the clients on the other hand. However, today we are witnessing a really big leakage of personal data day by day. That is why the secure storage of user data is becoming one of the most important issues in today’s online business in India.
Prateek: Please tell us more about the latest generation of JuicyScore API.
Mikhail Marchenko: The new product generation has a range of significant outstanding advantages from the perspective of information value and efficiency for our partners. Data vector information value was increased by more than 30%+: we added 28 new attributes to the output data vector, some of which are unique. Many attributes were created as a result of our research and some of them have already been patented under applicable law. Without false modesty, our output data vector is the most comprehensive among all the existing solutions for application fraud prevention and account protection at the moment. Also, we ultimately redeveloped and enhanced the technological stack of malware detection algorithms. The stack now includes 350+ technologies.
Also, we expanded the stack of device authentication technologies, increasing their number up to 31 in the new JuicyScore API generation, which makes our device fingerprint even more stable over time and more resistant to various anomalies. It turns out to be really important in terms of highly competitive and high-risk level markets.
For any such interaction opportunities, you may write to us at [email protected].
