The Monetary Authority of Singapore (MAS) and The Association of Banks in Singapore (ABS) today awarded 12 FinTech companies a total of SG$1.2 million divided for 12 different companies at the Fintech Awards, which took place at the third Singapore FinTech Festival.
This time around, the awards featured a greater ASEAN representation, with a focus on financial inclusion, spanning different business areas like credit-scoring, mobile security, anti-money laundering, and digital investment. The Fintech Awards, supported by PwC, recognises innovative FinTech solutions that have been implemented by FinTech companies, financial institutions and technology companies.
This year, 40 finalists were shortlisted from more than 280 global submissions including the companies who participated in the ASEAN PitchFest6. The winners were selected by a panel of 17 judges who represent a cross-section of international and local experts from the private and public sectors. The entries were evaluated based on four criteria: impact, practicality, interoperability, and uniqueness and creativity.
The panel of judges includes representatives from Accenture Technology, Allianz, AMTD Group, Credit Ease, DBS, Deloitte, GIC, Grammen Foundation India, HSBC, Insignia Venture Partners, Jungle Ventures, Mastercard, The Boston Consulting Group, The Disruptive Group, True Global Ventures, UOB and Vertex Ventures.
ASEAN Open Award
First Place: LenddoEFL (Philippines)
The company wants to provide people access to powerful financial products without exorbitant costs, quickly and more conveniently by using AI and advanced analytics to bring together digital and behavioural data. This helps lenders serve the underbanked. LenddoEFL has provided credit scoring, verification and insights to 50+ financial institutions, serving over 7 million people.
Singapore, 14 November 2018… The Monetary Authority of Singapore (MAS) and The Association of Banks in Singapore (ABS) today awarded 12 FinTech companies a total of S$1.2 million at the FinTech Awards, which took place at the third Singapore FinTech Festival.
ASEAN Open Award
1st place – LenddoEFL (Philippines)
2nd place – SQREEM Technologies (Singapore)
3rd place – Finantix Asia Pacific (Singapore)
ASEAN SME Award
1st place – FinAccel Teknologi (Indonesia)
2nd place – Katipult (Thailand)
3rd place – MoneyMatch Transfer (Malaysia)
Singapore Founder Award
1st place – CCRManager
2nd place – Cynopsis Solutions
3rd place – Thin Margin
1st place – Everspin (South Korea)
2nd place – Naffa Innovations (India)
3rd place – Keychain (Japan)
By Brett Elliot, Director of Product, LenddoEFL
Lenders often use loan officers, promoters or other types of agents to sell loans, financing, and credit cards. This can be an effective way to acquire new customers but there is a big risk in this approach. Agent incentivisation plans will make or break your bottom line. Good incentive plans lead to large, healthy portfolios, but bad ones lead to fraud, default and chargebacks. We’ve worked with lenders all around the globe and have seen both good and bad strategies. Here are some of the best and worst.
Worst agent incentivisation strategies
Paying per applicant
When your goal is to get new customers, a very simple approach is to pay agents for each customer that applies. Obviously, the more people into the top of the funnel, the more customers you will get right? Not exactly. Agents will optimize for their commissions. First they will go after good borrowers, then they will go after anyone. And some of them will realize they can make up fake applicants so they don’t have to go after anyone at all. If you simply try to optimize the number of applications, you will get a lot of applications, few disbursements, and even fewer good customers. This may seem obvious but we know of a large commercial bank in South America that did this and they had a huge problem finding good borrowers.
Paying per approval
Since paying per applicant does not work, the next logical step is to pay per approval. This way your agents can still acquire as many people as possible but you keep the portfolio healthy with controls in your approval process. This is the most common approach to incentivizing agents but it does create a perverse incentive for the agent to game the system in order to get more approvals. For example, one lender in Mexico was offering credit cards to college students. At some point the agents discovered that the only criteria for approval was that the applicant be under 26 years old. This caused a huge spike in fraud as the agents signed up anyone they could find that met the age criteria. If you are going to pay per approval, the controls you set must be strong and difficult to game. See below for recommendations about how using technology can help.
Paying a commission higher than the loan interest
A subtle but often overlooked problem with any incentive plan is paying an agent a higher commission than the loan interest costs. We know of a digital bank in South America that does this and they are experiencing a type of perpetual fraud. In this scheme, the agent fills out an application using a stolen identity. Then he takes out another loan using a different stolen identity and pays back the first one with it. He repeats this process over and over, collecting his commission. This is only possible if the commission is higher than the interest rate so keep that in mind when making your commission schedule.
Good agent incentivisation strategies
Paying a percentage of the money collected
One approach that aligns the agents and lenders is to pay the agent a percentage of the money collected. This incentivizes the agent to sign credit worthy new customers but also to follow up with the customer and make sure they make their payments. We sometimes call this the “MFI model” because of how effective some MFIs have become by using it.
Withholding payment for a certain period of time
Paying a percentage of the money collected doesn’t work for credit cards, but a strategy that does is to withhold payment for a certain amount of time. For example, one financial institution we know of pays the agent a little when the credit card is activated and then the remainder in 4 months so long as the card is not in arrears.
Combine several incentives
There is no one size fits all for any company and often combining different incentives works really well. The companies with the healthiest portfolios that we have seen do this. For example, a large MFI in Mexico pays their agents a very low fixed salary, plus a percentage of the amount disbursed and a percentage of the money collected.
Use technology to strengthen the controls
If you are certain that your controls and risk models are effective at weeding out the bad borrowers, then paying per approval is a reasonable approach. But how certain are you especially if your customers do not have much credit history? Technology can definitely help in this area. Using highly predictive alternative credit scores is a great start. Be sure to ask the vendor what controls are in place to detect agent fraud since they will try to game the system. At LenddoEFL, our scores are backed by our Score Confidence system which looks out for suspicious loan officer behavior and coaching as well as other signs of fraud.
The end goal is to reward agents for portfolio growth and portfolio quality. Lenders that limit the number of new clients added per month, maintain a solid portfolio of recurring clients, and combine different incentives for compensating agents, seem to have the largest and healthiest portfolios.
Written by Rodrigo Sanabria, Director Partner Success, Latin America
On a prior post by Carlos del Carpio (“The Economics of Credit Scoring”), we discussed the business considerations to assess the merit of a risk model. In this post, I will address how a good origination model impacts the bottom line of a company’s P&L.
These principles may be adapted to look into other types of models used at later stages of a loan life, but on this post we will only address loan origination.
From a business point of view, an origination model is a tool that helps us aim at the “sweet spot”: where we maximize profits. A simple way to think about it is as a trade-off between the cost of acquisition (per loan disbursed) and cost of defaults (provisions, write-offs): The higher the approval rate, the lower the cost of acquisition, but the number of defaults go up.
How do we go about finding the sweet spot? I’ll try to explain it below.
A good model has a good Gini. A “USEFUL” model creates a steep probability of default (also known as PD) curve – we usually refer to it as a “risk split”.
Figure 1 shows the performance of a model based on psychometric information used by an MFI. The Gini (not shown in the graphic) is pretty good (0.28). The risk split is great: the people in the lower 20% of the score ranking are about 9 times more likely to default than those in the top 20%.
Knowing the probability of default for a given group, we may set a credit policy. Basically, we need to answer: “what would the default look like given an acceptance rate?”
We have re-plotted the same data in Figure 2, but now we express the probability of default in accumulated terms. Basically, the graph shows that if we were to accept 80% of this population sample, we would have a 4.5% PD, but if we were to accept 40%, the PD would go down 2 points to 2.5%.
Now, from a business point of view, we still do not have enough information to decide. Do we?
Where would the profit be maximized?
The total cost of customer acquisition is mainly fixed. Whatever we spend on marketing and sales to attract this population, will not change if we reject more or fewer applicants. So, the cost per loan disbursed would grow as we reduce the acceptance rate.
Of course, the higher the acceptance rate, the larger the portfolio, and the more interest revenue we get. BUT, the higher the provisions and write-offs. The combination of these 2 variables (cost of acquisition and net interest income) produces an inverted U-shaped curve that uncovers the “sweet spot”
The current credit policy is yielding a profit at 100% acceptance rate (see Figure 3) because the sample being analyzed corresponds to all the customers that were accepted (i.e. we have repayment data about them). So, the portfolio is profitable.
But the sweet spot seems to be shy of 60% acceptance rate. If this FI were to cut down its approval rate to that level, profits would increase by about a third, and its return on portfolio value would almost double. Of course, there are other considerations around market share and capital adequacy that may play a role in such a strategic decision, but the opportunity is clearly uncovered by the model.
In my experience, the sweet spot usually lies within 30%-70% acceptance rates, driven by marketing expenditures, interest rates, cost of capital, sales channels, and regulation.
What if the shape of the curve shows a continuous positive growth? The sweet spot is at a 100% acceptance rate! – have we reached risk karma? – Most likely, the answer is no (but almost!).
Most likely, we are leaving money on the table. Some business rule may be filtering people before they are scored. I have experienced this situation while working with lenders. For example, a traditional bank was filtering out all SMEs that had been operating for less than X years. This bias in the population was creating a great portfolio from a PD point of view, but there was clearly an opportunity to include younger businesses. As you can see in Figure 4, the maximum return on the portfolio was achieved at 60% approval rate, but they could increase profits by approving beyond the current acceptance rate. Depending on their cost of capital, it may be a good idea to expand the portfolio by approving more people.
In summary, think of your origination model as a business tool. Don’t stop at looking at Gini to assess a model’s merit. Understand how your profitability would be impacted by changes in your acceptance rate. If the PD curve is steep enough, you may capture quite a lot of value by applying the model to either reduce or increase your acceptance rate.
Since our merger, we have welcomed a number of incredible new colleagues onto the LenddoEFL team. Jonathan Winkle joins us in our Boston office as our new Behavioral Science Manager. We cornered him to learn more.
Tell us about your background?
In undergrad I majored in psychology, where I developed a passion for researching the brain and behavior. To gain more experience after college, I worked in a systems neuroscience lab at MIT studying visual attention. Eventually I found my way to Duke where I earned my PhD in cognitive neuroscience. My dissertation focused on the behavioral economics of dietary choice, investigating how the mind is affected by “nudges” that can bias people towards healthy (or unhealthy) eating habits.
What brought you to LenddoEFL?
Studying behavior has always excited me because it is the ultimate endgame of our brains’ hard work, yet academic research on the topic can often be too disconnected from real-world problems. I found myself wanting to make more of an impact on society, and in this role I can leverage my experience to quickly and directly improve people’s lives around the world. As the Behavioral Science Manager for LenddoEFL, I can test a new hypothesis and apply that knowledge globally in a matter of weeks. And the better I do my job, the more people I can help get access to life-changing financial services.
What are your plans as Behavioral Science Manager?
My primary goal is to drive feature engineering. Features are the observations we collect about individuals to predict credit risk, and feature engineering is the process of discovering and creating new features to make our algorithms work better. For example, how honest a person is might be predictive of loan default, but we first need to quantify honesty as a feature to use it in a predictive model. As new features make our models more predictive and more powerful, our financial institution clients all over the world will gain a better understanding of their under-banked loan applicants.
If I am successful, we will be better at predicting if someone will repay their loans, thereby allowing our clients to make the best, most informed decisions possible. No pressure.
Across data sources, we look for ways to profile a person’s character, trying to understand how traits like honesty or conscientiousness relate to credit risk. This is a hard, but extremely important challenge.
LenddoEFL deals with both psychometric/behavioral and digital data sources. How do those differ and how do you think about each?
On the psychometric side, we engineer the form our data will take from the outset, then extract it by inserting new content (e.g., survey questions or psychometric games) into our simple, interactive assessment. We can be more hypothesis-driven when it comes to designing features in this realm.
On the digital side, we work with large, unstructured data sources where we necessarily have to be more exploratory and let the data do the talking.
Will you be working with our research advisors?
Absolutely! I am looking forward to working with leading researchers like Peter Belmi to push the envelope of our own research while also sharing the insights gained from our unique dataset with those in the field of behavioral economics. We will also be inviting more researchers to collaborate on our work.
Enough about work, what do you do for fun?
I like to rock climb, play Go, hang out with my dog Clementine (pic below), and try out new recipes in the kitchen.
What’s a fun fact about you?
I have a tattoo of Phineas Gage, a famous figure in the history of psychology and neuroscience. Gage was a railroad worker in 1848 that lost the left pre-frontal cortex of his brain when an accidental explosion sent a 3 foot iron rod rocketing through his head. Miraculously, he survived and was even able to walk himself to a doctor despite the 11⁄4 inch hole running behind his left cheek and out the top of his skull. He lived for 11 years after this event, but experienced marked changes in his personality that have been studied ever since. The story in itself is fascinating, and of particular interest to me is how Gage’s misfortune shaped theories of the mind for more than a century after the accident.
Look out for a future post from Jonathan about his field work in Mexico and learnings about group dynamics.
The evolution of bank-FinTech narrative brought us to a logical point, when FinTech is no longer perceived to be a threat to traditional banking, but rather as an instrument in re-establishing their position in the financial services industry. The narrative, however, doesn’t end there. As Citi emphasized in its March 2018 Bank of the Future: The ABCs of Digital Disruption in Financereport, traditional banking is being challenged not by small FinTech startups, but by established tech giants because of:
Big data customer insights
"Social media has been recognized by Wharton as an important data source for credit scoringback in 2014, although the practice of judging a stranger based on his/her social environment is not really new. One of the core ideas is that “who you know matters.” Companies like Lenddo, FriendlyScore, and ModernLend use non-traditional data to provide credit scoring and verification along with basic financial services. Those companies are creating alternative ways to indicate creditworthiness. The information contained about a person in social networks can provide some sort of verification that the person exists at all and who that person is."
"The Future of Artificial Intelligence in Banking", report examines the most significant uses of AI in retail banking, in both front-office and back-office implementations.
Bank of America
Inquire for Report at http://www.reportsweb.com/inquiry&RW0001866700/buying
CTOS has been Malaysia’s largest in terms of credit reporting, just announced a partnership with LenddoEFL to achieve a joint vision of financial inclusion for the people who had difficulties securing loans in Malaysia due to the lack of credit history.
Read article in MicroFinance Gateway website: https://www.microfinancegateway.org/announcement/malaysia-fintech-heavyweight-ctos-expands-services-better-financial-inclusion
The Africa SME Finance Forum 2018 will examine the key challenges faced by MSMEs in Africa, and explore innovative local and global best practice solutions to promote youth entrepreneurship and enhance access to financing for MSMEs.
The TechPitch will be held in the afternoon of May 15, and will provide an opportunity for innovative fintechs to demo their product to global and emerging market investment firms, financial institutions and other Forum participants. This exclusive opportunity is one of the key features of the conference and is open to a limited number of financial technology innovators working in the SME space. Approximately 12 fintech companies are selected to demo their products to Forum participants during this 90-minute session.
We are pleased to already have a number of fintech innovators such as Lendable, TALA, SME Credit Pro, Mobbisurance, N-Frnds,LendEnable, Alternative Circle, Lenddo, Q-Lana, Topicus, Uber and many others joining us during the TechPitch. Read full article.
LenddoEFL, a Singapore-based fintech company powering data-driven decisions for financial services, has appointed Darshan Shah as Managing Director, India and South Asia. Darshan is a credit bureau veteran and he brings close to two decades of experience including credit reporting, scoring, analytics and technology.
“Having worked across geographies and being well-versed with the problem of credit coverage, I look forward to leveraging my experiences to work on the challenge of financial inclusion in India,” said Darshan Shah, Managing Director, India and South Asia. “The need is massive with less than 45% of Indian adults included in the credit bureau and less than 10% borrowing from a financial institution in the last year, as per the World Bank.”