FinTech is more pervasive than ever nowadays. It has become an essential aspect of our lives with the introduction of Mpesa, electronic payments, mobile wallets, and others. Technology advancements have impacted every industry but have been more prevalent in the financial services sector.
Digital Credit Providers operating in Kenya have integrated many forms of technology to develop fast-processing analytical software. The technologies adopted include artificial intelligence, machine learning, robotic process automation, data analytics, and blockchain, which have played a vital role in their product/service offering, pathways for data-driven marketing, and understanding the borrower’sborrower’s behavior before and after availing the credit facility and predictive behavioral analytics.
Some of Kenya’s top licensed digital credit providers are Tala, Zenka Digital, Ksmart, and others. A fintech in the lending space may cater to various kinds of product offerings, which can be broadly categorized as follows:
1. Consumer loans
2. Personal loans
3. Business or MSME (Micro, Small, and
Medium Enterprise) loans
What are the critical back-end tech solutions/integrations needed?
2-Application, website, and/or app
4-Credit underwriting/ Scorecards/Fraud detection
5-Credit Bureau Integration
6-Automatic analysis of qualitative factors
9-Loan Management System (LMS)/Accounting
Let’s delve deeper into each of the above for a deeper understanding.
1. Customer acquisition:
Drawing in customers is a top priority for any fintech. There are various methods or sources through which a DCP acquires its customers. The customer acquisition process may differ for each lending institution depending on their product, the area in which they operate, the customer profile, etc. To attract potential borrowers, leverage digital marketing strategies, social media, and partnerships with relevant platforms. Focus on providing a seamless user experience to make your platform stand out from existing or traditional lenders.
2. Application, website, app or USSD
Develop a user-friendly and intuitive digital platform for borrowers to apply for loans easily. Mobile apps have become increasingly popular in Fintech, allowing users to access services conveniently. Consider application login through Gmail, social media, and so on to enable the user to seamlessly log in to the mobile application for the website without creating any new login credentials. At the same time, this also provides the Fintech with the profile of the loan applicant. Do you need customers to upload documents for KYC/AML verification? Ensure your platform allows uploading these documents and has back-end integration to verify the documents’ authenticity. Consider using the different available Optical Recognition Technologies (OCR), which should be able to read the data from the documents provided and create the text. For verification and
authentication of the information in the documents, the Fintech can develop its software and subscribe to various services or do an API integration with a service provider who can provide such services. The main goal is to give users a comfortable journey, so they must manually type minimum information.
3. Verifying APIs
Integrated persons registry system (IPRS) is Kenya’sKenya’s reputed organization providing APIs for KYC, Identity, etc., suitable for all lending businesses. The IPRS system aims to consolidate population information into a single centralized database, allowing for easy verification by government and private bodies, especially those in the financial sector. IPRS database combines primary registration, such as birth, national ID, passport, and Alien ID, with secondary registration, like Tax registration, and much more. Transunion also offers verifying APIs.
A few fintech companies in Kenya, like Smart Kiosk, have linked the entire customer journey with WhatsApp. Applicants or their customers can apply for a loan, provide the required documents, avail the loan, and hopefully, in the near future, make payments using WhatsApp messenger services. To implement this solution, a company needs to avail API services of WhatsApp for this purpose.
USSD and/or SMS – text and email notifications
USSD (Unstructured Supplementary Service Data), also known as “Quick Codes”, has always been known as a means of accessing mobile network providers. When you dial a number that begins with * and ends with #, you use USSD.
These USSD codes are helpful when you run out of mobile data or have poor internet connectivity. USSD provides customers with a quick offline solution for assessing mobile financial transactions. USSD can assess loans and other transactions through an interactive clear, displayed menu on your mobile screen. Many digital lenders and banks in Kenya have deployed USSD technology to provide mobile financial services to low-income customers.
Some DCPs use text messages, emails, and WhatsApp notifications (wherever available) to communicate important updates to customers throughout their journey. These updates include application confirmation, eligibility status, loan approval or rejection, loan disbursement, and more.
4. Credit underwriting/ Scorecards/Fraud detection
Underwriting and fraud detection is the most crucial task for a digital credit provider. In the Kenyan fintech market, credit underwriting, scorecards, and fraud detection play a critical role in enabling digital credit providers (DCPs) to offer customers fast and efficient lending services. Unlike traditional banks that rely heavily on credit bureau scores, fintech entities in Kenya have embraced alternative methods to assess a borrower’s creditworthiness, revolutionizing the lending landscape. While traditional banks have a standard way of granting credit facilities based on financial documents provided by the borrower, fintech entities try to assess the ability to pay and the willingness/intention to pay through an alternative method.
Generally, this alternative method is understanding the customer profile based on specific pre-set parameters like understanding their personal information, Mpesa transactions, social information through digital footprints, use of phone, actions on various social media platforms, understanding the call behavior in terms of calls made, calls received, calls missed, duration of the call, and so on.
i)Leveraging Alternative Data for Underwriting:
a) M-Pesa Transactions: M-Pesa, Kenya’s mobile money platform, has become a goldmine of financial data. Digital lenders analyze borrowers’ M-Pesa transaction history to understand their cash flow, spending habits, and repayment capacity. Regular and timely transactions might indicate financial stability, positively influencing the credit decision.
b) Social Media Footprints: Fintech companies explore borrowers’ social media activities to understand their behavior, interests, and social connections. Engaging with reputable brands and active participation in professional networks can be considered positive indicators for creditworthiness.
c) Mobile Phone Usage: Borrowers’ call behavior, such as frequency, duration, and missed calls, can reveal patterns related to their reliability and financial stability. For instance, consistent and responsible communication might reflect positively on a borrower’s character.
d) Digital Footprints: Beyond social media, analyzing a borrower’s digital footprint, including online interactions and behavior, can provide additional insights into their financial habits and personality traits.
Consider developing an algorithm incorporating M-Pesa transaction history, social media activities, and mobile phone usage data to assess a borrower’s creditworthiness. The algorithm assigns different weights to each parameter based on historical performance data and market trends, generating a customized scorecard for each borrower.
ii)Customized Scorecards for Precision:
Rather than relying solely on standardized credit bureau scores, Kenyan DCPs adopt customized scorecards to cater to various borrower segments and products. These scorecards are designed using machine learning and AI, enabling continuous refinement and enhancement based on real-time data.
A scorecard of a DCP offering microloans to small businesses is tailored to evaluate business owners based on their M-Pesa transaction history, business revenue patterns, and social media presence. The scorecard dynamically adjusts its parameters as the business grows, ensuring precise risk assessment.
In addition to the credit bureau and KYC verification, consider a solution that analyses for underwriting and fraud detection. One must recognize the importance of robust fraud detection mechanisms to protect borrowers and lenders from potential risks when building a DCP. These mechanisms leverage advanced technologies to identify fraudulent activities and patterns in real-time, i.e., AI-driven algorithms to monitor borrower behavior and identify suspicious patterns that might indicate fraudulent activities. The system flags accounts showing multiple loan applications within a short timeframe, attempts to borrow from various lenders simultaneously, or engages in other abnormal behaviors, prompting further investigation.
5. Credit Reference Bureau (CRB) Integration
CRB analysis is another critical ingredient while setting up a Digital lending platform. There are three credit Bureau agencies in Kenya, namely
These CRBs provide API integration with your system so you can automatically pick up specific information from their reports and run tools to analyze the data provided by them. Depending on the CRB you choose and the datasets you subscribe to, you can create an alternate scorecard for the Customer to arrive at a final scorecard. Examples of information fetched from these bureaus are; the Customer’s credit score, total loan outstanding Loans overdue within 30 days or 60 days, or 90 days, amounts written off, number and total outstanding balances of running loans, etc. Credit bureau scores and other information help analyze the applicant’sapplicant’s ability to pay” and “willingness to pay.” If a customer has written off loans, this may be a cause for concern. Similarly, too many inquiries in a month reflect the customer’scustomer’s desperation. A lending fintech would build its rule engine based on these parameters.
6. Automatic analysis of qualitative factors
Qualitative factors encompass various non-financial parameters that provide insights into a borrower’s character, reputation, and social behavior. These factors can be equally vital in assessing a borrower’s creditworthiness, complementing the traditional credit score derived from financial data. Lenders can gain a more holistic view of their creditworthiness by analyzing a borrower’s behavior beyond just financial transactions.
It’s important to note that qualitative factors do not replace traditional credit scores but rather supplement them. Traditional credit scores based on financial data provide valuable insights into borrowers’ credit history, while qualitative factors offer a glimpse into their character and social interactions.
For example, a lending platform may assign higher weightage to a borrower’s active participation in professional networks on LinkedIn, viewing it as a positive indicator of stability and repayment potential. On the other hand, frequent and excessive interactions on gambling websites might raise concerns and warrant a lower score.
Another example, a DCP might use Natural Language Processing (NLP) algorithms to analyze a borrower’s posts, comments, and interactions on social media. The tone of their language, the topics they discuss, and the people they associate with can all provide valuable insights into their personality and reliability.
The DCP should be able to generate an entire credit facility loan agreement, terms and conditions, and repayment schedule indicating interest or fees charged to the borrower for “acceptance” before disbursing the loan. Some of the popular DCPs, i.e Timiza/KCB Mpesa, disburse loans to e-wallets contained within their application, but a majority i.e. Mshwari and others, disburse directly to the borrower’s Mpesa or Airtel account. A few DCPs pay the loans to the applicant’s bank account. Safaricom, through their daraja API. Daraja API is an Application Programming Interface that creates a bridge for payment integration to web and mobile apps. This integration allows for secure and real-time fund transfers to customers’ M-Pesa accounts. You can use Safaricom to receive payments from clients. Customers can initiate loan repayments through M-Pesa by simply transferring the amount due to the lender’s M-Pesa paybill number or initiating the payment from the app, like in the case of Tala and Zenka. In your web app, you can create a button that, when a user clicks, they can initiate payment. For example, a web application provides a button that the user clicks to send a request to Safaricom Daraja; upon receiving the request, Daraja sends an STK push containing the amount deducted from the Mpesa wallet.
The user is then prompted to enter their PIN. Once the user enters the PIN, the transaction is processed immediately. M-Pesa provides a convenient and accessible platform for customers to receive loan disbursements and make repayments using their mobile phones.
Top-up and multiple loans to single borrowers
A few DCPs in Kenya offer loan facilities in addition to the existing ones, called Top-Up, based on the borrower’s eligibility and repayment track record. However, many digital lenders create a restriction that the same phone number or email cannot be used to request another loan if the previous loan has not been cleared.
Penalties, late payment fees, and other charges.
If a borrower defaults or delays payment, various charges are levied by the lenders. The DCP should factor in the in duplum rule when putting in place penalties. According to the law, interest should not exceed the principal owing when the loan becomes non-performing.
Implementing an effective loan collection and recovery strategy is crucial for any digital credit provider. The collection or recovery can be done in the following ways:
a). Multi-Channel Communication: Use a multi-channel communication approach to reach out to borrowers a day or two before their repayment date or those who have defaulted on their digital loans. This can include SMS reminders, emails, phone calls, and in-app notifications. Utilizing various channels increases the chances of reaching borrowers and encouraging them to repay.
b). Early Intervention: Start the collection process early when borrowers miss their first payment. Prompt action can prevent the default from escalating and increase the chances of recovering the debt. You can set up an in-house debt collection and customer service call center for the early interventions i.e, loans under <10 days.
c). Customized Repayment Plans: Offer flexible repayment plans based on individual borrowers’ financial situations. Tailoring the repayment schedule to their needs can facilitate timely repayment.
d). Automation and AI: Implement automation and AI-driven solutions to analyze borrower behavior and payment patterns. This can help identify high-risk borrowers and prioritize collection efforts accordingly.
e). Negotiation and Settlements: Be open to negotiating with borrowers who are facing financial difficulties. Arriving at a reasonable settlement can lead to partial recovery rather than no recovery at all.
f). Collaboration and data submission to Credit Bureaus: Collaborate with credit bureaus to access credit data and assess borrowers’ creditworthiness accurately. This can help in making informed decisions and improving debt recovery rates. If CBK licenses you, you can submit full-file data to CRBs. The borrower must be informed/notified 30 days in advance and informed how non-repayment of their loan will affect their credit score.
g). Legal Action as a Last Resort: Consider legal action as a last resort if all other collection efforts fail. Engage with legal professionals experienced in debt collection to pursue legal remedies.
h). Customer Support and Education: Provide borrowers with excellent customer support and financial education. Educating borrowers about responsible borrowing and repayment can foster a positive borrowing experience and reduce defaults.
Finally, you can outsource defaulted loans. Several debt collection companies in Kenya specialize in debt recovery. Whatever you do, ensure your company doesn’t use unethical debt collection practices.
9. Loan Management System (LMS)/Accounting
The second last and most crucial feature is integrating Loan Management System (LMS) with the accounting system, wherein the collections are entered into the LMS and the accounting system. You can tailor-make and customize your LMS or use a few off-shelf solutions like Mambu. Integrating your app with the accounting system helps a DCP avoid duplication of work and ensure the correctness of data. This makes all the the information available to the Customer on the loan management system as reflected in the accounting system. Some of the essential things to be taken care of are:
a)Integration of accounting software with DCP/ loan software
b)Auto debit/ credit to borrower account based on Mpesa or bank acc details
c)Interest calculation as per the laid down policy and process
d)Additional charges, overdue interest, penalties
Your loan management system should allow you to prepare and present various data and information, i.e., Disbursement, collection, overdue and outstanding to their investors, regulator, etc.
The last important aspect to focus on in a digital credit provider is the efficient handling of legal matters. Handling legal issues requires precision and expertise. Engage an in-house lawyer or partner with a reputable firm to guide you on data protection, AML/terrorism financing, and arbitration of legal cases.
Building a world-class digital lending platform can be challenging, but you don’t have to do it alone. If you’re seeking a reliable partner to lead the way, contact us via – firstname.lastname@example.org for a demo from one of our trusted partners. Together, we’ll revolutionize finance and empower financial inclusion for all.