Feb 17, 2022
According to the latest Worldbank study, 1.7 billion adults currently have no access to a bank account. Considering how traditional credit scoring data collection systems work, it is not surprising that the financial exclusion numbers are so high. In this article, we’ll explore how data collection systems can be improved to benefit credit invisibles and thus help with social mobility.
When granting personal credit, lenders use credit scores as a reference to know if a person is reliable enough to receive a loan. This credit rating results from a previous credit analysis, which may vary depending on the institution that performs it. In general, traditional bureaus use certain common parameters related to credit history, such as payments, current debts, and the number of open accounts.
The lower the credit score, the more difficult it will be for a person to receive a loan, and the more likely this person will incur higher interest rates given their perceived “high credit risk”. Consequently, limited credit history with insufficient historical data results in a shortsighted credit study with insufficient qualifications for loan approval. In other words, there is a vicious cycle in traditional credit scoring systems, a direct correlation between financial exclusion and traditional data collection processes. Credit bureaus depend on information obtained from the banking system for decision making, a system that currently 1.7 billion people cannot access.
The uprising of new fintech companies has allowed more people to have access to financial products. In the case of credit, these companies have provided new information collection systems based on alternative data and artificial intelligence that evaluate people, despite not having a bank account, according to much more complex behavioural parameters.
These fintechs have understood that a person’s digital presence says a lot about how a person is and that these behavioural patterns can change over time. Fintechs have brought to the table their technology to overcome traditional credit rating processes and obtain credit profiles in real-time more safely and capably to update and relearn continually. Alternative credit scores have come about to change the parameters of trust, shedding new light on a scoring system that leaves many people behind.
A "footprint" or "digital shadow'' results from all the activities, actions and traces that a person leaves behind when browsing the Internet. All this alternative data is processed by artificial intelligence mechanisms that analyse them and create non-linear behaviour models that predict one’s present and future behaviour.
Some examples of data that can be analysed from a "fingerprint" are email profile, that is if the email exists and if it comes from a fraudulent domain or not; the IP, where the connection originates; the telephone line, whether it is mobile or landline and whether the telephone exists; social networks, whether or not the person has social networks, which ones they use and who their friends are. With all this information, the profiles become much more complete, allowing lenders to make much more informed decisions.
Having a secure data collection system is one of the keys to today's world, especially in the financial world. Every day fraudulent programs become more malicious capable of creating false profiles in order to later apply for a loan. Therefore, unlike traditional rating systems, the new alternative scores can identify, report, and prevent false identities from submitting an application again.
Cyberattacks, such as phishing, are becoming more frequent within the industry. They point at the companies’ client portfolios to obtain private data such as passwords and bank account numbers. That is why alternative information travels in metadata format, protecting the identity of the clients. The data collected is encrypted and non-PII data -non-personally identifiable information- to prevent any attack from revealing the users' identity.
New data collection systems have not only increased the quality of credit scores but have also speed up decision-making processes. Thanks to automation, lenders can approve more trustworthy prospects, and borrowers won't have to wait long for their applications to be approved. This allows companies to accept more clients in less time and avoid the flight of prospects eager for instant results.
The new data collection systems have a great advantage over traditional systems due to their accuracy, ability to learn, security and processing speed. With these benefits in mind, technology helps improve data collection processes and work towards the ultimate goal of upward social mobility.
March 2, 2022
How to Combine Digital Footprint Lookups with Behavioural Data to Turbocharge Credit Scoring