Ngozi Dozie and his brother Chijioke relied on DataRobot to understand the Nigerian financial landscape

Ngozi Dozie and his brother Chijioke relied on DataRobot to understand the Nigerian financial landscape


by Analytics Insight


January 14, 2022

DataRobot really shines for Carbon, building large-scale models, which is crucial for a small team of just eight people.

Challenge

DataRobot enables organizations to leverage the transformative power of AI by providing the world’s only trusted enterprise AI platform combined with an AI-native strategic success team to help customers transform value data quickly.

When Ngozi Dozie and his brother Chijioke looked at the Nigerian financial landscape, particularly in the areas of consumer lending and credit infrastructure, they saw an immature landscape but one with huge opportunities. Out of 100 million adults in Nigeria, more than 40 million of them had no bank account and there were only about 200,000 credit cards distributed nationwide. As commercial banks were hesitant to offer consumer loans, this was an opportunity for Carbon, the fintech company founded by Ngozi and his brother, to help serve Nigeria’s underbanked population. Leveraging modern mobile app technology with cutting-edge data science backed by DataRobot, Carbon is now one of the biggest success stories in the African financial market, disbursing over 3,000 loans a day.

Building a credit rating in a market like Nigeria is a huge challenge, with little documented financial history or asset ownership. Lending to consumers without credit is understandably a risky proposition for traditional financial institutions. To circumvent this challenge, Carbon has embarked on a data-driven strategy. Specifically, it engaged in a data science-based lending model that leveraged DataRobot’s advanced AI and machine learning technology to create robust credit risk models for the largest country in Africa. With a staff of less than 150 people worldwide, in offices in Lagos, London and Kenya, Carbon has far fewer resources than the big banks. Despite this, Carbon has leveraged this strategy to operate profitably in a market that traditional financial institutions have avoided as too risky.

Initiative

At the heart of it all is DataRobot’s groundbreaking algorithmic credit risk engine that powers Carbon’s mobile app. When a consumer submits an app on the mobile app, Carbon’s models leverage a diverse set of data from first-, second-, and third-party sources to establish a credit score. In less than five minutes, users will receive a credit score and “good” customers will have access to better rates and higher limits, while high-risk customers will benefit from higher interest rates. All of this is powered by DataRobot, which helps Carbon dramatically increase the speed, volume, and accuracy of the credit risk models they build.

“When we launched the mobile app in 2016, we realized that we are collecting a lot of data and that we needed to analyze this data at scale and create many models in order to make proper lending decisions. One day our data Part-time scientist came in and said, “Guys, I solved our problem,” and we thought it was too good to be true, but then he showed us DataRobot.”

Results

Today, Carbon processes 150,000 loan requests each month through the DataRobot Prediction API and tracks these deployments in DataRobotMLOps. Four separate dashboards provide insight into each customer’s likelihood of defaulting on their loans. The app then adjusts its loan terms accordingly. Carbon’s algorithms also take into account fraud and anti-money laundering practices, which are prevalent in the Nigerian market, and put in place numerous safeguards accordingly.

Where DataRobot really shines for Carbon is building large-scale models, which is crucial for a small team of just eight people. In addition to allowing them to create many more models, DataRobot has already significantly streamlined and accelerated its credit model governance process, to the point that new models can be deployed in hours, rather than months, as it takes usually in large banks. There are many things customers love about DataRobot, even before they get to the point of actually running models. With their success in disbursing such a large volume of loans in Nigeria and helping to bring Nigeria’s consumer and SME lending market and lending infrastructure to greater maturity, Carbon is now focused on expanding. The company launched services in Kenya in late 2019 and has also begun expanding other product offerings, including peer-to-peer transfers, debit cards and savings. “And DataRobot continues to fuel the company’s foundation as it transforms into a pan-African digital bank. During their recent launch in Kenya in January 2020, the Carbon team was able to easily recycle and redeploy their models while building their customer database. DataRobot is an inspiring tool, a great educational tool,” said Ngozi.

DataRobot is an inspiring tool, a great educational tool,” said Ngozi. “We started with one data scientist, then another, and now we have a team of eight people. We haven’t stopped since, and we have no intention of stopping. In the next phase of growth, we are excited to use DataRobot for other non-credit related models such as unsubscribe, recommendation and customer segmentation. ” He added.

Share this article

Do the sharing

About the Author

More info about the author

Analytical overview


Analytics Insight is an influential platform dedicated to ideas, trends and opinions from the world of data-driven technologies. It monitors the developments, recognition and achievements of artificial intelligence, big data and analytics companies across the world.

More by Analytics Insight

Lance B. Holton