Jump-starting automation for Planet42
Rent-to-buy car subscription service Planet42 accelerated their document automation efforts, improved risk models, and secured investor confidence without hindering rapid growth in emerging markets.
THE CLIENT
Planet42: democratizing mobility via data science
Planet42 is a rent-to-buy car subscription service that aims to democratize access to mobility operating in South Africa and Mexico. The key to their success has been a deep understanding of the local markets they operate in to build effective risk models and a data science team dedicated to strategically deploying improved decision-making across the organization.
The obvious first point for the team to tackle was the automation of their document intake processes: the IDs, driver’s licenses, and bank statements that applicants needed to submit.
And to maintain control and best performance, the Planet42 data science team opted to leverage Amazon Textract to build their own workflows—and Resistant AI to protect it.
THE CHALLENGE
Building automation
in-house
The company acknowledged early on that on-the-ground validation teams wouldn’t be able to keep pace with the growth in applications. "We knew it was going to multiply linearly with the number of people, and teams do not multiply well linearly, but processes do," explained Adam.
This foresight led to a strategic pivot towards document automation, with two clear challenges to tackle: document validation, and document understanding.
Each is critical, as automating without validating opens the door to automated fraud—which is costly when the assets lost are individual cars.
But they're also individually mammoth tasks, and with existing processes manually driven, the team had little data to leverage and get started.
THE SOLUTION
Confident document automation security
Partnering with Resistant AI to automate document validation was a game-changer for Planet42’s data science team for a couple of reasons. First, it allowed the data science team to focus their efforts on building their document automation workflow, and rely on Resistant AI’s expertise to detect signs of tampering in every document.
Second, Resistant AI’s document classification data was an invaluable component in jump-starting Planet42's technical knowledge to enable important automation design decisions early on, such as determining which bank statements to validate.
By helping Planet42 turn a slow, manual application process into a fully automated one, it also allowed them to better securitize their debt.
"Resistant AI gave us a much better understanding of what our document set actually looked like, and where to focus our parsing efforts." explained Adam.
Document Forensics
Streamline your documents processing to identify fake or fraudulent documents — even when invisible to the human eye.
.svg){kind=small}
.svg){kind=small}
.svg){kind=small}
.svg){kind=small}
