Launching into space: Using satellite imagery in financial services
This case study (PDF), by Caribou Digital and the Mastercard Foundation, offers insight into the method behind how FinTechs integrated earth observation technology (satellite imagery) into their financial services. Innovative companies are testing whether earth observation data can be converted into data that financial service providers can use in credit scoring models that assess a farmers creditworthiness. Satellite imagery, in combination with demographics, financial, agronomic, geospatial and psychometric data, provides sufficient detail on clients without established credit history, to make lending decisions. Leveraging satellite imagery meaningfully requires specific tech skills and infrastructure, investment, capital, and data to train machine learning models. FinTechs incur major costs in the process of turning the raw data into critical, analytical insights that can be used for lending purposes. Further, required skills of scientists are key to building the infrastructure to support the processing of thousands of images, but they are not easily found. The FinTechs also needed to raise the investment capital necessary to start their company operations and absorb the initial risks with equity rounds, grand resources, and/or angel investment. Providing the value of earth observation data in lending requires constantly experimenting with data-driven models – data that can only be collected infrequently and can present statistical challenges. Despite challenges, initial testing with satellite imagery has been positive, indicating significant predictive power in terms of generating features relevant to credit models. Customer acquisition is the most challenging aspect in reaching scale and profit. To harness innovation in financial services, digital finance providers should collaborate with FinTechs. The key takeaway is that financial service providers must have a clear vision of why they want to leverage satellite imagery and ensure they have the in-house capacity to leverage it as well as realistic expectations of what the technology can achieve.