The credit analysis of projects that are presented on October is performed in-house. We collect quantitative and qualitative information necessary to assess the risk of a project and decide an interest rate. We have 2 types of credit analyses.
Standard projects are analysed using a combination of manual and automatic credit analysis. Our financial analysts are in charge of collecting analysing quantitative and qualitative data. For example, they get information from annual reports and insert it in our scoring model. They would fill the scoring model, automatically or manually, with a lot more information about a company's financial results, market outlook and management team. The scoring model generates a credit score and an interest rate that would be offered.
You can find more information about our standard credit analysis in our dedicated tutorial:
Instant projects are analysed using fully automatic credit analysis, using 2 different automatic loan assessment models, called Magpie and Kea. Both models use machine learning algorithms to assess the borrower's probability of default. The main difference between these automatic loan assessment models is the data used to score the project:
Magpie relies on financial and behaviour information and compares it to a large amount of data gathered by October across our 5 countries.
Kea analysed the borrower's bank transactions over the last 12 months and checks for payment regularity and consistency.
Both Magpie and Kea scoring returns a probability of default which is then converted into a credit score using the October scale (from A+ to C-).
You can find more information on the credit analysis of instant projects in our dedicated tutorial: