There are 4 stages to getting started with credolab.
Stage 1: Data Collection
The first stage involves collecting data on your customers. This can be done through CredoWeb, CredoSDK, CredoApp or CredoApply. The objective of this stage is to feed a good sample of data sets to the scoring algorithm in order to build final, custom scorecard for your business. This includes both good and defaulting customers. Ideally, we suggest having at least 300 defaulting customers in the data mix to ensure the algorithm is trained how to identify these customers and flag them. The duration of this stage varies from two to three months depending on the availability of data.
Note: no scores are generated at this stage. Merely collection of data is done to train the scoring machine/algorithm.
Stage 2: Outcome Window
This refers to examining the outcome of the credit disbursed during the start of the data collection stage. The scoring algorithm used this to match the features of applicant to their outcomes. Thus, the more data and their outcomes are fed into the machine, the more comprehensive the learning, and the more accurate the scoring algorithm gets. This stage starts form the first month and can last up to three months depending on the availability or satisfying mix of data to feed into the algorithm.
Stage 3: Model Development
Once we have the data and their outcomes, our standard scoring model is tweaked to customize it for your business, market and objective. The machine/algorithm is trained to identify a defaulting and fraudulent customer from day 1. This stage takes up to one week to complete, depending on the complexity of the features considered for scoring.
Stage 4: Production
After testing the customized scoring algorithm and ensuring it works perfectly, we then roll it out and make it live to be used by you. You can start generating scores now.