{"id":2526,"date":"2021-08-06T10:00:32","date_gmt":"2021-08-06T10:00:32","guid":{"rendered":"http:\/\/beeeye.com\/?p=2526"},"modified":"2022-01-31T10:22:51","modified_gmt":"2022-01-31T10:22:51","slug":"seeing-the-full-credit-risk-picture-using-external-data-sources","status":"publish","type":"post","link":"https:\/\/beeeye.com\/seeing-the-full-credit-risk-picture-using-external-data-sources\/","title":{"rendered":"Seeing the full credit risk picture using external data sources"},"content":{"rendered":"
<\/p>\n

There is an old parable about a group of blind men who have never seen an elephant before. When they first encounter one, each one feels a different part of it, like the trunk or the ears. Each one in turn describes the beast in a completely different way. There are several lessons that can be learned from this fable. What I take from it is to always remember to see the bigger picture. To always ask \u201cwhat am I missing?\u201d and include all the data points.<\/span><\/p>\n

This is especially true when it comes to credit risk modelling, and the use of varied data sources. If you only rely on internal data sources, you\u2019re definitely not seeing the full picture. The result? You are either exposing yourself to more risk than intended, or are leaving money on the table. <\/span><\/p>\n

Using the right sources, the right way<\/h3>\n

You must have full control on which data points and data sources are in use, as the <\/span>GDPR<\/span><\/a> and similar regulations require it. In a platform where all external data controllers are at the hands of the modeling team, unique value can be uncovered while keeping the models\u2019 transparency. This way the stakeholders that monitor data governance have full visibility into the data sources used. <\/span><\/p>\n

Examples of sources that are especially beneficial are: Applicants\u2019 email quality, data derived from a 3rd party partner retailer API and<\/span> governmental API <\/span><\/a>with local addresses data. <\/span>By adding these to the mix, you\u2019ll improve risk scoring and customer knowledge. <\/span><\/p>\n

So, why isn\u2019t everyone using alternative\/external data sources to complete the picture for them? Well, first and foremost, because many credit risk modelling platforms don\u2019t lend themselves to an easy integration with these sources. Another reason is that when using additional data sources, modelers must also have a detailed model explainability report. This is important so decision makers can assess both the exposure and the lift impact new data points add. Then they can use them with discretion to achieve the optimal data mix.<\/span><\/p>\n

The key features to look for<\/b><\/h3>\n

Here\u2019s what you\u2019ll gain from working with a platform that can automatically integrate external data sources to your workflow: <\/span><\/p>\n