Nowadays, online behavioural data is Terra Incognita. But as the industry learns how to gain better long-term insights, this type of data can still lead to the results in the short term.
The huge volume of collected information and its detailed analysis helped to identify highly informative predictors and markers. These predictors provide us with a deeper understanding of people’s behaviour, and help us to estimate their real income without using personal data. Another advantage is that their hit-rate exceeds 99% for online users.
Here are the examples:
1 – The real cost of the device or personal computer and NPL90 +. The difference between NPL90+ (in %) between the most expensive devices and the cheapest ones is more than two times.
|2 – The number of additional requests for credit products from the device for one week and NPL90 +. The NPL90 + difference (in %) between the groups with the largest and the smallest number of requests is more than three times.|
|3 – The number of certain actions of an online user on the company’s website and NPL90 +. The difference of NPL90+ (in %) between the smallest and largest number of actions is more than two times.|
The detailed usage description may be obtained from our partners, credit bureaus, developers of credit conveyers and data aggregators. Please, let us know should you have any comments or new studies proposals.
We will cover them in our future publications.
Have a question for us about something that is relevant to the development of your business? Send your queries to firstname.lastname@example.org and we will do our best to cover them in our publications and studies.