# Introduction to Risk Insights

Risk Insights provides lenders with a sophisticated feature library based on real-time data to see the full extent of an end-user's repayment capacity. Tink offers freedom to improve your own in–house risk modelling with our features that are built from the biggest data set in Europe.

Lenders and assessors face many challenges when evaluating end-user risk:

- Traditional risk data is not up-to-date. This fact often excludes lending to end-users who have not been in the credit system for more than six months.
- Data that is used to feed traditional risk models is susceptible to fraud.
- Vital risk patterns are excluded, for example, gambling, spending habits and ATM behaviour.
- Manual work heightens the risk of error. This affects end-users who quickly need a lending decision and hinders lenders that optimise for 'time to money'.

!https://images.ctfassets.net/tmqu5vj33f7w/3v75h4lYUZ3Vog6wOMQvk/0c5df89a5df0c630c4fbead0f97b912f/Risk-insights-comparisons.png

## What this solves

Risk Insights provides a full and deep risk overview that is free from generic data. Tink offers over 300 features that you can choose from and feed your existing risk model. In other words, Tink allows you to cherry-pick from a variety of the most predictive, tried and tested features to create an improved risk model that is best suited for your risk appetite.

Transaction data is retrieved in real-time. The data is enriched, categorized and up–to–date. This leaves you with a lean risk process where focus is on pricing risk rather than cleaning up data, which is often a very tedious process.

For end-users, Tink retrieves data via open banking, which does not necessarily affect their credit score.

## How it works

Tink is the largest open–banking provider in Europe with the biggest financial data set, used to continually develop risk–evaluation patterns via artificial intelligence and machine learning.

When a customer consents to the use of Risk Insights, all transactions are retrieved from their bank accounts. Relevant transactions are filtered, enriched and cleaned. The results are categorized and distilled into the most relevant feature set for risk decisioning.

The end result is an insightful summary that allows for making a better risk decision based both on the applicant’s historical and current spend behaviours and financial habits.