Credit Karma is a leading financial digital platform with over 100 million users. It helps consumers find the best credit products for their needs and goals. Many credit card providers use Credit Karma to advertise their offers and reach their target audience.
One of our clients, a major credit card provider, wanted to increase its customer acquisition on Credit Karma by adding a “pre-approved” badge next to its offer. This badge would show the users that they have a high chance of getting approved for the card if they apply. This would boost their confidence and motivation to apply, as well as reduce the risk of rejection and credit score damage.
However, creating a pre-approval model that accurately predicts the final approval decision is not an easy task. It requires a lot of data, analysis, and testing to ensure that the model is reliable and effective.
We partnered with our client to develop a custom pre-approval model for their specific credit card offer. We used historical data from Credit Karma and our client to train and validate the model. We also applied advanced machine learning techniques to optimize the model performance and accuracy.
The pre-approval model we developed had a 98% accuracy rate in predicting the final approval decision. This means that only 2% of the users who saw the “pre-approved” badge and applied for the card were rejected.
We implemented the pre-approval model on the Credit Karma platform and added the “pre-approved” badge next to our client’s offer. We also added other badges such as “Poor” or “Fair” to indicate the approval odds for users with lower credit profiles. This way, we discouraged them from applying for the card and hurting their credit score.
The pre-approval campaign we launched for our client was a huge success. Within two months of implementation, our client saw a 100% increase in customer acquisition on the Credit Karma platform. This means that twice as many users applied for their credit card offer after seeing the “pre-approved” badge.
Moreover, the quality of the applications also improved significantly. Since the pre-approval model screened out the users who were likely to be rejected, our client received more applications from qualified and eligible customers. This reduced the cost and time of processing and approving the applications.
We use cookies to analyze website traffic and optimize your website experience. By accepting our use of cookies, your data will be aggregated with all other user data.