We are working on models that give personalized predictions of the response to sponsored search ads. These models improve the user experience by making changes to ranking and presentation of ads, according to the user's past behavior. A core component of sponsored search is the click prediction model. We extended this model to incorporate user-specific information that helps us better predict whether users will click on ads or not. Personalizing the predictions benefits both the users and the advertisers. The users are presented ads in a manner that is most relevant to them, and the advertisers receive clicks from users who are more engaged with the ads. Bucket testing confirmed that personalization of the number of (North) ads leads to an increase in click yield and conversion rate.