Machine Learning Optimization

Machine learning optimization leverages machine learning and a unique algorithm to maximize a campaign's performance. 

Machine learning operates in two distinct modes:

  • Learning mode: In this stage, the technology captures information to create a model. In learning mode, the campaign uses the campaigns' Default CPM Bid values to bid on all impressions. A model is created after 150 clicks have been acquired by the brand.

  • Optimized mode: In this stage, a model is available and is used to decide if the DSP should bid on an impression or not, as well as how much to bid.

    In optimized mode, the campaign uses available models and the Maximum Bid to calculate the price to bid for the impression based on the overall probability of a click. Bid prices are unique for every impression and depend on many factors, including the inventory available, the timing of the impression, and the device that will display the impression.

Enabling Machine Learning Optimization for a Campaign

  1. Create a new campaign.

  2. In the Budget section of the General tab, be sure that the campaign has a start date and an end date defined. If the group specifies flight dates, campaign flight dates are optional. 

  3. In the Optimization section of the General tab, select Machine learning optimization.

  4. Choose a CPC Goal target value, the campaign's CPC goal value to meet. The default value is $5.00.

  5. Choose a Maximum Bid, the highest CPM bid the user is willing to pay for an impression. The default value is $10.00.

    Note: The maximum CPM bid does not have to be equal or greater than the campaign's Default CPM Bid. We recommend starting with a Maximum Bid equal to the campaign's Default CPM Bid. After the campaign has run in optimized mode for a few days, you can lower the Maximum Bid if it's not achieving the desired CPC goal or leave it unchanged if it is achieving the goal.  


  6. On the Inventory tab, choose the exchanges that you want the campaign to run on. Optimized campaigns can be enabled to Run on Selected Exchanges or Run on All Exchanges.

  7. Adjust your campaign targeting and audiences, link the creatives, and save the campaign.

Other Optimization Types

You can't use algorithmic optimization and machine learning optimization at the same time. 

You can use ad optimization while using machine learning optimization. 


Was this article helpful?
0 out of 0 found this helpful