CRR reflects the effectiveness of campaigns with the predictive model, and helps increase the client's profit; Optimizing the CPA for the order; Increasing the LTV of attracted users. This can be achieved by increasing the frequency of orders per user or increasing the value of the average bill Tools:

Accumulating 30,000 installs, among them — at least 40% with conversion; Making recommendations for the client on unmarked events on the event map; Collecting additional raw data on the Push API and getting a key for sending s2s events; Creating a tree of user behavior; Training the model and splitting users into clusters by LTV; Starting to send a Smart Event. In July created test campaign optimized for a predictive event; Updating the settings and enriching the Smart Event with additional information Results: Optimized campaigns using Smart Event. The CRR for them became lower than the CRR of conventional campaigns; By 25% reduced CRR for the period from October 2021 to February 2022 compared to conventional campaigns; By 23% lowered CPO; 4 times increased budget of predictive ad campaigns from October to February and reduced the share of regular promotion