As mobile advertising budgets for app install ads scale into the billions of dollars, fraud becomes an increasingly complex and sophisticated issue. Appsflyer estimated that fraud cost app marketers $2.3 billion in the first half of 2019. 

Sift’s platform uses advanced machine-learning algorithms to automatically optimize campaign performance for conversion rate and click to install time. Sift’s platform monitors conversion rates in real time for each campaign and algorithm, automatically optimizing campaigns across inventory sources to improve conversion rate. In addition, Sift’s platform monitors the click to install time distribution in real time for each campaign and algorithm, automatically optimizing campaigns to pause ad spend on inventory where the CTIT distribution is abnormal. For example, no installs should come in less than 10 seconds from the click, and the vast majority of installs should come in within 24 hours. Since Sift’s platform runs ads across 400k mobile apps and 25k mobile websites, we also offer full support for including and excluding specific app bundles and domains to help optimize campaign performance for our advertisers. Sift’s platform also optimizes campaigns for post-install engagement and automatically blocks traffic sources with high rates of rejected postbacks from mobile measurement partners (MMPs). In addition, Sift’s platform supports click signing in collaboration with MMPs to secure tracking URLs to prevent URL editing and invalidate duplicate clicks.