The Future of Mobile Gaming Growth: Unlocking the Power of Neural Networks

The mobile gaming industry has traditionally relied on programmatic advertising to achieve scale, but with increasingly competitive markets, a more strategic approach is needed. To drive growth, mobile games require an ad partner that can leverage data in innovative ways to deliver consistent user engagement, in-app purchases, and strong ROI. This is where neural network solutions, such as Liftoff's Cortex, come into play. By harnessing the power of neural networks, Cortex represents a significant evolution in machine-learning capabilities, enabling the identification of complex patterns in larger datasets to make accurate predictions for specific outcomes. For gaming advertisers, this means connecting their game with high-value audiences who are more likely to engage consistently and spend more on in-game purchases over time. In recent years, real-time bidding (RTB) has become increasingly popular, offering advertisers greater transparency and precision in targeting their ideal audience. However, traditional targeting methods, which rely on segmenting audiences based on demographic characteristics, are limited in their ability to model user behavior. Advanced machine learning solutions, such as Cortex, leverage historical data, including session time, ads watched, and previous purchases, to predict current and future user behavior. By combining first-party attribution data with exclusive data from the Vungle SDK and GameRefinery, Cortex can predict the likelihood of users installing and engaging with a game or making purchases post-install. To maximize return on ad spend (ROAS), mobile games need to identify and nurture high-value users, such as 'whales' and high spenders. Deep learning, powered by neural networks, is better equipped to spot these quality users than traditional machine learning models. For instance, a user who spends a lot on a live event but not again over the next 60 days may be misidentified by logistic regression models as a low-value user. Neural network models, with their enhanced memory and ability to uncover complex patterns, can recognize high-value users who spend periodically but in large amounts. Engaging and nurturing quality users is crucial for growing a game, and superior, user-centric ad creative is essential for sparking a connection with users. The key to creative innovation is iterating on existing formats to create more personalized forms of engagement based on user behavior. Neural net models accelerate creative testing, making it easier to identify winning ad formats. Liftoff's Cortex has enabled the development of exclusive dynamic ad formats that change depending on user behavior, such as the 'page-turner' format, which introduces a different playable ad if the user does not engage with the initial playable. This format has been shown to increase impression-to-install (ITI) by up to 9.5% and lower cost-per-install (CPI) by 7.5%. By integrating motivational frameworks and data from GameRefinery, Cortex can improve gaming ad creative performance by personalizing delivery and matching users with ads that tap into their motivations. The ultimate goal is to deliver a more personalized ad experience that drives performance for advertisers while providing a relevant, non-disruptive experience for users. With the increasing importance of privacy, advertisers on iOS are facing challenges in working without device-level identifiers. Ironically, this shift has increased the impact of neural network models, which can optimize for outcomes based on user behavior, moving away from reliance on single identifiers. At Liftoff, the results of Cortex have been impressive, with partners seeing an average of 23% lower CPIs, 21% lower CPAs, and 16% higher ROAS. As Seokyung Lee, marketing manager at Playlinks, noted: 'We are satisfied with the strong ML logic of Cortex, which has shown strong ROAS results compared to other networks, with almost 80% of new users on iOS.' Performance marketing managers at Krafton, Sangbum Kim and Kevin Youn, also shared their positive experience with Cortex, stating that it helped them expand their focus to purchase and retention optimization, leading to increased overall campaign ROAS and retention.