The goal of the collaboration was to increase the LTV of players. AppNava found that almost half of the newcomers of this games leave no money in the game. Their LTV is "0" - no in-app purchase, no rewarding video watching. The LTV (Lifetime Value) prediction is a crucial aspect of user acquisition, game development, and monetization. Otherwise hard to decide "How much you can spend in acquiring a new player?", "What is the potential value of this player?"
The capability of detecting and predicting the LTV segment of players as early as possible is the most important factor for promising mobile games.
AppNava LTV prediction model here to take advantage of the data can bring. Then, AppNava's LTV Model was initiated for Newcomers. AppNava distinguished players into two segments; "valuable players" & "worthless players". The definition of the “worthless player" is one who doesn't interact with opt-in ads & in-app purchases. After the newcomers finished their first session, AppNava detected "worthless players", in the game by using the pLTV segmentation model.
Then "worthless players" (low LTV segment) were associated with interstitial ads while "valuable players" (high LTV) segments didnt.
The LTV of the game increased by 200% by accurately identifying their Lifetime Value. There is no change in Day-7 and Day-10 retention rates of the game even if they implemented interstitial ads. Surprisingly slightly higher retention like 0.80% points.
The most significant benefit of showing interstitial ads to some specific segments is to monetize them in a short time. AppNava Machine Learning Model helped them to predict the lifetime value (LTV) of players precisely. The motto is “know your player” before it is too late!