In our codelab we have abstracted away the process of refining the model architecture, so you can still implement this workflow without having much of a background in ML. In a production workflow we would retrain the model regularly with fresh data to ensure that it continues to behave optimally. We picked a reference architecture implemented in TensorFlow, and iterated both on the data we used to train it and the architecture itself. number of layers, types of layers, operations), data, and the actual training process. Training requires a model architecture (e.g. Train the model, evaluate its performance, and iterate In our scenario, it makes it easy to summarize and transform the data to get it ready for model training, as well as combine it with other data sources our app might be using BigQuery is Google’s fully-managed, serverless data warehouse that enables scalable analysis over petabytes of data. We can collect training data easily by sending events to Google Analytics for Firebase and then exporting them to BigQuery.
a user’s skill level, point balance, or choice of avatar may be useful when predicting which powerups they’d prefer). This is where intuition around which factors could influence the outcome are very helpful (e.g. These were of different types, such as event timestamp, user skill levels, information about recent sessions, and other information about the user's gameplay style. HalfBrick collected 129 different signals to train the model. You can also follow along with more detailed implementation steps in the codelab.Ĭollect the data necessary to train the model We have described the problem above, and will now cover the rest of the steps. ML workflows largely anchor themselves on to the following components: A problem to solve, data to train the model, training of the model, model deployment, and client-side implementation. Once trained, the model runs fully on-device, so it doesn’t require network requests to a cloud service and there are no per-inference costs. why they died in the last round, what powerups they selected), and increased conversions by 36% in just our first iteration of the experiment. Using a custom ML model, we were able to personalize which reward to offer using inputs such as the gamer’s skill level, and information about the current session (e.g. Before the study, the digital good offered in return for watching the ad was always selected at random. Our objective was to increase the conversion rate for this particular interaction. In-between levels, players are presented with an option to obtain a digital good by watching a rewarded video ad. We recently worked with game developer HalfBrick on optimizing player rewards within one of their most popular games, with over 500M downloads, Jetpack Joyride.
"What is the right frequency to offer a rewarded video to each user?") we recommend using Firebase Remote Config’s personalization feature.
If you are looking for a simpler personalization solution that doesn’t require you to train your own model and where the answer is unlikely to change multiple times per session (e.g. “Which item from the catalog should I offer to a user that has reached skill level ‘pro’, is on level 5, and has 1 life left?")Ĭustom ML models can be architected, tuned, and trained based on the inputs that you think are relevant to your decision, making the implementation specific to your use case and customers. Once trained, they can “ask” the model to give the best recommendations for a particular user given a set of inputs (e.g. However, taking all relevant signals into account, game developers can train a Machine Learning model to create a personalized experience for each user. In this blog post we'll walk through how HalfBrick implemented this functionality and share a codelab for you to try it yourself.Įvery end-user or gamer is different, and personalizing an app purely based on hard-coded logic can quickly become complex and hard to scale. We worked with game developer HalfBrick to train and implement a custom model that personalized the user's in-game experience based on the player's skill level and session details, resulting in increased interactions with a rewarded video ad unit by 36%. Mobile app and game developers can use on-device machine learning in their apps to increase user engagement and grow revenue.
0 kommentar(er)
