Owing to the improved computational capacity and affordability of mobile phones, the user base of mobile games is growing. Improving the user experience by making personalised game suggestions is therefore a topic of great interest in both academic and commercial arenas. This collaborative project aims at building a recommender system to provide better game recommendations on the Game Launcher Platform of Samsung Galaxy devices. The implemented solution provides Samsung Research UK with an alternative approach to create more efficient game recommendations.
Explaining the science
When considering recommender systems, the problem can be framed in terms of two types of entities: users - individuals to whom the recommendations are made - and items - entities that are recommended to the users such as movies, news articles or in our case, mobile games. The relationship between users and items can be represented by a so-called user-item matrix, where every element represents the preference of a given user for a specific item, here this relationship is the preference of a game player given an Android game. These preferences can be provided by users explicitly in the form of a rating (e.g., a number between 0 and 5).
Alternatively, preferences can be induced from implicit feedback provided by the users, for instance, you can use the number of times a user has listened to a particular song to deduce whether the user likes the song or not. However, in either cases, there isn't preference information available for every user and for every item. Take users of the online shopping site Amazon, it is quite unlikely for every user user to have a feedback for every single item on the website. The main goal of a recommender tool is therefore to fill in the missing preference information for users. Items with higher preference score will then be recommended to the users.
Getting the right information
As people spend more time online and on their mobile phones, the quantity of data they generate is reaching staggering proportions. Although the number of users and items do increase, the number of different items that users interact with does not necessarily increase, which leads to almost entirely incomplete user-item matrices. Traditional approaches attempt to infer user preference by using solely the known interaction between the users and items, however these methods perform poorly when these known user-item interactions, i.e. preferences, are extremely limited.
Recent developments therefore are investigating whether incorporating auxiliary information can lead to better methods to estimate preference and hence provide better recommendations. For example, if creating a tool for recommending songs, it might be useful to consider additional information coming from the songs such as audio and lyrics or to add extra information about the users. This is a very intuitive approach, and allows the recommender system to learn directly which users are similar to one another, and likewise for items.
The striking performance of deep learning methods have placed them at the very heart of modern recommender tools. A number of studies have been proposed using deep learning methods together with more traditional approaches since these hybrid recommender systems provide a deeper understanding of different aspects of users and items as well as the relationship between them. In this project, a hybrid model is exploited based on the approach proposed in Kim et al. This method has a proven advantage especially when there is text-based auxiliary information which in this case is the descriptions of the mobile games.
The project seeks to build a recommender system incorporating state of the art deep learning based tools. The main aim of the project is to achieve an improved user engagement with the suggested game via increased clicks, installs and the quality of gaming experience as well as to have an increased retention period compared to the other players who have not been recommended the game.
This is a six month collaborative project between the Turing and Samsung Research UK, the collaboration having originated from the Turing Data Study Group in May 2017. Whilst maintaining close contact, both parties are working on creating separate recommender tools to be able to compare the performance of different methodologies on solving the given problem.
With the proliferation of technological devices, unprecedented amounts of data now are available online. Recommender systems offer a solution to filter this increased amount of online data to assist users to make the best informed decisions. Recommender tools are being used to address a diverse set of problems, from generating film recommendations to shopping suggestions. The tool generated in this project can be applied to any recommendation problem where text-based auxiliary data exist.
This project has been successfully completed including submission of a report and complete code files (see the GitHub repo) alongside a final meeting with the Samsung Research UK.