A recommender system to address the Cold Start problem for App usage prediction
- PDF / 2,700,928 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 67 Downloads / 155 Views
ORIGINAL ARTICLE
A recommender system to address the Cold Start problem for App usage prediction Di Han1 · Jianqing Li1 · Lei Yang2 · Zihua Zeng1 Received: 5 June 2018 / Accepted: 4 August 2018 © Springer-Verlag GmbH Germany, part of Springer Nature 2018
Abstract The Cold Start Recommender System (RS) for App usage prediction on mobile phones is important for improving new user experience on mobile operating systems. At present, the existing Cold Start RS computes the probability of App launching mainly by mining the potential information of new users and similar users (i.e., collaborative filtering algorithm CF). But for newly installed Apps, the default CF does not have any useful information for App Cold Start recommendation, resulting in the data sparseness. To tackle the problems, we think that App usage periodicity installed by the new user is regularly followed under different conditions. It not only compensates for the data sparseness of similar users but also increases the predictive flexibility when the user’s environment changes. Therefore, we designed Predictor, an efficient dynamic CF fusion algorithm that provides App Cold Start prediction for new users on mobile devices. It dynamically combines both App preferences of similar users (user-based CF) and App usage periodicity (item-based CF) through the conditional combination. Compared to other traditional methods, Predictor proposes more appropriate App launching recommendation and matches the launching expectations of most users. Keywords App Cold Start · Recommender system · Collaborative filtering · App usage periodicity
1 Introduction Currently, all the mobile systems (Android and iOS) and mobile phone manufacturers have added predictive recommendation function in App launching. By collecting historical data of the user, the mobile system can predict the behavior of the user, allowing the user to accurately locate the very App that he wants to start among many, with a better user experience. Although the methods used in these Recommender Systems (RS) from different mobile phone manufacturers are not exactly the same, the basic source of the model training dataset is users’ contextual behavior, such as the Apps log opened last time, and whether it has been connected with Bluetooth, power supply, location, WiFi and so on. Unlike our work, we call these existing predictions
* Jianqing Li [email protected] 1
Faculty of Information Technology, Macau University of Science and Technology, Taipa, Macau
School of Software Engineering, South China University of Technology, Guangzhou, China
2
using user context of App history records as “Warm Start” [1]. However, many manufacturers begin to attach importance to App launching prediction when users first use the prediction system. We refer to user installing and launching the prediction mechanism for the first time as “Cold Start” prediction [2], which is currently an intensively studied issue on the mobile Internet. Lack of accurate recommendation for initial users on mobile devices can bring po
Data Loading...
