Predicting and Recommending the next Smartphone Apps based on Recurrent Neural Network
- PDF / 2,018,719 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 43 Downloads / 368 Views
REGULAR PAPER
Predicting and Recommending the next Smartphone Apps based on Recurrent Neural Network Shijian Xu1 · Wenzhong Li1 · Xiao Zhang1 · Songcheng Gao1 · Tong Zhan1 · Sanglu Lu1 Received: 3 May 2020 / Accepted: 29 September 2020 © China Computer Federation (CCF) 2020
Abstract The popularity of smartphones has witnessed the rapid growth of the number of mobile applications. Nowadays, there are millions of applications available, and at the same time, many applications are already installed on people’s smartphones. Installing numerous apps will cause some troubles in finding the specific apps promptly. Hence it is necessary to predict the next app(s) to be used in a short term and launching them as shortcuts, which will make the smartphone system more efficient and user-friendly. In this paper, we pay attention to two subproblems that are related to the app usage prediction. One is the 𝛥T app prediction problem that focuses on predicting a set of apps that will be used in a time interval. The other is the Top-K app recommendation problem that focuses on recommending the K most probable APPs to be used next. In order to solve these problems, we propose a generic prediction model based on Long Short-term Memory (LSTM), which is an enhancement of the recurrent neural network (RNN) model. The proposed model converts the temporal-sequence dependency and contextual information into a unified feature representation for next app prediction. We implement the model in the Android platform. Extensive experiments based on real collected dataset demonstrate that the proposed LSTM model outperforms the baselines for app usage prediction, and achieves high accuracy for app recommendation. Keywords Smartphone · App usage prediction · Recurrent neural network · LSTM
1 Introduction Nowadays, smartphones have become an indispensable part of people’s daily lives. Due to the easy accessibility and great conveniences that mobile applications bring to everyday life, the number of applications installed in smartphones has been keeping growing. According to the report of Statista,1 by the fourth quarter of 2019, the number of apps available for download on Google Play is 2.57 million and it is 1.84 million on Apple App Store. Another report conducted by App Annie2 said that by 2017, the average number of apps installed on smartphones is about 80 to 90 and the average number of apps used per day is up to 10. Installing so many applications has brought some inconvenience to users. When a user is going to use some particular * Wenzhong Li [email protected] Sanglu Lu [email protected] 1
State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China
apps, they are not always available promptly, and searching for these applications will waste a lot of time. Therefore, accurate prediction of the next apps to be used may help the design of smartphone systems to quickly launch apps and pre-fetch content, thereby improving the user’s quality of experience (QoE). Many works have been done to make the specific apps
Data Loading...
