Which app will you use next?

Abstract

The application a smart phone user will launch next intuitively depends on the sequence of apps used recently. More generally, when users interact with systems such as shopping websites or online radio, they click on items that are of interest in the current context. We call the sequence of clicks made in the current session interactional context. It is desirable for a recommender system to use the context set by the user to update recommendations. Most current context-aware recommender systems focus on a relatively less dynamic representational context defined by attributes such as season, location and tastes. In this paper, we study the problem of collaborative filtering with interactional context, where the goal is to make personalized and dynamic recommendations to a user engaged in a session. To this end, we propose the iConRank algorithm that works in two stages. First, users are clustered by their transition behavior (one-step Markov transition probabilities between items), and cluster-level Markov models are computed. Then personalized PageRank is computed for a given user on the corresponding cluster Markov graph, with a personalization vector derived from the current context. We give an interpretation of the second stage of the algorithm as adding an appropriate context bias, in addition to click bias (or rating bias), to a classical neighborhood-based collaborative filtering model, where the neighborhood is determined from a Markov graph. Experimental results on two reallife datasets demonstrate the superior performance of our algorithm, where we achieve at least 20% (up to 37%) improvement over competitive methods in the recall level at top-20.

A Next Application Prediction Service Using the BaranC Framework

“…Most of the current proposed works [10], [11] seem to focus on recommending an application to install based on the context and only consider representational context such as location, time, etc. Nagarajan et al [12] present an algorithm, iConRank, in order to rank the applications based on the recent app sequences. They believe that the sequence of recent applications is related to the next application.…”

“…The service has four components, Data Handler, Pattern Recognizer, Rule Learner, and Recommender. There are various work show why and where the next application prediction is important [16], [12]. The recommender systems, adaptive services, and contextaware applications are examples that use next user action's prediction [14].…”

A Service-Oriented User Interaction Analysis Framework Supporting Adaptive Applications

“…Analysing the UDI enables better understanding of a user [1] and provides the basis for personalized services [14], [13]. The UDI can, therefore, be a valuable basis for many applications such as recommender systems [10], [11], games, adaptable services [9]. They can use a user model or presence in order to change their services and systems behaviour.…”

“…The available context (at the time that the user interacts) is important in building a rich user model. Several projects employ a user behavioural model in order to better understand, and provide adaptive and personalized services, to a user [9], [10], [11], [12]. For instance, a software system, MoodScope [13], infers the user's mood based on their smart-phone usage.…”

A pro-active and dynamic prediction assistance using BaranC framework

“…the sequence of applications, music, etc.) has been used, however, for predicting future actions [8]. These approaches do not seem to attempt recommendations based on both interactional and Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page.…”