Probabilistic sequential POIs recommendation via check-in data

Abstract

While on the go, people are using their phones as a personal concierge discovering what is around and deciding what to do. Mobile phone has become a recommendation terminal customized for individuals. While existing research predominantly focuses on one-step recommendation-recommending the next single activity according to current context, this work moves one step beyond by recommending a series of activities, which is a package of sequential Points of Interest (POIs). The recommended POIs are not only relevant to user context (i.e., current location, time, and check-in), but also personalized to his/her check-in history. We presents a probabilistic approach, which is highly motivated from a large-scale commercial mobile check-in data analysis, to ranking a list of sequential POI categories (e.g., "Japanese food" and "bar") and POIs (e.g., "I love sushi"). The approach enables users to plan consecutive activities on the move. Specifically, the probabilistic recommendation approach estimates the transition probability from one POI to another, conditioned on current context and check-in history in a Markov chain. To alleviate the discritization error and sparsity problem, we further introduce context collaboration and integrate prior information. Experiments on over 100k real-world check-in records and 20k POIs validate the effectiveness of the proposed approach. (a) user info and context (b) rank of sequential POI categories (c) rank of sequential POIs 1 2 3 4 6 5 Package #1 Package #2 Figure 1: The interface of sequential POI recommendation application developed based on the proposed approach. A user named "Emily" checks in a shopping mall at the context of (a), and gets recommendation of (b) sequential POI categories (e.g., cafe→restaurant) and (c) the corresponding packages of sequential POIs when selecting a specific POI category sequence in (b). The recommendation of sequential POI categories and POIs rather a single POI is a metaphor of "plan activities in real life" and thus more natural to mobile users. Users will have much less interactions with the phone to complete their tasks.

Survey on Recommendation of Personalized Travel Sequence

“…This approach of recommendation is highly motivated from a large-scale commercial mobile check-in data analysis, to rank a list of sequential POI categories and different POIs. The approach enables users to plan continuous activities going from one place to another [3].…”

Dynamic user data analysis and web composition technique using big data

“…A wide study has been conducted on web service QoS for commission composition and repair choice [2]. Service providers or third party organizations achieve the QoS values easily is a presumption by the earlier research investigations.…”

“…Several researchers [2] have analysed a mechanism to identify the unknown QoS values. The values of QoS for internet services can be identified by two approaches namely memory based or neighborhood-based and cooperative filtering (CF).…”

“…The experiment results illustrate that the developed hybrid preference model analyses the user inclination in a better manner by preserving the consistency of the preference, and the proposed algorithm out performs the traditional approaches. Jitao Sang [2] developed a mobile phone which has been considered as a terminal for recommendation tailored for individuals. Most of the current research primarily emphasizes on recommendation in a single stage ie.…”

Travel Recommendation Based on Data From Social Media

“…on social media record users" daily life and travel experience. These data are not solely helpful for reliable POIs (points of interest) Ming dynasty [4], travel routes ming, but provide Associate in Nursing chance to suggest customized travel POIs and routes supported user"s interest. There are two main challenges for automatic travel recommendation.…”