Xiangjie Kong

TL;DR: This paper proposes a novel method to solve the cross-domain recommendation problem in the scenario, where there are common ratings between different domains, and compares it to a trust-aware recommendation method and demonstrates its effectiveness in terms of prediction accuracy, recall, and coverage.

TL;DR: An extreme gradient boosting-based collaboration sustainability prediction model named CSTeller is devised and proposed to analyze the sustainability of scientific collaboration from the perspectives of collaboration duration and collaboration times and investigates factors that may affect collaboration sustainability based on scholars’ local properties and network properties.

TL;DR: A novel approach to predict the urban traffic congestion efficiently with floating car trajectory data using an innovative traffic flow prediction method utilizing particle swarm optimization algorithm and a congestion state fuzzy division module is applied.

TL;DR: This paper proposes a data-driven taxi operation strategy to maximize drivers' profit, reduce energy consumption, and decrease environment pollution, and introduces the Time-Location-Sociality model which can identify three dimensional properties of city dynamics to predict the number of passengers in different social functional regions.

TL;DR: A novel social matrix factorization-based recommendation method is proposed to improve the recommendation quality by fusing user’s social status and homophily and is evaluated using real-life datasets including the Epinions and Douban datasets.