Scalable Content-Aware Collaborative Filtering for Location Recommendation

ABSTRACT:

Location recommendation plays an essential role in helping people find attractive places. Though recent research has studied how to recommend locations with social and geographical information, few of them addressed the cold-start problem of new users. Because mobility records are often shared on social networks, semantic information can be leveraged to tackle this challenge. A typical method is to feed them into explicit-feedback-based content-aware collaborative filtering, but they require drawing negative samples for better learning performance, as users’ negative preference is not observable in human mobility. However, prior studies have empirically shown sampling-based methods do not perform well. To this end, we propose a scalable Implicit-feedback-based Content-aware Collaborative Filtering (ICCF) framework to incorporate semantic content and to steer clear of negative sampling. We then develop an efficient optimization algorithm, scaling linearly with data size and feature size, and quadratically with the dimension of latent space. We further establish its relationship with graph Laplacian regularized matrix factorization. Finally, we evaluate ICCF with a large-scale LBSN dataset in which users have profiles and textual content. The results show that ICCF outperforms several competing baselines, and that user information is not only effective for improving recommendations but also coping with cold-start scenarios.

PROJECT OUTPUT VIDEO:

EXISTING SYSTEM:

• Horozov et al. have developed a user-based collaborative filtering system to recommend restaurants to a user.

• Zheng et al. design a random walk style model for tourism hot spot recommendation. They consider location recommendation and activity recommendation together, so that they can provide location recommendation with respect to different types of activities.

• Ye et al. study how to jointly exploit geographical influence and collaborative filtering for recommending points of interest (of any category) given large scale mobility records from location-based social networks.

• Content-aware collaborative filtering is the integration of content-based recommendation and collaborative filtering. In recent years, several general algorithms, including the regression-based latent factor model, LibFM, MatchBox, and SVD Feature, have been proposed. These algorithms are almost equivalent to each other in model representation but different in terms of optimization algorithms.

DISADVANTAGES OF EXISTING SYSTEM:

• In the existing methods, we mainly study the effects of user information instead of location information on recommendation. User information should be more important than location information when addressing the cold start problem since it is available earlier for inferring user interest.

• Existing works do not take all the characteristics of implicit feedback into account, and most of them require sampling negatively preferred locations from unvisited ones.

PROPOSED SYSTEM:

• In this paper, we propose a novel scalable Implicit-feedback based Content-aware Collaborative Filtering (ICCF) framework. It steers clear of sampling negative locations, by treating all unvisited locations as negative and proposing a sparse and rank-one weighting configuration for modeling preference confidence.

• This sparse and rankone weighting configuration not only assigns vastly varying confidence to visited and unvisited locations, but also subsumes three previously developed different weighting schemes for unvisited locations and naturally introduces a novel mixed weighting scheme.

• ICCF takes a user-location preference matrix, a user-feature matrix (e.g., gender, age and tweets) and a location-feature matrix (e.g., categories, descriptions and neighborhood) as input, and maps each user, each location and their features onto a joint latent space, such that the dot product between two objects defines a preference score.

ADVANTAGES OF PROPOSED SYSTEM:

• ICCF not only improves location recommendation, but also addresses the cold-start problems of both new users and new locations.

• The effectiveness of the proposed sparse and rank-one weighting schemes has been extensively evaluated, showing its significant benefit for improving recommendation, in particular for locations at long tails.

• We propose an efficient coordinate descent optimization algorithm to learn parameters in the sparse and rank-one weighting schemes, which scales linearly with data size and feature size, and quadratically with the dimension of latent space.

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

• System           : Pentium Dual Core.

• Hard Disk      : 120 GB.

• Monitor          : 15’’ LED

• Input Devices : Keyboard, Mouse

• Ram                : 1 GB

SOFTWARE REQUIREMENTS:

• Operating system : Windows 7.

• Coding Language : Python

• Database               : MYSQL

REFERENCE:

Defu Lian, Yong Ge, Fuzheng Zhang, Nicholas Jing Yuan, Xing Xie, Tao Zhou, and Yong Rui, “Scalable Content-Aware Collaborative Filtering for Location Recommendation”, IEEE Transactions on Knowledge and Data Engineering, 2018.