Context-aware POI recommendations in an automotive scenario using multi-criteria decision making methods

Bader, Roland; Neufeld, Eugen; Woerndl, Wolfgang; Prinz, Vivian

doi:10.1145/1961634.1961640

Cited by 26 publications

(13 citation statements)

References 12 publications

(9 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The column "Multi" shows the average multiplicity of user-item pairs in the training events. 4 Chronological train-test splits were created. The length of the test period was selected to be at least one day depending also on the domain and the frequency of events.…”

Section: Methodsmentioning

confidence: 99%

“…Recently, entire workshops were devoted to this topic on major conferences. The application fields of context-aware recommenders include among other movie [6] and music recommendation [5], point-of-interest recommendation (POI) [4], citation recommendation [11]. Context-aware recommender approaches can be classified into three main groups: pre-filtering, postfiltering and contextual modeling [2].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Context-aware item-to-item recommendation within the factorization framework

Hidasi

Tikk²

2013

Proceedings of the 3rd Workshop on Context-Awareness in Retrieval and Recommendation

View full text Add to dashboard Cite

Item-to-item recommendation -when the most similar items sought to the actual item -is an important recommendation scenario in practical recommender systems. One way to solve this task is to use the similarity between item feature vectors of factorization models. By doing so, one may transfer the well-known accuracy of factorization models observed at the personalized recommendations to the item-toitem case. This paper introduces context-awareness to item similarities in the factorization framework. Two levels of context-aware similarities are defined and applied to two context-aware implicit feedback based factorization methods (iTALS and iTALSx). We investigate the advantages and drawbacks of the approaches on four real life implicit feedback data sets and we characterize the conditions for their application. The results suggest that it is worth using contextual information for item-to-item recommendations in the factorization framework, however, one should carefully select the appropriate method to achieve similar accuracy gain than in the case of the more general item-to-user recommendation scenario.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Context-aware item-to-item recommendation within the factorization framework

Hidasi

Tikk²

2013

Proceedings of the 3rd Workshop on Context-Awareness in Retrieval and Recommendation

View full text Add to dashboard Cite

show abstract

“…The application fields of context-aware recommenders include among others: point-of-interest [4], video [33], music [8], and news recommendation [20]. Context-aware recommender approaches can be classified into three main groups: prefiltering, postfiltering, and contextual modeling [3].…”

Section: Related Workmentioning

confidence: 99%

“…This property makes the algorithm suitable to handle the context-aware implicit recommendation problem. 4 iTALS uses pointwise ranking through weighted RMSE (wRMSE)-based loss function and directly minimizes said loss function. Learning efficiency is guaranteed by the careful decomposition of the gradient into independent computations.…”

Section: Review Of Italsmentioning

confidence: 99%

Speeding up ALS learning via approximate methods for context-aware recommendations

Hidasi

Tikk²

2015

Knowl Inf Syst

View full text Add to dashboard Cite

Implicit feedback-based recommendation problems, typically set in real-world applications, recently have been receiving more attention in the research community. From the practical point of view, scalability of such methods is crucial. However, factorization-based algorithms efficient in explicit rating data applied directly to implicit data are computationally inefficient; therefore, different techniques are needed to adapt to implicit feedback. For alternating least squares (ALS) learning, several research contributions have proposed efficient adaptation techniques for implicit feedback. These algorithms scale linearly with the number of nonzero data points, but cubically in the number of features, which is a computational bottleneck that prevents the efficient usage of accurate high factor models. Also, map-reduce type big data techniques are not viable with ALS learning, because there is no known technique that solves the high communication overhead required for random access of the feature matrices. To overcome this drawback, here we present two generic approximate variants for fast ALS learning, using conjugate gradient (CG) and coordinate descent (CD). Both CG and CD can be coupled with all methods using ALS learning. We demonstrate the advantages of fast ALS variants on iTALS, a generic context-aware algorithm, which applies ALS learning for tensor factorization on implicit data. In the experiments, we compare the approximate techniques with the base ALS learning in terms of training time, scalability, recommendation accuracy, and convergence. We show that the proposed solutions offer a trade-off between recommendation accuracy and speed of training time; this makes it possible to apply ALS-based methods efficiently even for billions of data points.

show abstract

“…The considered criteria, their weights and the overall score calculation is presented in more detail in [5]. The parameters were in part derived from an earlier study investigating the influencing factors of gas station selection such as fuel level, detour and total length of route [1]. Due to limited space, we only give a few examples of the context model.…”

Section: Implementation and Evaluation 41 Prototype Implementation Omentioning

confidence: 99%

A model for proactivity in mobile, context-aware recommender systems

Woerndl

Huebner

Bader

et al. 2011

Proceedings of the Fifth ACM Conference on Recommender Systems

Self Cite

View full text Add to dashboard Cite

A proactive recommender system pushes recommendations to the user when the current situation seems appropriate, without explicit user request. This is conceivable in mobile scenarios such as restaurant or gas station recommendations. In this paper, we present a model for proactivity in mobile recommender systems. The model relies on domain-dependent context modeling in several categories. The recommendation process is divided into two phases to first analyze the current situation and then examine the suitability of particular Ítems. We have implemented a prototype gas station recommender and conducted a survey for evaluation. Results showed good correlation of the output of our system with the assessment of users regarding the question when to genérate recommendations.

show abstract

Context-aware POI recommendations in an automotive scenario using multi-criteria decision making methods

Cited by 26 publications

References 12 publications

Context-aware item-to-item recommendation within the factorization framework

Context-aware item-to-item recommendation within the factorization framework

Speeding up ALS learning via approximate methods for context-aware recommendations

A model for proactivity in mobile, context-aware recommender systems

Contact Info

Product

Resources

About