Corpus ID: 199064378

Session-Based Hotel Recommendations: Challenges and Future Directions

@article{Adamczak2019SessionBasedHR,
  title={Session-Based Hotel Recommendations: Challenges and Future Directions},
  author={Jens Adamczak and Gerard Paul Leyson and Peter Knees and Yashar Deldjoo and Farshad Bakhshandegan Moghaddam and Julia Neidhardt and Wolfgang W{\"o}rndl and Philipp Monreal},
  journal={ArXiv},
  year={2019},
  volume={abs/1908.00071}
}
In the year 2019, the Recommender Systems Challenge deals with a real-world task from the area of e-tourism for the first time, namely the recommendation of hotels in booking sessions. In this context, this article aims at identifying and investigating what we believe are important domain-specific challenges recommendation systems research in hotel search is facing, from both academic and industry perspectives. We focus on three main challenges, namely dealing with (1) multiple stakeholders and… Expand
Session-based Hotel Recommendations Dataset
TLDR
The qualitative characteristics of the dataset are described and the comparison of several baseline algorithms trained on the data are presented, which are vitally important for recommendation systems research in the area of hotel search. Expand
Boosting algorithms for a session-based, context-aware recommender system in an online travel domain
TLDR
This paper presents the approach to the 2019 RecSys Challenge on the proper problem representation, feature extraction, and model blending, and achieves the 1st place out of 500 teams. Expand
A 2020 perspective on "Online guest profiling and hotel recommendation": Reliability, Scalability, Traceability and Transparency
TLDR
An update and comment is offered on the previous article by providing a recent literature review and identifying the challenges laying ahead concerning the online recommendation of tourism resources supported by crowdsourced data. Expand
RecSys challenge 2019: session-based hotel recommendations
The workshop features presentations of accepted contributions to the RecSys Challenge 2019 organized by trivago, TU Wien, Politecnico di Bari, and Karlsruhe Institute of Technology. In the challenge,Expand
Session-based Hotel Recommendations Dataset
TLDR
In 2019, the Recommender Systems Challenge dealt for the first time with a real-world task from the area of e-tourism, namely the recommendation of hotels in booking sessions, and the results showed strong support for web-based reservations. Expand
A pipelined hybrid recommender system for ranking the items on the display
TLDR
This work proposes a pipelined hybrid recommender system that considers the two contexts simultaneously via weighted summation of loss functions designed for the combination of a recurrent neural network (RNN) and a convolutional neural networks (CNN). Expand
Towards Evaluating User Profiling Methods Based on Explicit Ratings on Item Features
TLDR
Differences between explicit user preferences and implicit user profiles modelled by the best investigated profiling method are investigated and encourage a more in-depth study to investigate and improve this important user profile modelling step, which will eventually translate into better recommendations. Expand
Booking.com Multi-Destination Trips Dataset
TLDR
A novel dataset of real multi-destination trips booked through Booking.com, which consists of 1.5 million reservations representing 359,000 unique journeys made across 39,000 destinations, presents a uniquely valuable resource for Machine Learning and information retrieval researchers. Expand
Hotel2vec: Learning Hotel Embeddings from User Click Sessions with Side Information
We propose a new neural network architecture for learning vector representations of items with attributes, specifically hotels. Unlike previous works, which typically only rely on modeling ofExpand
Recommender Systems Fairness Evaluation via Generalized Cross Entropy
TLDR
It is argued that fairness in recommender systems does not necessarily imply equality, but instead it should consider a distribution of resources based on merits and needs, and a probabilistic framework based on generalized cross entropy is presented. Expand
...
1
2
...

References

SHOWING 1-4 OF 4 REFERENCES
Recommender systems based on user reviews: the state of the art
TLDR
This article provides a comprehensive overview of how the review elements have been exploited to improve standard content-based recommending, collaborative filtering, and preference-based product ranking techniques and classifies state-of-the-art studies into two principal branches: review-based user profile building and review- based product profile building. Expand
Evaluation of recommender systems: A new approach
TLDR
A framework is proposed, attempting to extract the essential features of recommender systems, and it is shown that a new metric emerges naturally from this framework, the most essential feature is the objective of the recommender system. Expand
Statistical Methods for Recommender Systems
TLDR
This comprehensive treatment of the statistical issues that arise in recommender systems includes detailed, in-depth discussions of current state-of-the-art methods such as adaptive sequential designs (multi-armed bandit methods), bilinear random-effects models (matrix factorization), and scalable model fitting using modern computing paradigms like MapReduce. Expand
IT and tourism: still a hot topic, but do not forget IT
TLDR
It is argued that IT and tourism is still a hot topic, also or especially from a scientific point of view, and it is claimed that, in order to prevent the field from becoming insignificant, more emphasis must be put on technical and formal aspects of science. Expand