A Data Driven Approach to Predicting Rating Scores for New Restaurants

Xiaochen Wang, Yanyan Shen, Yanmin Zhu
Proceedings of The 10th Asian Conference on Machine Learning, PMLR 95:678-693, 2018.

Abstract

This paper focuses on predicting rating scores of new restaurants listed in online restaurant review platforms. Most existing works rely on customer reviews to make an prediction. However, in practice, the customer reviews for new restaurants are always missing. In this paper, we mine useful features from the information of restaurants as well as highly available urban data to tackle this problem. We propose a deep-learning based approach called MR-Net to model both endogenous and exogenous factors in a unified manner and capture deep feature interaction for rating score prediction. Extensive experiments on real world data from Dianping show that our approach achieves better performance than various baseline methods. To the best of our knowledge, it is the first work that predicts rating scores for new restaurants without the knowledge of customer reviews.

Cite this Paper


BibTeX
@InProceedings{pmlr-v95-wang18c, title = {A Data Driven Approach to Predicting Rating Scores for New Restaurants}, author = {Wang, Xiaochen and Shen, Yanyan and Zhu, Yanmin}, booktitle = {Proceedings of The 10th Asian Conference on Machine Learning}, pages = {678--693}, year = {2018}, editor = {Zhu, Jun and Takeuchi, Ichiro}, volume = {95}, series = {Proceedings of Machine Learning Research}, month = {14--16 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v95/wang18c/wang18c.pdf}, url = {https://proceedings.mlr.press/v95/wang18c.html}, abstract = {This paper focuses on predicting rating scores of new restaurants listed in online restaurant review platforms. Most existing works rely on customer reviews to make an prediction. However, in practice, the customer reviews for new restaurants are always missing. In this paper, we mine useful features from the information of restaurants as well as highly available urban data to tackle this problem. We propose a deep-learning based approach called MR-Net to model both endogenous and exogenous factors in a unified manner and capture deep feature interaction for rating score prediction. Extensive experiments on real world data from Dianping show that our approach achieves better performance than various baseline methods. To the best of our knowledge, it is the first work that predicts rating scores for new restaurants without the knowledge of customer reviews.} }
Endnote
%0 Conference Paper %T A Data Driven Approach to Predicting Rating Scores for New Restaurants %A Xiaochen Wang %A Yanyan Shen %A Yanmin Zhu %B Proceedings of The 10th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jun Zhu %E Ichiro Takeuchi %F pmlr-v95-wang18c %I PMLR %P 678--693 %U https://proceedings.mlr.press/v95/wang18c.html %V 95 %X This paper focuses on predicting rating scores of new restaurants listed in online restaurant review platforms. Most existing works rely on customer reviews to make an prediction. However, in practice, the customer reviews for new restaurants are always missing. In this paper, we mine useful features from the information of restaurants as well as highly available urban data to tackle this problem. We propose a deep-learning based approach called MR-Net to model both endogenous and exogenous factors in a unified manner and capture deep feature interaction for rating score prediction. Extensive experiments on real world data from Dianping show that our approach achieves better performance than various baseline methods. To the best of our knowledge, it is the first work that predicts rating scores for new restaurants without the knowledge of customer reviews.
APA
Wang, X., Shen, Y. & Zhu, Y.. (2018). A Data Driven Approach to Predicting Rating Scores for New Restaurants. Proceedings of The 10th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 95:678-693 Available from https://proceedings.mlr.press/v95/wang18c.html.

Related Material