Comprehensive Empirical Evaluation of Deep Learning Approaches for Session-based Recommendation in E-Commerce

• URL: http://arxiv.org/abs/2010.12540v1
• Date: Sat, 17 Oct 2020 17:22:35 GMT
• Title: Comprehensive Empirical Evaluation of Deep Learning Approaches for Session-based Recommendation in E-Commerce
• Authors: Mohamed Maher (1), Perseverance Munga Ngoy (1), Aleksandrs Rebriks (1), Cagri Ozcinar (1), Josue Cuevas (3), Rajasekhar Sanagavarapu (3), Gholamreza Anbarjafari (1 and 2) ((1) iCV Lab, University of Tartu, Tartu, Estonia, (2) Faculty of Engineering, Hasan Kalyoncu University, Gaziantep, Turkey, (3) Rakuten Inc., Big Data Department, Machine Learning Group, Tokyo, Japan)
• Abstract summary: In session-based recommendation, a recommendation system counts on the sequence of events made by a user within the same session to predict and endorse other items. We present a comprehensive evaluation of the state-of-the-art deep learning approaches used in the session-based recommendation.
• Score: 38.42250061908039
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Boosting sales of e-commerce services is guaranteed once users find more matching items to their interests in a short time. Consequently, recommendation systems have become a crucial part of any successful e-commerce services. Although various recommendation techniques could be used in e-commerce, a considerable amount of attention has been drawn to session-based recommendation systems during the recent few years. This growing interest is due to the security concerns in collecting personalized user behavior data, especially after the recent general data protection regulations. In this work, we present a comprehensive evaluation of the state-of-the-art deep learning approaches used in the session-based recommendation. In session-based recommendation, a recommendation system counts on the sequence of events made by a user within the same session to predict and endorse other items that are more likely to correlate with his/her preferences. Our extensive experiments investigate baseline techniques (\textit{e.g.,} nearest neighbors and pattern mining algorithms) and deep learning approaches (\textit{e.g.,} recurrent neural networks, graph neural networks, and attention-based networks). Our evaluations show that advanced neural-based models and session-based nearest neighbor algorithms outperform the baseline techniques in most of the scenarios. However, we found that these models suffer more in case of long sessions when there exists drift in user interests, and when there is no enough data to model different items correctly during training. Our study suggests that using hybrid models of different approaches combined with baseline algorithms could lead to substantial results in session-based recommendations based on dataset characteristics. We also discuss the drawbacks of current session-based recommendation algorithms and further open research directions in this field.

Related papers

• Exploring Popularity Bias in Session-based Recommendation [0.6798775532273751]
  We extend the analysis to session-based setup and adapted propensity calculation to the unique characteristics of session-based recommendation tasks. We study the distributions of propensity and different stratification techniques on different datasets and find that propensity-related traits are actually dataset-specific.
  arXiv  Detail & Related papers  (2023-12-13T02:48:35Z)
• Sample Complexity of Preference-Based Nonparametric Off-Policy Evaluation with Deep Networks [58.469818546042696]
  We study the sample efficiency of OPE with human preference and establish a statistical guarantee for it. By appropriately selecting the size of a ReLU network, we show that one can leverage any low-dimensional manifold structure in the Markov decision process.
  arXiv  Detail & Related papers  (2023-10-16T16:27:06Z)
• Deep networks for system identification: a Survey [56.34005280792013]
  System identification learns mathematical descriptions of dynamic systems from input-output data. Main aim of the identified model is to predict new data from previous observations. We discuss architectures commonly adopted in the literature, like feedforward, convolutional, and recurrent networks.
  arXiv  Detail & Related papers  (2023-01-30T12:38:31Z)
• A Sequence-Aware Recommendation Method Based on Complex Networks [1.385805101975528]
  We build a network model from data and then use it to predict the user's subsequent actions. The proposed method is implemented and tested experimentally on a large dataset.
  arXiv  Detail & Related papers  (2022-09-30T16:34:39Z)
• Sequential Search with Off-Policy Reinforcement Learning [48.88165680363482]
  We propose a highly scalable hybrid learning model that consists of an RNN learning framework and an attention model. As a novel optimization step, we fit multiple short user sequences in a single RNN pass within a training batch, by solving a greedy knapsack problem on the fly. We also explore the use of off-policy reinforcement learning in multi-session personalized search ranking.
  arXiv  Detail & Related papers  (2022-02-01T06:52:40Z)
• A Survey on Neural Recommendation: From Collaborative Filtering to Content and Context Enriched Recommendation [70.69134448863483]
  Research in recommendation has shifted to inventing new recommender models based on neural networks. In recent years, we have witnessed significant progress in developing neural recommender models.
  arXiv  Detail & Related papers  (2021-04-27T08:03:52Z)
• Session-aware Recommendation: A Surprising Quest for the State-of-the-art [6.617487928813376]
  Session-aware recommendations can be personalized according to the users' long-term preferences. We benchmarked recent session-aware algorithms against each other and against a number of session-based recommendation algorithms. Our work indicates that there remains a huge potential for more sophisticated session-aware recommendation algorithms.
  arXiv  Detail & Related papers  (2020-11-06T15:18:01Z)
• A Deep Hybrid Model for Recommendation Systems [0.0]
  We propose a new deep neural network architecture which consists of not only ID embeddings but also auxiliary information such as features of job postings and candidates for job recommendation system. Experimental results on the dataset from a job-site show that the proposed method improves recommendation results over deep learning models utilizing ID embeddings.
  arXiv  Detail & Related papers  (2020-09-21T10:41:28Z)
• S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization [104.87483578308526]
  We propose the model S3-Rec, which stands for Self-Supervised learning for Sequential Recommendation. For our task, we devise four auxiliary self-supervised objectives to learn the correlations among attribute, item, subsequence, and sequence. Extensive experiments conducted on six real-world datasets demonstrate the superiority of our proposed method over existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-08-18T11:44:10Z)
• Long-tail Session-based Recommendation [7.832914615902803]
  We propose a novel network architecture, namely TailNet, to improve long-tail recommendation performance. A novel is proposed and applied in TailNet to determine user preference between two types of items, so as to softly adjust and personalize recommendations.
  arXiv  Detail & Related papers  (2020-07-24T03:36:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.