Enhancing session-based E-commerce recommendations with self-attention: a transformer-based approach

In e-commerce, suggesting relevant items to users based on their immediate, in-session behavior is a critical task. Session-based recommendation systems (SBRS) aim to infer a user's short-term intent from the sequence of interactions within a single browsing session. Although recurrent and convolutional models (RNN/CNN) have been widely used, their reliance on strictly local or sequential processing restricts their ability to capture global relationships spanning the entire session. To address this, we introduce the Transformer-based Session Recommender (T-SR), which applies multi-head self-attention to evaluate all item interactions simultaneously. This mechanism enables the model to learn long-range and global behavioral patterns. Experiments on the RecSys 2020 e-commerce dataset demonstrate that T-SR significantly outperforms CNN and RNN baselines in ranking performance, achieving a Hit Rate (HR@10) of 0.652 and an NDCG@10 of 0.580, showcasing its effectiveness in generating relevant recommendation lists.

• Publication year

  2026

• Venue

  Modern Innovations Systems and Technologies

• Publication date

  2026-02-09

• Fields of study

  Not labeled

• Identifiers
  DOI 10.47813/2782-2818-2026-6-1-3043-3050
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Session based recommendation system using gradient descent temporal CNN for e-commerce application

  2024cited by this paper
• The Impact of Digital Marketing on the Performance of SMEs: An Analytical Study in Light of Modern Digital Transformations

  2024cited by this paper
• BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer

  2019cited by this paper
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

  2019cited by this paper
• Deep Learning Recommendation Model for Personalization and Recommendation Systems

  2019cited by this paper
• 3D Convolutional Networks for Session-based Recommendation with Content Features

  2017cited by this paper
• Attention is All you Need

  2017cited by this paper
• Collaborative Filtering

  2016cited by this paper
• RECURRENT NEURAL NETWORKS

  2015cited by this paper
• Content-Based Recommendation Systems

  2007cited by this paper

• No citing papers are available for this paper.