The SYNERISE dataset: An E-Commerce Dataset for Sequential Recommendation, Universal Behavior Modeling and Deep Relational Learning

Jacek Dabrowski; Maria Janicka; Łukasz Sienkiewicz; Gergely Stomfai; Jannach Dietmar; Francesco Barile; Marco Polignano; Claudio Pomo; Abhishek Srivastava

doi:10.1145/3758126.3758188

The SYNERISE dataset: An E-Commerce Dataset for Sequential Recommendation, Universal Behavior Modeling and Deep Relational Learning

Jacek Dabrowski
, Maria Janicka
, Łukasz Sienkiewicz
, Gergely Stomfai
, Jannach Dietmar
, Francesco Barile
, Marco Polignano
, Claudio Pomo
, Abhishek Srivastava

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Research in the area of recommender systems heavily relies on offline experimentation with historical data. The validity of such research efforts may however be limited by the quality and representativeness of publicly available datasets. To address these limitations, we introduce the Synerise dataset as a new, large-scale e-commerce dataset derived from real-world logs. This dataset provides rich, time-stamped user-item interactions alongside detailed item metadata - including categories, descriptions, and prices - and incorporates user search and navigation behavior for a more holistic understanding of user intent. In the paper, we provide a description of the dataset and how it can be used for model evaluation in different research questions. Furthermore, we provide an overview of the ACM RecSys 2025 Challenge, which introduced the novel task of Universal Behavioral Modeling, and which was based on the Synerise dataset. The dataset can be downloaded at https://recsys.synerise.com.

Original language	English
Title of host publication	Proceedings of the Workshop on the ACM RecSys Challenge 2025
Publisher	Association for Computing Machinery, Inc
Pages	1-6
Number of pages	6
ISBN (Electronic)	9798400720994
DOIs	https://doi.org/10.1145/3758126.3758188
Publication status	Published - 21 Sep 2025
Externally published	Yes
Event	Workshop on the 19th ACM Conference on Recommender Systems, RecSysChallenge 2025 - Prague, Czech Republic Duration: 22 Sep 2025 → 26 Sep 2025

Publication series

Name	Proceedings of the Workshop on the ACM RecSys Challenge 2025

Conference

Conference	Workshop on the 19th ACM Conference on Recommender Systems, RecSysChallenge 2025
Country/Territory	Czech Republic
City	Prague
Period	22/09/25 → 26/09/25

Keywords

Dataset
Deep Relational Learning
Evaluation
Recommender Systems
Sequential Recommendation

Access to Document

10.1145/3758126.3758188

Cite this

Dabrowski, J., Janicka, M., Sienkiewicz, Ł., Stomfai, G., Dietmar, J., Barile, F., Polignano, M., Pomo, C., & Srivastava, A. (2025). The SYNERISE dataset: An E-Commerce Dataset for Sequential Recommendation, Universal Behavior Modeling and Deep Relational Learning. In Proceedings of the Workshop on the ACM RecSys Challenge 2025 (pp. 1-6). (Proceedings of the Workshop on the ACM RecSys Challenge 2025). Association for Computing Machinery, Inc. https://doi.org/10.1145/3758126.3758188

Dabrowski, Jacek ; Janicka, Maria ; Sienkiewicz, Łukasz et al. / The SYNERISE dataset : An E-Commerce Dataset for Sequential Recommendation, Universal Behavior Modeling and Deep Relational Learning. Proceedings of the Workshop on the ACM RecSys Challenge 2025. Association for Computing Machinery, Inc, 2025. pp. 1-6 (Proceedings of the Workshop on the ACM RecSys Challenge 2025).

@inproceedings{31d1aa95f48b4b9ebfb478bfb9daefa0,

title = "The SYNERISE dataset: An E-Commerce Dataset for Sequential Recommendation, Universal Behavior Modeling and Deep Relational Learning",

abstract = "Research in the area of recommender systems heavily relies on offline experimentation with historical data. The validity of such research efforts may however be limited by the quality and representativeness of publicly available datasets. To address these limitations, we introduce the Synerise dataset as a new, large-scale e-commerce dataset derived from real-world logs. This dataset provides rich, time-stamped user-item interactions alongside detailed item metadata - including categories, descriptions, and prices - and incorporates user search and navigation behavior for a more holistic understanding of user intent. In the paper, we provide a description of the dataset and how it can be used for model evaluation in different research questions. Furthermore, we provide an overview of the ACM RecSys 2025 Challenge, which introduced the novel task of Universal Behavioral Modeling, and which was based on the Synerise dataset. The dataset can be downloaded at https://recsys.synerise.com.",

keywords = "Dataset, Deep Relational Learning, Evaluation, Recommender Systems, Sequential Recommendation",

author = "Jacek Dabrowski and Maria Janicka and {\L}ukasz Sienkiewicz and Gergely Stomfai and Jannach Dietmar and Francesco Barile and Marco Polignano and Claudio Pomo and Abhishek Srivastava",

note = "Publisher Copyright: {\textcopyright} 2025 Copyright held by the owner/author(s).; Workshop on the 19th ACM Conference on Recommender Systems, RecSysChallenge 2025 ; Conference date: 22-09-2025 Through 26-09-2025",

year = "2025",

month = sep,

day = "21",

doi = "10.1145/3758126.3758188",

language = "English",

series = "Proceedings of the Workshop on the ACM RecSys Challenge 2025",

publisher = "Association for Computing Machinery, Inc",

pages = "1--6",

booktitle = "Proceedings of the Workshop on the ACM RecSys Challenge 2025",

}

Dabrowski, J, Janicka, M, Sienkiewicz, Ł, Stomfai, G, Dietmar, J, Barile, F, Polignano, M, Pomo, C & Srivastava, A 2025, The SYNERISE dataset: An E-Commerce Dataset for Sequential Recommendation, Universal Behavior Modeling and Deep Relational Learning. in Proceedings of the Workshop on the ACM RecSys Challenge 2025. Proceedings of the Workshop on the ACM RecSys Challenge 2025, Association for Computing Machinery, Inc, pp. 1-6, Workshop on the 19th ACM Conference on Recommender Systems, RecSysChallenge 2025, Prague, Czech Republic, 22/09/25. https://doi.org/10.1145/3758126.3758188

The SYNERISE dataset: An E-Commerce Dataset for Sequential Recommendation, Universal Behavior Modeling and Deep Relational Learning. / Dabrowski, Jacek; Janicka, Maria; Sienkiewicz, Łukasz et al.
Proceedings of the Workshop on the ACM RecSys Challenge 2025. Association for Computing Machinery, Inc, 2025. p. 1-6 (Proceedings of the Workshop on the ACM RecSys Challenge 2025).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - The SYNERISE dataset

T2 - Workshop on the 19th ACM Conference on Recommender Systems, RecSysChallenge 2025

AU - Dabrowski, Jacek

AU - Janicka, Maria

AU - Sienkiewicz, Łukasz

AU - Stomfai, Gergely

AU - Dietmar, Jannach

AU - Barile, Francesco

AU - Polignano, Marco

AU - Pomo, Claudio

AU - Srivastava, Abhishek

PY - 2025/9/21

Y1 - 2025/9/21

N2 - Research in the area of recommender systems heavily relies on offline experimentation with historical data. The validity of such research efforts may however be limited by the quality and representativeness of publicly available datasets. To address these limitations, we introduce the Synerise dataset as a new, large-scale e-commerce dataset derived from real-world logs. This dataset provides rich, time-stamped user-item interactions alongside detailed item metadata - including categories, descriptions, and prices - and incorporates user search and navigation behavior for a more holistic understanding of user intent. In the paper, we provide a description of the dataset and how it can be used for model evaluation in different research questions. Furthermore, we provide an overview of the ACM RecSys 2025 Challenge, which introduced the novel task of Universal Behavioral Modeling, and which was based on the Synerise dataset. The dataset can be downloaded at https://recsys.synerise.com.

AB - Research in the area of recommender systems heavily relies on offline experimentation with historical data. The validity of such research efforts may however be limited by the quality and representativeness of publicly available datasets. To address these limitations, we introduce the Synerise dataset as a new, large-scale e-commerce dataset derived from real-world logs. This dataset provides rich, time-stamped user-item interactions alongside detailed item metadata - including categories, descriptions, and prices - and incorporates user search and navigation behavior for a more holistic understanding of user intent. In the paper, we provide a description of the dataset and how it can be used for model evaluation in different research questions. Furthermore, we provide an overview of the ACM RecSys 2025 Challenge, which introduced the novel task of Universal Behavioral Modeling, and which was based on the Synerise dataset. The dataset can be downloaded at https://recsys.synerise.com.

KW - Dataset

KW - Deep Relational Learning

KW - Evaluation

KW - Recommender Systems

KW - Sequential Recommendation

UR - https://www.scopus.com/pages/publications/105020568843

U2 - 10.1145/3758126.3758188

DO - 10.1145/3758126.3758188

M3 - Conference contribution

AN - SCOPUS:105020568843

T3 - Proceedings of the Workshop on the ACM RecSys Challenge 2025

SP - 1

EP - 6

BT - Proceedings of the Workshop on the ACM RecSys Challenge 2025

PB - Association for Computing Machinery, Inc

Y2 - 22 September 2025 through 26 September 2025

ER -

Dabrowski J, Janicka M, Sienkiewicz Ł, Stomfai G, Dietmar J, Barile F et al. The SYNERISE dataset: An E-Commerce Dataset for Sequential Recommendation, Universal Behavior Modeling and Deep Relational Learning. In Proceedings of the Workshop on the ACM RecSys Challenge 2025. Association for Computing Machinery, Inc. 2025. p. 1-6. (Proceedings of the Workshop on the ACM RecSys Challenge 2025). doi: 10.1145/3758126.3758188

The SYNERISE dataset: An E-Commerce Dataset for Sequential Recommendation, Universal Behavior Modeling and Deep Relational Learning

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this