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 article in proceeding › Academic › 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 .

Original language	English
Title of host publication	Proceedings of the Recommender Systems Challenge 2025
Place of Publication	New York, NY, USA
Publisher	Association for Computing Machinery
Pages	1–6
Number of pages	6
ISBN (Print)	9798400720994
DOIs	https://doi.org/10.1145/3758126.3758188
Publication status	Published - 2025

Publication series

Series	RecSysChallenge: Proceedings of the Recommender Systems Challenge

Keywords

Recommender Systems
Dataset
Evaluation
Sequential Recommendation
Deep Relational Learning

Access to Document

10.1145/3758126.3758188Licence: CC BY

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 Recommender Systems Challenge 2025 (pp. 1–6). Association for Computing Machinery. 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 Recommender Systems Challenge 2025. New York, NY, USA : Association for Computing Machinery, 2025. pp. 1–6 (RecSysChallenge: Proceedings of the Recommender Systems Challenge).

@inproceedings{ee267dd5f4e14ece8551e9fb8cf1638a,

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 .",

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

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",

year = "2025",

doi = "10.1145/3758126.3758188",

language = "English",

isbn = "9798400720994",

series = "RecSysChallenge: Proceedings of the Recommender Systems Challenge",

publisher = "Association for Computing Machinery",

pages = "1–6",

booktitle = "Proceedings of the Recommender Systems Challenge 2025",

address = "United States",

}

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 Recommender Systems Challenge 2025. Association for Computing Machinery, New York, NY, USA, RecSysChallenge: Proceedings of the Recommender Systems Challenge, pp. 1–6. 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 Recommender Systems Challenge 2025. New York, NY, USA: Association for Computing Machinery, 2025. p. 1–6 (RecSysChallenge: Proceedings of the Recommender Systems Challenge).

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

TY - GEN

T1 - The SYNERISE dataset: An E-Commerce Dataset for Sequential Recommendation, Universal Behavior Modeling and Deep Relational Learning

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

Y1 - 2025

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 .

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 .

KW - Recommender Systems

KW - Dataset

KW - Evaluation

KW - Sequential Recommendation

KW - Deep Relational Learning

U2 - 10.1145/3758126.3758188

DO - 10.1145/3758126.3758188

M3 - Conference article in proceeding

SN - 9798400720994

T3 - RecSysChallenge: Proceedings of the Recommender Systems Challenge

SP - 1

EP - 6

BT - Proceedings of the Recommender Systems Challenge 2025

PB - Association for Computing Machinery

CY - New York, NY, USA

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 Recommender Systems Challenge 2025. New York, NY, USA: Association for Computing Machinery. 2025. p. 1–6. (RecSysChallenge: Proceedings of the Recommender Systems Challenge). 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

Keywords

Access to Document

Fingerprint

Cite this