Replication data for: Context-adaptive deep learning for sustainable product recommendation: Application to concrete

DOI

This repository contains the training dataset, evaluation dataset, and expert validation data for the paper "Deep learning for multi-criteria construction product selection: A context-sensitive preference scoring model applied to concrete". The dataset comprises 42,874 labelled scenarios combining deterministic control cases, LLM-generated synthetic labels, and expert annotations, each describing between two and five concrete product alternatives characterised by sustainability, performance, stakeholder, and situational features. The expert validation subset includes preference rankings and confidence scores collected from six domain experts across 32 real-product scenarios, used to assess alignment between model outputs and professional judgement. The code used to train, test, and validate the model is publicly available at https://github.com/eirasroger/concrete-selection-dl-model

Identifier
DOI https://doi.org/10.34810/DATA3164
Metadata Access https://dataverse.csuc.cat/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=doi:10.34810/DATA3164
Provenance
Creator Vergés, Roger ORCID logo; Gaspar, Katia ORCID logo; Forcada, Nuria ORCID logo; Hosseini, M. Reza (ORCID: 0000-0001-8675-736X)
Publisher CORA.Repositori de Dades de Recerca
Contributor Vergés, Roger; Universitat Politècnica de Catalunya; 170 (MP)
Publication Year 2026
Funding Reference https://ror.org/01bg62x04 2023 DI 00037 ; https://ror.org/01bg62x04 2021 SGR 00341 ; https://ror.org/003x0zc53 PID2024-158844OB-I00
Rights CC BY-NC 4.0; info:eu-repo/semantics/openAccess; http://creativecommons.org/licenses/by-nc/4.0
OpenAccess true
Contact Vergés, Roger (Universitat Politècnica de Catalunya)
Representation
Resource Type Experimental data; Dataset
Format application/json; text/plain
Size 9461; 627958; 144860; 103217844; 39216666; 5229
Version 1.0
Discipline Construction Engineering and Architecture; Engineering; Engineering Sciences
Spatial Coverage (2.034W, 41.540S, 2.084E, 41.573N)