Applying Heuristic and Machine Learning Strategies to Product Resolution

Oliver Strauß, Ahmad Almheidat, Holger Kett

2019

Abstract

In order to analyze product data obtained from different web shops a process is needed to determine which product descriptions refer to the same product (product resolution). Based on string similarity metrics and existing product resolution approaches a new approach is presented with the following components: a) extraction of information from the unstructured product title extracted from the e-shops, b) inclusion of additional information in the matching process, c) a method to compute a product similarity metric from the available data, d) optimization and adaption of model parameters to the characteristics of the underlying data via a genetic algorithm and e) a framework to automatically evaluate the matching method on the basis of realistic test data. The approach achieved a precision of 0.946 and a recall of 0.673.

Paper Citation

in Harvard Style

Strauß O., Almheidat A. and Kett H. (2019). Applying Heuristic and Machine Learning Strategies to Product Resolution.In Proceedings of the 15th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST, ISBN 978-989-758-386-5, pages 242-249. DOI: 10.5220/0008069402420249

in Bibtex Style

@conference{webist19,
author={Oliver Strauß and Ahmad Almheidat and Holger Kett},
title={Applying Heuristic and Machine Learning Strategies to Product Resolution},
booktitle={Proceedings of the 15th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST,},
year={2019},
pages={242-249},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008069402420249},
isbn={978-989-758-386-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST,
TI - Applying Heuristic and Machine Learning Strategies to Product Resolution
SN - 978-989-758-386-5
AU - Strauß O.
AU - Almheidat A.
AU - Kett H.
PY - 2019
SP - 242
EP - 249
DO - 10.5220/0008069402420249