An Adaptable Framework for Entity Matching Model Selection in Business Enterprises

Entity matching is the process of identifying data in different data sources that refer to the same real-world entity. A significant number of entity matching approaches have been introduced in the literature, which complicates the selection process. In this study, we propose a framework to support researchers in finding the best fitting entity matching model (s) based on the characteristics of their datasets. The proposed framework can be extended by adding more models, features, and use cases. To evaluate the framework, we have conducted a case study in the context of a business enterprise to support them with finding the right entity matching model out of five preselected models by the case study experts. The case study participants confirmed the framework's usefulness in assisting them in finding the best-fitting entity matching models. Having the knowledge regarding entity matching models readily available supports decision-makers at business enterprises in making more efficient and effective decisions that meet their requirements and priorities. Furthermore, such reusable knowledge can be employed by other researchers to develop new concepts and solutions for future challenges.