@article{Kruse_Awick_Marx Gómez_Loos_2021, title={Developing a Legal Form Classification and Extraction Approach for Company Entity Matching: Benchmark of Rule-Based and Machine Learning Approaches}, volume={1}, url={https://www.tib-op.org/ojs/index.php/bis/article/view/44}, DOI={10.52825/bis.v1i.44}, abstractNote={<p>This paper explores the data integration process step record linkage. Thereby we focus on the entity company. For the integration of company data, the company name is a crucial attribute, which often includes the legal form. This legal form is not concise and consistent represented among different data sources, which leads to considerable data quality problems for the further process steps in record linkage. To solve these problems, we classify and ex-tract the legal form from the attribute company name. For this purpose, we iteratively developed four different approaches and compared them in a benchmark. The best approach is a hybrid approach combining a rule set and a supervised machine learning model. With our developed hybrid approach, any company data sets from research or business can be processed. Thus, the data quality for subsequent data processing steps such as record linkage can be improved. Furthermore, our approach can be adapted to solve the same data quality problems in other attributes.</p>}, journal={Business Information Systems}, author={Kruse, Felix and Awick, Jan-Philipp and Marx Gómez, Jorge and Loos, Peter}, year={2021}, month={Jul.}, pages={13–26} }