@article{GrafLaskowskiPapsdorfetal.2022,
  author    = {Graf, Martin and Laskowski, Lukas and Papsdorf, Florian and Sold, Florian and Gremmelspacher, Roland and Naumann, Felix and Panse, Fabian},
  title     = {Frost: a platform for benchmarking and exploring data matching results},
  series = {Proceedings of the VLDB Endowment},
  volume    = {15},
  journal   = {Proceedings of the VLDB Endowment},
  number    = {12},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {2150-8097},
  doi       = {10.14778/3554821.3554823},
  pages     = {3292 -- 3305},
  year      = {2022},
  abstract  = {"Bad" data has a direct impact on 88\% of companies, with the average company losing 12\% of its revenue due to it. Duplicates - multiple but different representations of the same real-world entities are among the main reasons for poor data quality, so finding and configuring the right deduplication solution is essential. Existing data matching benchmarks focus on the quality of matching results and neglect other important factors, such as business requirements. Additionally, they often do not support the exploration of data matching results. To address this gap between the mere counting of record pairs vs. a comprehensive means to evaluate data matching solutions, we present the Frost platform. It combines existing benchmarks, established quality metrics, cost and effort metrics, and exploration techniques, making it the first platform to allow systematic exploration to understand matching results. Frost is implemented and published in the open-source application Snowman, which includes the visual exploration of matching results, as shown in Figure 1.},
  language  = {en}
}