Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

A Hybrid AI Tool to Extract Key Performance Indicators from Financial Reports for Benchmarking

: Brito, Eduardo; Sifa, Rafet; Bauckhage, Christian; Loitz, Rüdiger; Lohmeier, Uwe; Pünt, Christin


Borghoff, U. ; Association for Computing Machinery -ACM-:
DocEng 2019, 19th ACM Symposium on Document Engineering. Proceedings : September 23-26, 2019, Berlin, Germany
New York: ACM, 2019
ISBN: 978-1-4503-6887-2
Art. 36, 4 S.
Symposium on Document Engineering (DocEng) <19, 2019, Berlin>
Fraunhofer IAIS ()
document analysis; visualization; information extraction

We present a tool that enables benchmarking of companies by means of automatic extraction of key performance indicators from publicly available financial reports. Our tool monitors companies of interest so that their reports are automatically downloaded as soon as they become available. After tables and paragraphs have been extracted from the documents using a table detection module based on convolutional neural networks, relevant key performance indicators are stored in a central database. The extracted values are finally displayed in a user-friendly web application where the user can compare time series of key performance indicators against arbitrary available companies.