Towards automating Numerical Consistency Checks in Financial Reports
This addresses the need for efficient auditing of financial statements, particularly for auditing firms, though it is an incremental improvement in automating domain-specific tasks.
The paper tackles the problem of automating numerical consistency checks in financial reports by introducing KPI-Check, a system that identifies and cross-checks semantically equivalent key performance indicators, achieving a micro F1 score of 73.00% on a test set.
We introduce KPI-Check, a novel system that automatically identifies and cross-checks semantically equivalent key performance indicators (KPIs), e.g. "revenue" or "total costs", in real-world German financial reports. It combines a financial named entity and relation extraction module with a BERT-based filtering and text pair classification component to extract KPIs from unstructured sentences before linking them to synonymous occurrences in the balance sheet and profit & loss statement. The tool achieves a high matching performance of $73.00$% micro F$_1$ on a hold out test set and is currently being deployed for a globally operating major auditing firm to assist the auditing procedure of financial statements.