X-IM Framework to Overcome Semantic Heterogeneity Across XBRL Filings

Abstract

Semantic heterogeneity in XBRL precludes the full automation of the business reporting pipeline, a key motivation for the SEC’s XBRL mandate. To mitigate this problem, several approaches leveraging Semantic Web technologies have emerged. While some approaches are promising, their mapping accuracy in resolving semantic heterogeneity must be improved to realize the promised benefits of XBRL. Considering this limitation and following the design science research methodology (DSRM), we develop a novel framework, XBRL indexing-based mapping (X-IM), which takes advantage of the representational model of representation theory to map heterogeneous XBRL elements across diverse XBRL filings. The application of representation theory to the design process informs the use of XBRL label linkbases as a repository of regularities constitutive of the relationships between financial item names and the concepts they describe along a set of equivalent financial terms of interest to investors. The instantiated design artifact is thoroughly evaluated using standard information retrieval metrics. Our experiments show that X-IM significantly outperforms existing methods.