In this paper, we describe an extension of the methodology for explanation generation in financial knowledge-based systems, offering the possibility to automatically generate explanations and diagnostics to support business decision tasks. The central goal is the identification of specific knowledge structures and reasoning methods required to construct computerized explanations from financial data and business models. A multi-step look-ahead algorithm is proposed that deals with so-called calling-out effects, which are a common phenomenon in financial data sets. The extended methodology was tested on a case-study conducted for Statistics Netherlands involving the comparison of financial figures of firms in the Dutch retail branch. The analyses are performed with a diagnostic software application which implements our theory of explanation. Comparison of results of the classic explanation methodology with the results of the extended methodology shows significant improvements in the analyses when cancelling-out effects are present in the data.

artificial intelligence, decision support systems, explanation, finance, production statistics
Statistical Decision Theory; Operations Research (jel C44), Information and Product Quality; Standardization and Compatibility (jel L15), Business Administration and Business Economics; Marketing; Accounting (jel M), Management of Technological Innovation and R&D (jel O32)
Erasmus Research Institute of Management
hdl.handle.net/1765/6987
ERIM Report Series Research in Management
ERIM report series research in management Erasmus Research Institute of Management
Erasmus Research Institute of Management

Caron, E.A.M, & Daniels, H.A.M. (2005). General Model for Automated Diagnosis of Business Performance (No. ERS-2005-058-LIS). ERIM report series research in management Erasmus Research Institute of Management. Erasmus Research Institute of Management. Retrieved from http://hdl.handle.net/1765/6987