Case Based Reasoning is a very important research trend in Artificial Intelligence and can be a powerful approach in the solution of complex problems characterized by heterogeneous knowledge. In this paper we present an ongoing research project where CBR is exploited to support the identification of enterprises potentially going to bankruptcy, through a comparison of their balance indexes with the ones of similar and already closed firms. In particular, the paper focuses on how developing similarity measures for strings can be profitably supported by metadata models of case structures and semantic methods like Query Expansion.
Mazzucchelli, A., Sartori, F. (2014). String Similarity in CBR Platforms: A Preliminary Study. In Metadata and Semantics Research (pp. 22-29). Springer Verlag [10.1007/978-3-319-13674-5_3].
String Similarity in CBR Platforms: A Preliminary Study
MAZZUCCHELLI, ALICEPrimo
;SARTORI, FABIOUltimo
2014
Abstract
Case Based Reasoning is a very important research trend in Artificial Intelligence and can be a powerful approach in the solution of complex problems characterized by heterogeneous knowledge. In this paper we present an ongoing research project where CBR is exploited to support the identification of enterprises potentially going to bankruptcy, through a comparison of their balance indexes with the ones of similar and already closed firms. In particular, the paper focuses on how developing similarity measures for strings can be profitably supported by metadata models of case structures and semantic methods like Query Expansion.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
