Hypothesis generation paradigm for fraud detection

It is suggested that generating new hypotheses as a basic requirement of reasoning processes provides the novel paradigm required for complex problem solving. We propose a conceptual framework to perform new hypothesis generation. The limitations encountered in the explanation generation mechanism which concentrates upon the problem of building the explanation to fill the gaps left by explanation based learning, are largely overcome by our paradigm. The proposed paradigm, which involves an anomaly detection model, case based hypothesis generation, and hypothesis synthesis, is deemed to provide a basic platform for management intelligence systems and fraud detection in electronic data processing environment