Integration of General Bayesian Network and ubiquitous decision support to provide context prediction capability

We propose a new type of ubiquitous decision support system which is powered by a General Bayesian Network (GBN). While complicated decision support problems are plagued by complexities involved in interpreting causal relationships among decision variables, GBN has shown excellent decision support competence due to its flexible structure which allows itself to extract appropriate and robust causal relationships among target variable and related explanatory variables. The potentials of GBN, however, were not explored enough in the field of ubiquitous decision support area. Hence, we propose a new type of ubiquitous decision support mechanism named U-BASE which uses GBN for context prediction to improve decision support. To prove the validity of the proposed decision support mechanism, we collected a set of contextual data from college students, and applied U-BASE to induce useful and robust results. Practical implications are fully discussed for motivating future studies.