• The dataset included 1,287 records, each representing a county’s voting outcome from a past ballot. The following lists variables to be used in their ANN models :
– Ballot Type I (Gambling versus Wagering, a binary variable)
– Percent population votes (real-valued numeric variable)
– Medium family income (integer-valued numeric variable)
– Percent population church members (real-valued numeric variable)
– PREDICTING GAMBLING REFERENDA WITH NEURAL NETWORKS
– Percent population male (real-valued numeric variable)
– Poverty level (real-valued numeric variable)
– Unemployment rate (real-valued numeric variable)
– Percent population minority-non-White percentage (real-valued numeric variable)
– Percent population order than 45 (real-valued numeric variable)
– Metropolitan statistical area (yes/no, a binary variable)