Abstract: In an approach to mapping marketing triggers across geographies, a computer receives one or more variables associated with one or more rulesets. A computer retrieves data corresponding to the one or more variables. A computer sorts the retrieved data by season. A computer computes a seasonal average for each variable by associated postal code. A computer trains a self-organizing map to arrange the data associated with the source geography postal codes into one or more source clusters. A computer maps the retrieved data and the computed data associated with the target geography to the one or more source clusters, thereby creating target counterpart clusters that correspond with at least one of the one or more source clusters. A computer applies one or more cluster rulesets associated with the one or more source clusters to the corresponding one or more target counterpart clusters. A computer outputs one or more bucket sheets.

Abstract: A system, method, and computer program product may identify a preferred geographic area for targeted advertising for a given brand to a targeted consumer. A set of locations of residences of actual consumers of physical brand locations may first be determined. The actual distance traveled by the consumer to the physical brand location is calculated based on the determined residence locations. A sphere of influence for the physical location is identified and a set of geographic areas within the sphere of influence is selected as a target area in which to perform targeted advertising for the particular brand.

Abstract: A network of nodes is constructed from data obtained from a data source of a social medium. A node corresponds to a medical professional. From the data, a likelihood is determined of the node prescribing a product. From the data, for a period, a level of knowledge is computed of the node about the product. A change in the level of knowledge of the node from a previous period is determined. Using a change in a level of knowledge corresponding to each node in the network, an amount of knowledge reinforcement to be applied to each node in the network is computed. A knowledge reinforcement resource to perform knowledge reinforcement at a subset of the nodes is allocated according to a schedule, where the allocated knowledge reinforcement resource to the node has a correspondence with the change in the level of knowledge of the node.