Abstract: According to some embodiments, historic transaction data and loss data may be received from a data storage device. Geographic data and dynamically updated social network data corresponding to the entity may also be received and automatically analyzed by an estimator device to determine an estimated number of employees employed by the entity and similar entities having at least one common characteristic with the entity. A data weighting device generates weighted data by applying weighting factors to the received data including a weighting factor based on a location of users providing social networking posts and a weighting factor based on whether the social network data includes image, video, or audio data. At least one risk-related parameter corresponding to the entity is determined by a comparison engine that applies predictive models to (i) the weighted data, (ii) the estimated number of employees, and (iii) the similar entities to the entity.

Abstract: According to some embodiments, historic transaction data and loss data may be received from a data storage device. Geographic data and dynamically updated social network data corresponding to the entity may also be received and automatically analyzed by an estimator device to determine an estimated number of employees employed by the entity and similar entities having at least one common characteristic with the entity. A data weighting device generates weighted data by applying weighting factors to the received data including a weighting factor based on a location of users providing social networking posts and a weighting factor based on whether the social network data includes image, video, or audio data. At least one risk-related parameter corresponding to the entity is determined by a comparison engine that applies predictive models to (i) the weighted data, (ii) the estimated number of employees, and (iii) the similar entities to the entity.

Abstract: According to some embodiments, historic transaction data and loss data may be received from a data storage device. Geographic data and dynamically updated social network data corresponding to the entity may also be received and automatically analyzed by an estimator device to determine an estimated number of employees employed by the entity and similar entities having at least one common characteristic with the entity. A data weighting device generates weighted data by applying weighting factors to the received data including a weighting factor based on a location of users providing social networking posts and a weighting factor based on whether the social network data includes image, video, or audio data. At least one risk-related parameter corresponding to the entity is determined by a comparison engine that applies predictive models to (i) the weighted data, (ii) the estimated number of employees, and (iii) the similar entities to the entity.

Abstract: According to some embodiments, a system may detect an occurrence of a trigger event in connection with a first insurance agent of a plurality of insurance agents. For example, the system might detect that a person has added a friend on Facebook, changed his or her status, or that he or she is currently visiting a local coffee shop. Responsive to said detection, some embodiments may automatically post information to at least one social network server in connection with the first insurance agent. For example, an offer to meet at a particular location and/or a discount or other benefit associated with an insurance product might be posted or otherwise provided via one or more social networks.

Abstract: According to some embodiments, historic transaction data and loss data may be received from a data storage device. Geographic data and dynamically updated social network data corresponding to the entity may also be received and automatically analyzed by an estimator device to determine an estimated number of employees employed by the entity and similar entities having at least one common characteristic with the entity. A data weighting device generates weighted data by applying weighting factors to the received data including a weighting factor based on a location of users providing social networking posts and a weighting factor based on whether the social network data includes image, video, or audio data. At least one risk-related parameter corresponding to the entity is determined by a comparison eng ne that applies predictive models to (i) the weighted data, (ii) the estimated number of employees, and (iii) the similar entities to the entity.

Abstract: According to some embodiments, historic transaction data and loss data may be received from a data storage device. Information about a potential business insurance customer may also be received and automatically analyzed to identify a set of related businesses. A coverage comparison engine may then determine insurance information for the potential business insurance customer based at least in part on historic transaction data and loss data associated with the set of related businesses.

Abstract: According to some embodiments, historic transaction data and loss data may be received from a data storage device. Information about a potential business insurance customer may also be received and automatically analyzed to identify a set of related businesses. A coverage comparison engine may then determine insurance information for the potential business insurance customer based at least in part on historic transaction data and loss data associated with the set of related businesses.

Abstract: According to some embodiments, a system may detect an occurrence of a trigger event in connection with a first insurance agent of a plurality of insurance agents. For example, the system might detect that a person has added a friend on Facebook, changed his or her status, or that he or she is currently visiting a local coffee shop. Responsive to said detection, some embodiments may automatically post information to at least one social network server in connection with the first insurance agent. For example, an offer to meet at a particular location and/or a discount or other benefit associated with an insurance product might be posted or otherwise provided via one or more social networks.