Evaluating an organization's risk to be exposed to cyber security events, by collecting security-based risk indicators about multiple organizations and an indication on whether or not each of the multiple organizations suffered a security event, inputting values of the security-based risk indicators about the multiple organization into a software model, running the software model multiple times, where the software model outputs multiple sets of one or more classifiers, where each set of one or more classifiers distinguishes organizations that suffered the security event from organizations that did not suffer the security event, where the one or more classifiers include classifiers selected from the security-based risk indicators, assigning a risk score for a specific organization according to the importance of classifiers related to the specific organization, and computing an underwriting score for the specific organization.

Evaluating an organization's risk to be exposed to cyber security events, by collecting security-based risk indicators about multiple organizations and an indication on whether or not each of the multiple organizations suffered a security event, inputting values of the security-based risk indicators about the multiple organization into a software model, running the software model multiple times, where the software model outputs multiple sets of one or more classifiers, where each set of one or more classifiers distinguishes organizations that suffered the security event from organizations that did not suffer the security event, where the one or more classifiers include classifiers selected from the security-based risk indicators, assigning a risk score for a specific organization according to the importance of classifiers related to the specific organization, and computing an underwriting score for the specific organization.

An automated wetstock management system can include a plurality of sensors disposed in a fuel storage facility, the plurality of sensors configured to sense fuel data characterizing one or more aspects of the fuel storage facility, and a wetstock management server communicatively coupled to the plurality of sensors. The wetstock management server can process the fuel data to detect whether the fuel data satisfies an exception indicative of an operational issue of the fuel storage facility based on one or more predefined rules or models stored in the wetstock management server. In some embodiments, the wetstock management server can generate a workflow for assisting a user of the fuel storage facility to resolve the operational issue. In some embodiments, the wetstock management server can assign a risk category to the exception and electronically transmit an alert characterizing the operational issue to the user.

An automated wetstock management system can include a plurality of sensors disposed in a fuel storage facility, the plurality of sensors configured to sense fuel data characterizing one or more aspects of the fuel storage facility, and a wetstock management server communicatively coupled to the plurality of sensors. The wetstock management server can process the fuel data to detect whether the fuel data satisfies an exception indicative of an operational issue of the fuel storage facility based on one or more predefined rules or models stored in the wetstock management server. In some embodiments, the wetstock management server can generate a workflow for assisting a user of the fuel storage facility to resolve the operational issue. In some embodiments, the wetstock management server can assign a risk category to the exception and electronically transmit an alert characterizing the operational issue to the user.

In non-limiting examples of the present disclosure, systems, methods and devices for surfacing drive safety notifications are provided. A personal driving pattern library comprising first data associated with a first user for a plurality of road sections included in a first route may be maintained. A global driving pattern library comprising second data associated with a plurality of users for the plurality of road sections included in the first route may be maintained. A determination may be made that the first user is going to travel the first route. A first drive safety score for the first user driving the first route may be calculated. A determination may be made that the first drive safety score is below a threshold value. A drive safety notification may be caused to be surfaced.

A system and a computer-implemented method of managing building wellness. The method may include the steps of: obtaining wellness parameters for a building (e.g., an office building) having an occupant(s); processing the wellness parameter to determine a current wellness index for the building and, based on the current wellness index, sending a message regarding the current wellness index to a recipient(s) (e.g., a building occupant), displaying the current wellness index for a user(s), and/or identifying a remediation action(s) to improve the current wellness index.

A system and a computer-implemented method of managing building wellness. The method may include the steps of: obtaining wellness parameters for a building (e.g., an office building) having an occupant(s); processing the wellness parameter to determine a current wellness index for the building and, based on the current wellness index, sending a message regarding the current wellness index to a recipient(s) (e.g., a building occupant), displaying the current wellness index for a user(s), and/or identifying a remediation action(s) to improve the current wellness index.

Techniques for adaptive validation and remediation are described. In some embodiments, the method includes determining, for a plurality of media service accounts, corresponding fraud suspicion values based on a model. The method also includes identifying a plurality of suspected accounts based on the corresponding fraud suspicion values. The method additionally includes identifying one or more suspected devices and predicting a likelihood of account takeover from each of the one or more suspected devices. The method further includes detecting a triggering event from a device of the one or more suspected devices associated with an account. The method additionally includes executing a validation and/or remediation procedure based on a trigger sensitivity value associated with the triggering event, a respective likelihood of account takeover from the device associated with the account, a respective device risk value associated with the device, and a respective fraud suspicion value associated with the account.

Techniques for adaptive validation and remediation are described. In some embodiments, the method includes determining, for a plurality of media service accounts, corresponding fraud suspicion values based on a model. The method also includes identifying a plurality of suspected accounts based on the corresponding fraud suspicion values. The method additionally includes identifying one or more suspected devices and predicting a likelihood of account takeover from each of the one or more suspected devices. The method further includes detecting a triggering event from a device of the one or more suspected devices associated with an account. The method additionally includes executing a validation and/or remediation procedure based on a trigger sensitivity value associated with the triggering event, a respective likelihood of account takeover from the device associated with the account, a respective device risk value associated with the device, and a respective fraud suspicion value associated with the account.

Provided are an artificial intelligence insurance server and a method for providing an artificial intelligence insurance service. The artificial intelligence insurance server comprises a receiving unit for receiving input data including medical data of an insurance user, a comparison data selection unit for selecting comparison data based on the input data, and deriving first analysis data by analyzing the comparison data, an artificial intelligence analysis unit for obtaining second analysis data derived by performing artificial intelligence analysis on the input data, a comparison unit for comparing the first and the second analysis data and generating final analysis data using the first and the second analysis data and a decision-making unit for making at least one insurance-related decision using the final analysis data.