Abstract: A method may include determining a combination of values of attributes represented by reference data associated with payment transaction by training a machine learning model based on an association between (i) respective values of the attributes and (ii) the payment transactions having a given result. The combination may be correlated with having the given result. The method may also include selecting a subset of the payment transactions that is associated with the combination of values. The method may additionally include determining a first rate at which payment transactions of the subset have the given result during a first time period and a second rate at which one or more payment transactions associated with the combination have the given result during a second time period, and generating an indication that the two rates differ.

Abstract: A system for enforcing occupancy for a facility includes client electronic devices, each associated with one or more individuals who have access to a facility, an access monitoring system, and a computing device in communication with at least a portion of the plurality of the client electronic devices and the access monitoring system. The system determines, for the facility, a health risk rating, a maximum occupancy, a risk-adjusted occupancy, an estimated occupant number, and determines, based on the risk-adjusted occupancy and the estimated occupant number whether one or more individuals need to exit the facility. If individuals need to exit the facility, the system identifies and notifies the individuals.

Abstract: A method of estimating indoor location of an electronic device is disclosed. The electronic device will detect multiple Wi-Fi signals, each of which originates from a unique Wi-Fi access point in a building. For each of the signals, the system will determine an access point device identifier and a signal strength indicator, retrieve location coordinates for the access point; and various candidate constants to apply to a distance calculation for determining a distance from the electronic device to each of the access points. The system will repeat the distance calculation multiple times for each of the various constants and determine which constant minimizes a loss value. The system will identify a set of coordinates of the electronic device that are associated with the constant that minimizes the loss value, and then use the coordinates to estimate a location of the electronic device within the building.

Abstract: A method of estimating indoor location of an electronic device is disclosed. The electronic device will detect multiple Wi-Fi signals, each of which originates from a unique Wi-Fi access point in a building. For each of the signals, the system will determine an access point device identifier and a signal strength indicator, retrieve location coordinates for the access point; and various candidate constants to apply to a distance calculation for determining a distance from the electronic device to each of the access points. The system will repeat the distance calculation multiple times for each of the various constants and determine which constant minimizes a loss value. The system will identify a set of coordinates of the electronic device that are associated with the constant that minimizes the loss value, and then use the coordinates to estimate a location of the electronic device within the building.

Abstract: A method of proactively identifying print device incidents for servicing by a service provider may include receiving print device data for one or more print devices, determining a probability value for each of the one or more of the print devices based on the print device data, where each probability value represents a likelihood that the print device will experience a subsequent incident of an incident type within a timeframe, identifying one or more of the print devices associated with probability values that each exceed a threshold value, and for one or more of the print devices that is identified, automatically initiating a service request for the subsequent incident.