G06Q30/0205

METHODS AND APPARATUS FOR PREDICTING A USER CHURN EVENT

In some examples, a system may be configured to obtain a set of features of a set of users including one or more features of transaction of the set of users and one or more features of engagement data of the set of users. Additionally, the system may be configured to implement a first set of operations that generate output data including a plurality of churn scores, based on the set of features. In some examples, each churn score of the plurality of churn scores being associated with a particular user of the set of users and characterize a likelihood of a churn event of the corresponding user.

PRESENTING EVENT INTELLIGENCE AND TRENDS TAILORED PER GEOGRAPHIC AREA GRANULARITY
20200151183 · 2020-05-14 ·

The present invention extends to methods, systems, and computer program products for presenting event intelligence and trends tailored per geographic area granularity. Event related data can be combined with information from other domains to enable intelligent decision making within those domains. Responsive to user commands, graphical presentation can be tailored to a geographic granularity and can vary between geographic granularities. Event related information and other information for a defined area as well as adjacent areas can be at least partially summarized based on geographic granularity. At least partially summarizing data for currently presented areas as well as adjacent areas reduces resource consumption when moving between presented areas, for example, in a map. The level of summarization can be a tailored to a selected geographic granularity. As such, overall presented graphical data (e.g., total number of icons) can be relatively stable, and possibly tuned to available computing resources.

Inventory mirroring in a heterogeneous fulfillment network
10650344 · 2020-05-12 · ·

A method of determining an inventory mirroring plan for a set of distinct items in a heterogeneous fulfillment network is presented. The fulfillment network can include a plurality of distribution centers, each distribution center having differing capabilities. The method can include determining a solution value of the number of clusters for each distinct item that minimizes a sum of a total shipping cost of each distinct item, subject to a total distinct item capacity of the plurality of distribution centers in the fulfillment network. The method can further include using a probability of the item being placed in a specific distribution center based on either the capacity of the distribution center or historical data. The probability can be used to stock items. Overages and deficits can be used to further refine the distribution. Other embodiments are also disclosed.

VERIFICATION METHOD FOR DIVISION OF ADMINISTRATIVE REGION, SERVER AND STORAGE MEDIUM
20200143400 · 2020-05-07 ·

A verification method for division of an administrative region includes steps of: acquiring a region name of an administrative region; loading an electronic map corresponding to the administrative region according to the region name, the administrative region being divided into a plurality of sub-regions in the electronic map; acquiring an insurance policy quantity corresponding to the region name, and a road section quantity corresponding to the region name; performing a verification on the plurality of sub-regions of the administrative region by making use of the insurance policy quantity and the road section quantity; and recording the plurality of sub-regions of the administrative region as reasonable sub-regions if the verification is passed.

ALLOCATION OF SERVICE PROVIDER RESOURCES BASED ON A CAPACITY TO PROVIDE THE SERVICE
20200143401 · 2020-05-07 ·

An example includes one or more devices may include one or more memories and one or more processors, communicatively coupled with at least one of the one or more memories, to identify a service that is provided within a region; identify a model that is associated with the service, the model having been trained based on consumer profile data, service provider data, and historical information; determine a current demand associated with the service in the region; predict, using the model and based on the current demand associated with the service, a future demand for the service during a time period; determine a current capacity to provide the service based on real-time service provider information associated with service providers that are providing the service in the region; and perform an action associated with the service based on the future demand for the service and the current capacity to provide the service.

PORTABLE REAL-TIME EXPERIENCE COMMUNICATIONS DEVICE AND MONITORING SYSTEM
20200143309 · 2020-05-07 · ·

A system and computer-implemented method for real-time monitoring and responding to user experiences at a location. The method includes deploying a centralized communications and display node, and each of a plurality of portable communications devices with a respective subject, within the location, receiving, from one or more of the portable devices, and at the centralized node, transmitted data including a respective identifier of a respective actuator of each of the one or more portable devices and that was activated by the respective subject, a respective activation time indicator, and a respective identifier of each of the one or more portable devices. The method also includes generating respective machine-readable values indicative of a positive or negative experience type for each of the actuator-activating subjects using the received data, and a respective alert using the generated machine-readable values and if the indicated experience type for the respective subject is negative.

ELIGIBILITY PREDICTIONS FOR INSTANT BOOKING IN AN ONLINE MARKETPLACE
20200134513 · 2020-04-30 ·

Systems and methods are provided for receiving a request for services in a given location from a client device operated by a user and generating a set of features based on information included in the request for services in the given location. The systems and methods further provide for analyzing the set of features using a machine learning model to predict whether only services that can be instantly booked should be provided in response to the request for services in the given location, analyzing a prediction output by the machine learning model to determine that only services that can be instantly booked should be provided in response to the request for services in the given location, and generating a list with only services that can be instantly booked.

SYSTEM FOR IDENTIFYING DAMAGED BUILDINGS
20200134573 · 2020-04-30 ·

A system for identifying buildings that are damaged in a geographic area from a damaging weather event. Accessing weather data and identifying a date of the damaging weather event. Accessing geographic data for identifying the geographic area where the damaging weather event occurred. Accessing visual data of buildings where the damaging weather event occurred. Identifying an individual building that was damaged based on the visual data, geographic data and weather data.

DISPLAY CONTROL METHOD, DISPLAY CONTROL DEVICE, NON-TRANSITORY RECORDING MEDIUM STORING DISPLAY CONTROL PROGRAM, AND DISPLAY CONTROL SYSTEM

A display control method includes causing a display control device to perform: a step (a) forecasting a demand for a vehicle dispatch at an arbitrary point or in an arbitrary area at a time specified by a host vehicle; and a step (b) superimposing, at a position on a map screen, information about the forecasted demand, the position corresponding to the arbitrary point or the arbitrary area.

Uncertainty modeling in traffic demand prediction

The disclosure involves a method comprising clustering a plurality of observation samples related to historical travel demands into one or more clusters; for each cluster, constructing an actual probability distribution of the historical travel demands corresponding to the observation samples in the cluster; for each cluster, inputting observation samples in the cluster into a prediction model for predicting future travel demands to produce a result of prediction; for each cluster, computing a predicted probability distribution of the historical travel demands corresponding to the observation samples in the cluster based on the result of prediction; for each cluster, evaluating a difference between the actual probability distribution and the predicted probability distribution of the cluster; and modifying the prediction model so that a statistical sum of the differences for the one or more clusters is decreased.