Abstract: An event analysis system receives events in a time-series from a set of monitored systems and identifies a set of alert threshold values for each of the types of events to identify outliers in the time-series at an evaluated time. Portions of historic event data is selected to identify windows of event data near the evaluated time at a set of seasonally-adjusted times to predict the value of the event type. The alert threshold value may also account for a prediction based on recent, higher-frequency events. Using the alert threshold values for a plurality of event types, the event data is compared with the alert threshold values to determine an alert level for the data. The event data types are also clustered and displayed with the alert levels to provide a visualization of the event data and identify outliers when the new event data is received.

Abstract: An event analysis system receives events in a time-series from a set of monitored systems and identifies a set of alert threshold values for each of the types of events to identify outliers in the time-series at an evaluated time. Portions of historic event data is selected to identify windows of event data near the evaluated time at a set of seasonally-adjusted times to predict the value of the event type. The alert threshold value may also account for a prediction based on recent, higher-frequency events. Using the alert threshold values for a plurality of event types, the event data is compared with the alert threshold values to determine an alert level for the data. The event data types are also clustered and displayed with the alert levels to provide a visualization of the event data and identify outliers when the new event data is received.

Abstract: An event analysis system receives events in a time-series from a set of monitored systems and identifies a set of alert threshold values for each of the types of events to identify outliers in the time-series at an evaluated time. Portions of historic event data is selected to identify windows of event data near the evaluated time at a set of seasonally-adjusted times to predict the value of the event type. The alert threshold value may also account for a prediction based on recent, higher-frequency events. Using the alert threshold values for a plurality of event types, the event data is compared with the alert threshold values to determine an alert level for the data. The event data types are also clustered and displayed with the alert levels to provide a visualization of the event data and identify outliers when the new event data is received.

Abstract: A computing system operates to process multiple transport requests at one time, each of the multiple transport request specifying a pickup location that is within a geographic region. During a given interval when each of the multiple transport request are open, a pool of candidate drivers is determined within the geographic region that can fulfill one or more of the transport requests within a threshold duration of time. A driver is selected for each of the multiple transport requests.

Abstract: An event analysis system receives events in a time-series from a set of monitored systems and identifies a set of alert threshold values for each of the types of events to identify outliers in the time-series at an evaluated time. Portions of historic event data is selected to identify windows of event data near the evaluated time at a set of seasonally-adjusted times to predict the value of the event type. The alert threshold value may also account for a prediction based on recent, higher-frequency events. Using the alert threshold values for a plurality of event types, the event data is compared with the alert threshold values to determine an alert level for the data. The event data types are also clustered and displayed with the alert levels to provide a visualization of the event data and identify outliers when the new event data is received.

Abstract: An event analysis system receives events in a time-series from a set of monitored systems and identifies a set of alert threshold values for each of the types of events to identify outliers in the time-series at an evaluated time. Portions of historic event data is selected to identify windows of event data near the evaluated time at a set of seasonally-adjusted times to predict the value of the event type. The alert threshold value may also account for a prediction based on recent, higher-frequency events. Using the alert threshold values for a plurality of event types, the event data is compared with the alert threshold values to determine an alert level for the data. The event data types are also clustered and displayed with the alert levels to provide a visualization of the event data and identify outliers when the new event data is received.

Abstract: An event analysis system receives events in a time-series from a set of monitored systems and identifies a set of alert threshold values for each of the types of events to identify outliers in the time-series at an evaluated time. Portions of historic event data is selected to identify windows of event data near the evaluated time at a set of seasonally-adjusted times to predict the value of the event type. The alert threshold value may also account for a prediction based on recent, higher-frequency events. Using the alert threshold values for a plurality of event types, the event data is compared with the alert threshold values to determine an alert level for the data. The event data types are also clustered and displayed with the alert levels to provide a visualization of the event data and identify outliers when the new event data is received.

Abstract: A travel coordination system provides information to providers to reduce the wait time between trips. A region is partitioned into zones and generates a score for each zone. A zone score can be generated by estimating the wait time for the zone, which may be determined by a model for the wait time. The model for the wait time may use factors that contribute to the wait time, such as the number of providers in a zone and the trip request rate. The zone score for each zone is displayed to the provider on a road map of the geographic region. The travel coordination system also provides routes that use zone scoring to reduce the wait time for receiving an assignment request during travel to the destination. The travel coordination system identifies a destination and generates candidate routes to the destination. A route is selected based on route scores.

Abstract: An event analysis system receives events in a time-series from a set of monitored systems and identifies a set of alert threshold values for each of the types of events to identify outliers in the time-series at an evaluated time. Portions of historic event data is selected to identify windows of event data near the evaluated time at a set of seasonally-adjusted times to predict the value of the event type. The alert threshold value may also account for a prediction based on recent, higher-frequency events. Using the alert threshold values for a plurality of event types, the event data is compared with the alert threshold values to determine an alert level for the data. The event data types are also clustered and displayed with the alert levels to provide a visualization of the event data and identify outliers when the new event data is received.

Abstract: An event analysis system receives events in a time-series from a set of monitored systems and identifies a set of alert threshold values for each of the types of events to identify outliers in the time-series at an evaluated time. Portions of historic event data is selected to identify windows of event data near the evaluated time at a set of seasonally-adjusted times to predict the value of the event type. The alert threshold value may also account for a prediction based on recent, higher-frequency events. Using the alert threshold values for a plurality of event types, the event data is compared with the alert threshold values to determine an alert level for the data. The event data types are also clustered and displayed with the alert levels to provide a visualization of the event data and identify outliers when the new event data is received.

Abstract: A system and method for arranging an on-demand service is described. A computing device can maintain a queue that includes a plurality of user identifiers corresponding to a plurality of users. Each user identifier is added to the queue in response to receiving a request for service from a corresponding user. The computing device receives information from a device of a service provider that the service provider is available to provide service to users. In response to receiving the information, the computing device selects a user identifier from the queue to assign a corresponding user to the service provider based, at least in part, on specified on-demand service locations corresponding to the plurality of user identifiers and a current location of the service provider.

Abstract: A computing system operates to process multiple transport requests at one time, each of the multiple transport request specifying a pickup location that is within a geographic region. During a given interval when each of the multiple transport request are open, a pool of candidate drivers is determined within the geographic region that can fulfill one or more of the transport requests within a threshold duration of time. A driver is selected for each of the multiple transport requests.

Abstract: A system and method for arranging a transport service is described. A server can receive a request for transport from a computing device of a first user. The request can include information about a pickup location of the first user. In response to receiving the request, the server can determine a plurality of drivers that are capable of providing transport for the first user by determining a first set of drivers that are each driving a vehicle that is unoccupied by other users, and determining a second set of drivers that are each providing transport service to one or more other users to a respective destination location that is within a threshold distance or threshold estimated travel time from the pickup location of the first user. The server can select a first driver from the plurality of drivers to provide the transport service for the first user.