Abstract: Techniques are described for determining locations of interest based on user visits. In some situations, the techniques include obtaining information about actual locations of users at various times, and automatically analyzing the information to determine particular locations in a geographic area that are of interest, such as for frequent destinations visited by users. After determining a particular location of interest, it may be represented by generating a corresponding location model to describe the geographic subarea or other location point(s) covered by the determined location of interest, and one or more points of interest (e.g., businesses, parks, schools, landmarks, etc.) may be identified that are located at or otherwise correspond to the determined location of interest. In addition, a determined location of interest may be further used in various ways, including to identify later user visits to that location (e.g., to a point of interest identified for the location).

Abstract: Techniques are described for determining locations of interest based on user visits. In some situations, the techniques include obtaining information about actual locations of users at various times, and automatically analyzing the information to determine particular locations in a geographic area that are of interest, such as for frequent destinations visited by users. After determining a particular location of interest, it may be represented by generating a corresponding location model to describe the geographic subarea or other location point(s) covered by the determined location of interest, and one or more points of interest (e.g., businesses, parks, schools, landmarks, etc.) may be identified that are located at or otherwise correspond to the determined location of interest. In addition, a determined location of interest may be further used in various ways, including to identify later user visits to that location (e.g., to a point of interest identified for the location).

Abstract: Techniques are described for determining locations of interest based on user visits. In some situations, the techniques include obtaining information about actual locations of users at various times, and automatically analyzing the information to determine particular locations in a geographic area that are of interest, such as for frequent destinations visited by users. After determining a particular location of interest, it may be represented by generating a corresponding location model to describe the geographic subarea or other location point(s) covered by the determined location of interest, and one or more points of interest (e.g., businesses, parks, schools, landmarks, etc.) may be identified that are located at or otherwise correspond to the determined location of interest. In addition, a determined location of interest may be further used in various ways, including to identify later user visits to that location (e.g., to a point of interest identified for the location).

Abstract: Techniques are described for determining locations of interest based on user visits. In some situations, the techniques include obtaining information about actual locations of users at various times, and automatically analyzing the information to determine particular locations in a geographic area that are of interest, such as for frequent destinations visited by users. After determining a particular location of interest, it may be represented by generating a corresponding location model to describe the geographic subarea or other location point(s) covered by the determined location of interest, and one or more points of interest (e.g., businesses, parks, schools, landmarks, etc.) may be identified that are located at or otherwise correspond to the determined location of interest. In addition, a determined location of interest may be further used in various ways, including to identify later user visits to that location (e.g., to a point of interest identified for the location).

Abstract: Techniques are described for assessing road traffic conditions in various ways based on obtained traffic-related data, such as data samples from vehicles and other mobile data sources traveling on the roads, as well as in some situations data from one or more other sources (such as physical sensors near to or embedded in the roads). The assessment of road traffic conditions based on obtained data samples may include various filtering and/or conditioning of the data samples, and various inferences and probabilistic determinations of traffic-related characteristics from the data samples. In some situations, the filtering of the data samples includes identifying data samples that are inaccurate or otherwise unrepresentative of actual traffic condition characteristics, such as data samples that are not of interest based at least in part on roads with which the data samples are associated and/or that otherwise reflect vehicle locations or activities that are not of interest.

Abstract: Techniques are described for automatically and dynamically modifying ongoing operations of computing devices in device-specific manners, such as based on an automated identification of a computing device's status (e.g., identifying a likely ongoing or imminent failure of a smart phone or other computing device based on a series of observed hardware states of the computing device, and taking automated corrective actions to prevent or otherwise mitigate such device failure, such as by modifying configuration settings on the computing device or on associated systems). The techniques may include, for each of multiple device status outcomes of interest (e.g., device failure versus device non-failure), generating a state-space outcome model representing devices that reach that status outcome within a time period of interest, and using such outcome models to identify a likely ongoing or imminent outcome of a current device, with corresponding automated corrective actions then taken.

Abstract: Techniques are described for automatically and dynamically modifying ongoing operation of computing devices in device-specific manners, such as to improve ongoing performance of the computing devices by modifying configuration settings on the computing devices or on associated systems in communication with the computing devices. The techniques may include generating one or more decision structures that are each specific to a type of measured performance effect, and using the decision structure(s) to improve corresponding performance of a computing device, with the generating of the decision structure(s) including analyzing training data that associates prior measured performance effects with corresponding attributes of computing devices and of modification actions that were performed for the computing devices.

Abstract: A method and apparatus for traffic modeling comprising: receiving by a server, traffic data generated by one or more devices configured to record data indicating speeds of vehicles traveling a road segment. The server separates, with a processor, the traffic data into zero speed data and non-zero speed data. The server determines, with the processor, a zero speed data characteristic value of the zero speed data. The server determines, with the processor, at least one non-zero speed data characteristic value of the non-zero speed data. The server generates, with the processor, a representative traffic value for the road segment as a function of the zero speed characteristic value and the non-zero speed characteristic value.

Abstract: Subject innovations are directed towards a churn model using dynamic state-space modeling to determine churn risks for each active subscriber of a service provider having exhibited a precise sequence of behaviors. The churn model identifies complex behavioral patterns that are consistent with those of subscribers who have churned in a defined past, allowing for a personalized determination of churn risk. The churn model may also use static contextual data to assist in refinement of the churn model through identification of subscriber segments. A churn index is produced that may be used by an automated contextual marketing model to refine decision making for selectively marketing to a subscriber based, in part, on that individual subscriber's churn risk.

Abstract: Techniques train a tree to identify offers to send to a particular customer. Messages that include offers and having attributes are sent to a target user group. Feature measure results from the messages on the target user group, is used with feature measure results for a control user group, to train the tree with branch splits being identified based on maximizing an information gain from the feature measure results for a message/user attribute, where each node within the tree includes target and control distributions for the feature measure. The tree is traversed for a given marketing message/user, drawing randomly from feature measure distributions in the tree to determine whether to send the given marketing message to the user. By drawing randomly from the feature measure distributions, exploration and exploitation of various messages may be performed to minimize ignoring of messages that may have an information gain for particular customers.

Abstract: Subject innovations are directed towards a platform architecture, system, and special purpose software and hardware that employs a machine learning approach using transactional behavioral events and data about customers to allow a telecommunications marketer to express a set of configurable business rules and constraints, and within a dynamic optimization approach, derive solutions or marketing approaches to optimize delayed key performance indicators. In one embodiment, this is obtained using marketing experiments that seek to learn and influence long term behaviors of customers.

Abstract: Techniques are described for analyzing user-supplied information, including in at least some situations to predict future aspects of additional related information that will be supplied by users. The user-supplied information that is analyzed may, for example, include distributed group discussions that involve numerous users and occur via user comments made to one or more social networking sites and/or other computer-accessible sites. The analysis of user-supplied information may, for example, include determining particular topics that are of interest for a specified category during one or more periods of time, quantifying an amount of user interest in particular topics and the category during the period of time, predicting future amounts of user interest in the particular topics and the category during one or more future period of times, and taking one or more further actions based on the predicted information.

Abstract: Techniques are described for determining and using information related to domains of interest, such as by automatically analyzing documents and other information related to a domain in order to automatically determine relationships between particular terms within the domain. Such automatically determined information may then be used to assist users in obtaining information from the domain that is of interest (e.g., documents with contents that are relevant to user-specified terms and/or to other terms that are determined to be sufficiently related to the user-specified terms). For example, recommendations may be automatically generated for a user by using information about specified preferences or other interests of the user with respect to one or more terms and identifying other particular terms that are sufficiently probable to be of interest to that user, such as based on a generated probabilistic representation of relationships between particular terms for the domain.

Abstract: Techniques are described for assessing road traffic conditions in various ways based on obtained traffic-related data, such as data samples from vehicles and other mobile data sources traveling on the roads, as well as in some situations data from one or more other sources (such as physical sensors near to or embedded in the roads). The assessment of road traffic conditions based on obtained data samples may include various filtering and/or conditioning of the data samples, and various inferences and probabilistic determinations of traffic-related characteristics from the data samples. In some situations, the filtering of the data samples includes identifying data samples that are inaccurate or otherwise unrepresentative of actual traffic condition characteristics, such as data samples that are not of interest based at least in part on roads with which the data samples are associated and/or that otherwise reflect vehicle locations or activities that are not of interest.

Abstract: A method and apparatus for traffic modeling comprising: receiving by a server, traffic data generated by one or more devices configured to record data indicating speeds of vehicles traveling a road segment. The server separates, with a processor, the traffic data into zero speed data and non-zero speed data. The server determines, with the processor, a zero speed data characteristic value of the zero speed data. The server determines, with the processor, at least one non-zero speed data characteristic value of the non-zero speed data. The server generates, with the processor, a representative traffic value for the road segment as a function of the zero speed characteristic value and the non-zero speed characteristic value.

Abstract: Techniques are described for assessing road traffic conditions in various ways based on obtained traffic-related data, such as data samples from vehicles and other mobile data sources traveling on the roads, as well as in some situations data from one or more other sources (such as physical sensors near to or embedded in the roads). The assessment of road traffic conditions based on obtained data samples may include various filtering and/or conditioning of the data samples, and various inferences and probabilistic determinations of traffic-related characteristics from the data samples. In some situations, the filtering of the data samples includes identifying data samples that are inaccurate or otherwise unrepresentative of actual traffic condition characteristics, such as data samples that are not of interest based at least in part on roads with which the data samples are associated and/or that otherwise reflect vehicle locations or activities that are not of interest.

Abstract: Subject innovations are directed towards a churn model using dynamic state-space modeling to determine churn risks for each active subscriber of a service provider having exhibited a precise sequence of behaviors. The churn model identifies complex behavioral patterns that are consistent with those of subscribers who have churned in a defined past, allowing for a personalized determination of churn risk. The churn model may also use static contextual data to assist in refinement of the churn model through identification of subscriber segments. A churn index is produced that may be used by an automated contextual marketing model to refine decision making for selectively marketing to a subscriber based, in part, on that individual subscriber's churn risk.

Abstract: Techniques are described for analyzing user-supplied information, including in at least some situations to predict future aspects of additional related information that will be supplied by users. The user-supplied information that is analyzed may, for example, include distributed group discussions that involve numerous users and occur via user comments made to one or more social networking sites and/or other computer-accessible sites. The analysis of user-supplied information may, for example, include determining particular topics that are of interest for a specified category during one or more periods of time, quantifying an amount of user interest in particular topics and the category during the period of time, predicting future amounts of user interest in the particular topics and the category during one or more future period of times, and taking one or more further actions based on the predicted information.

Abstract: Techniques are described for assessing road traffic conditions in various ways based on obtained traffic-related data, such as data samples from vehicles and other mobile data sources traveling on the roads and/or from one or more other sources (such as physical sensors near to or embedded in the roads). The road traffic conditions assessment based on obtained data samples may include various filtering and/or conditioning of the data samples, and various inferences and probabilistic determinations of traffic-related characteristics of interest from the data samples. In some situations, the inferences include repeatedly determining current traffic flow characteristics and/or predicted future traffic flow characteristics for road segments of interest during time periods of interest, such as to determine average traffic speed, traffic volume and/or occupancy, and include weighting various data samples in various ways (e.g., based on a latency of the data samples and/or a source of the data samples).

Abstract: Subject innovations are directed towards a platform architecture, system, and special purpose software and hardware that employs a machine learning approach using transactional behavioral events and data about customers to allow a telecommunications marketer to express a set of configurable business rules and constraints, and within a dynamic optimization approach, derive solutions or marketing approaches to optimize delayed key performance indicators. In one embodiment, this is obtained using marketing experiments that seek to learn and influence long term behaviors of customers.