Abstract: Various methods and systems for processing web crawling queries using a web crawling prioritization model based on classification operation performance. A classification operation for organizing products in a product listing platform is accessed. A web crawling engine is accessed for the classification operation. The web crawling engine operates based on a web crawling query prioritization model that supports determining web crawling priority scores that indicate a predicted performance improvement for classification operations executed with known data and web crawled data to be retrieved from executing a web crawling query operation. Using the web crawling prioritization model, a web crawling priority score is determined for a web crawling query for the corresponding classification operation. The classification operation is associated with a product in a product listing platform and known data for the product.

Abstract: Various methods and systems for processing web crawling queries using a web crawling prioritization model based on classification operation performance. A classification operation for organizing products in a product listing platform is accessed. A web crawling engine is accessed for the classification operation. The web crawling engine operates based on a web crawling query prioritization model that supports determining web crawling priority scores that indicate a predicted performance improvement for classification operations executed with known data and web crawled data to be retrieved from executing a web crawling query operation. Using the web crawling prioritization model, a web crawling priority score is determined for a web crawling query for the corresponding classification operation. The classification operation is associated with a product in a product listing platform and known data for the product.

Abstract: Apparatus and methods are described for performing a differential diagnosis of a patient, including, using a computer processor (18), in a machine-learning stage, receiving data relating to a plurality of patients, receiving conditions that respective patients are diagnosed as having, and thereby determining correlations between respective patient parameters and the conditions that patients are diagnosed as having. In a patient-diagnosis stage, one or more conditions that a given patient is suspected of having are determined. Based at least partially upon the correlations determined during the machine-learning stage and the conditions that the given patient is suspected of having, a set of questions to ask the patient is determined such that determining that the patient has one of the conditions with a likelihood that passes a threshold likelihood may be achieved with a minimum number of questions being asked. Other applications are also described.

Abstract: Various methods and systems for processing web crawling queries using a web crawling prioritization model based on classification operation performance. A classification operation for organizing products in a product listing platform is accessed. A web crawling engine is accessed for the classification operation. The web crawling engine operates based on a web crawling query prioritization model that supports determining web crawling priority scores that indicate a predicted performance improvement for classification operations executed with known data and web crawled data to be retrieved from executing a web crawling query operation. Using the web crawling prioritization model, a web crawling priority score is determined for a web crawling query for the corresponding classification operation. The classification operation is associated with a product in a product listing platform and known data for the product.

Abstract: Various methods and systems for processing web crawling queries using a web crawling prioritization model based on classification operation performance. A classification operation for organizing products in a product listing platform is accessed. A web crawling engine is accessed for the classification operation. The web crawling engine operates based on a web crawling query prioritization model that supports determining web crawling priority scores that indicate a predicted performance improvement for classification operations executed with known data and web crawled data to be retrieved from executing a web crawling query operation. Using the web crawling prioritization model, a web crawling priority score is determined for a web crawling query for the corresponding classification operation. The classification operation is associated with a product in a product listing platform and known data for the product.

Abstract: Techniques provide time-aware ranking, such as ranking of information, files or URL (uniform resource locator) links. For example, time-aware modeling assists in determining user intent of a query to a search engine. In response to the query, results are ranked in a time-aware manner to better match the user intent. The ranking may model query, URL and query-URL pair behavior over time to create time-aware query, URL and query-URL pair models, respectively. Such models may predict behavior of a query-URL pair, such as frequency and timing of clicks to the URL of the pair when the query of the pair is posed to the search engine. Results of a query may be ranked by predicted query-URL behavior. Once ranked, the results may be sent to the user in response to the query.

Abstract: A ranked set of users may be calculated from an expertise categorization for each user and a person's trust in the users for specific categories. The ranked set of users may be used for presenting search results, recommendations, social marketing, or other uses. A person's reputation may be determined through various online activities. A person's trust in another person may be related to their proximity and activity in one or more social networks.

Abstract: A system for automatically generating predictions and salesmen-recommendations relating to sales, the system comprising at least one processor configured to: receive customers' historical sales data relating to one or more previous sale attempts wherein the customers historical sales data includes two or more data fields; receive at least one indication of at least one sale outcome relating to at least one of the sale attempts; for at least a given data field of the data fields, automatically determine possible values thereof; and based at least on the customer's historical sales data, the given field's possible values and the at least one indication, generate a prediction model useable for customer-based predictions.

Abstract: Techniques provide time-aware ranking, such as ranking of information, files or URL (uniform resource locator) links. For example, time-aware modeling assists in determining user intent of a query to a search engine. In response to the query, results are ranked in a time-aware manner to better match the user intent. The ranking may model query, URL and query-URL pair behavior over time to create time-aware query, URL and query-URL pair models, respectively. Such models may predict behavior of a query-URL pair, such as frequency and timing of clicks to the URL of the pair when the query of the pair is posed to the search engine. Results of a query may be ranked by predicted query-URL behavior. Once ranked, the results may be sent to the user in response to the query.

Abstract: Techniques provide time-aware ranking, such as ranking of information, files or URL (uniform resource locator) links. For example, time-aware modeling assists in determining user intent of a query to a search engine. In response to the query, results are ranked in a time-aware manner to better match the user intent. The ranking may model query, URL and query-URL pair behavior over time to create time-aware query, URL and query-URL pair models, respectively. Such models may predict behavior of a query-URL pair, such as frequency and timing of clicks to the URL of the pair when the query of the pair is posed to the search engine. Results of a query may be ranked by predicted query-URL behavior. Once ranked, the results may be sent to the user in response to the query.

Abstract: An active filter monitors a web browser session to identify executable code transmitted in the session. The executable code may be analyzed to determine if the code is digitally signed. When the code is digitally signed by the web server or by another trusted source, the code may be executed. When the code is neither digitally signed or when the source is not trusted, the code may be rejected and not executed. The filter may be implemented as a web browser component or plugin, as well as a gateway device, proxy, or other service. The filter may also be implemented on the server side to reject incoming data that may include unauthenticated code.

Abstract: Architecture that selects a classification engine based on the expertise of the engine to process a given entity (e.g., a file). Selection of an engine is based on a probability that the engine will detect an unknown entity classification using properties of the entity. One or more of the highest ranked engines are activated in order to achieve the desired performance. A statistical, performance-light module is employed to skip or select several performance-demanding processes. Methods and algorithms are utilized for learning based on matching the best classification engine(s) to detect the entity class based on the entity properties. A user selection option is provided for specifying a maximum number of ranked, classification engines to consider for each state of the machine. A user can also select the minimum probability of detection for a specific entity (e.g., unknown file). The best classifications are re-evaluated over time as the classification engines are updated.

Abstract: Techniques provide time-aware ranking, such as ranking of information, files or URL (uniform resource locator) links. For example, time-aware modeling assists in determining user intent of a query to a search engine. In response to the query, results are ranked in a time-aware manner to better match the user intent. The ranking may model query, URL and query-URL pair behavior over time to create time-aware query, URL and query-URL pair models, respectively. Such models may predict behavior of a query-URL pair, such as frequency and timing of clicks to the URL of the pair when the query of the pair is posed to the search engine. Results of a query may be ranked by predicted query-URL behavior. Once ranked, the results may be sent to the user in response to the query.

Abstract: A network traffic analyzer may identify applications transmitting information across a network by analyzing various protocol attributes of the communication. A set of signatures may be created by training a machine learning system using network traffic with and without a specific application. The machine learning system may generate a signature for the specific application, and the signature may be analyzed using a monitoring system to identify the presence of the application's traffic on the network. In some embodiments, a decision tree may be used to detect the application within a statistical confidence. The monitoring system may be used for malware detection as well as other applications.

Abstract: Social influencers may be identified for specific usage contexts and for influencer type. Influencers may be categorized by mavens, connectors, salesmen, or other categories. Within each usage context, a unified data model may be used to collect data from multiple sources, including multiple social networks, as well as to collect data from different levels of influencers in each usage context. The relevance of various communication media as well as the frequency and quality of use of the media may be factors used to determine a person's effectiveness as a specific type of influencer within a usage context.

Abstract: A ranked set of users may be calculated from an expertise categorization for each user and a person's trust in the users for specific categories. The ranked set of users may be used for presenting search results, recommendations, social marketing, or other uses. A person's reputation may be determined through various online activities. A person's trust in another person may be related to their proximity and activity in one or more social networks.

Abstract: A social marketing system may reward and incentivize participants, and may also have a fraud detection system. The manager may create social marketing campaigns that may be simulated to determine an expected set of activities, which may be compared to an actual set of activities. A fraud detection system may detect abnormal activity and may bring the activity to a manager's attention and may also punish the participants by withholding rewards, lowering the participant's reputation, or some other punishment mechanism.

Abstract: A social incentive system is described herein that formalizes information propagation through social networks in a structured and systematic way. The system provides incentives and rewards to entities who participate in propagating the information, allowing heavy influencers to gain from their influence while the marketer rewards them. The system provides one or more tools for creation and design of social incentive plans with rewards for socially distributing information, including marketing campaigns. In particular, the system introduces a semantic framework where marketers can create structured incentive plans for rewarding consumers and distribution platforms for distributing information through social networks. As users complete specified activities they earn points, and the points can be redeemed for various incentives, such as cash, debit cards, prizes, merchandise, subscriptions, and so forth. The framework is robustly designed to avoid abuse and allow for fraud detection.

Abstract: A social marketing manager may facilitate marketing campaigns in online social networks by creating and monitoring campaigns, as well as facilitating online social interactions. A campaign manager may create a campaign and define various operational parameters. A recruitment system may identify social influencers through which the campaign may be started, and a promotion manager may create and track objects that may be passed to participants in the campaign. An analysis and monitoring system may determine the overall effectiveness of the campaign and provide feedback, payments to participants, or other results of the campaign.

Abstract: Architecture that selects a classification engine based on the expertise of the engine to process a given entity (e.g., a file). Selection of an engine is based on a probability that the engine will detect an unknown entity classification using properties of the entity. One or more of the highest ranked engines are activated in order to achieve the desired performance. A statistical, performance-light module is employed to skip or select several performance-demanding processes. Methods and algorithms are utilized for learning based on matching the best classification engine(s) to detect the entity class based on the entity properties. A user selection option is provided for specifying a maximum number of ranked, classification engines to consider for each state of the machine. A user can also select the minimum probability of detection for a specific entity (e.g., unknown file). The best classifications are re-evaluated over time as the classification engines are updated.