Microsoft Technology Licensing, LLC

Livingsocial, Inc.

Pinterest, Inc.

Mehrdad Bidgoli

Eliot Carleton Gillum

Krishna C Vitaldevara

Jason D Walter

Robert L McCann

Malcolm Hollis Davis

Milenko Drinic

Geoffrey John Hulten

Ivan Osipkov

Aravind K Ramachandran

Yunnan Wu

Andrew Craig Bragdon

Douglas John Hines

Ryan Charles Colvin

Justin Velo

Chad W Mills

Joshua Korb

Vasantha K Vemula

Mengya You

Wendy Lu

Nipoon Malhotra

Raphael Grignani

Harsh Goel

Shahrouz Tavakoli

Vivian Clara Chow

Robert Lee Mccann

Joshua David Korb

A server receives a request for a deal from a client device of a merchant, the request for a deal including a merchant identifier. The server then accesses merchant information based on the merchant identifier, the merchant information including a merchant category and a merchant location. Additionally, the server obtains a set of candidate deals based on the merchant category and merchant location. The server then obtains historical information for each candidate deal, the historical information corresponding to one or more conversion rates of the candidate deal when the candidate deal was previously offered by one or more merchants. Next, the server determines a predicted conversion rate for each candidate deal, based on the historical information for the respective candidate deal and selects a deal based on the predicted conversion rates for the set of candidate deals. Lastly, the server communicates data corresponding to the selected deal to the client device, the data including the predicted conversion rate for the selected deal.

Customized deal generation

Disclosed are systems and methods for presenting supplemental content items on a user device while requested additional content is obtained. For example, a user is presented with a content item, such as an image, an advertisement, etc., on a display of a user device. The content item, when interacted with by the user, results in a request for additional content, such as a web page, being sent to a remote computing resource, the additional content item being received by the user device from the remote computing resource, loaded by the user device, and presented to the user on the display of the user device. Rather than presenting the user with a blank screen, an empty window, a 'loading' notification (e.g., spinning icon), etc., while the additional content item is retrieved and loaded, the implementations discussed herein provide the user with effectively instant gratification by presenting on the display of the user device and while the additional content item is retrieved and loaded, supplemental content that is already stored in memory of the user device.

Supplemental content items

Customized deal generation graphic user interface for point-of-sale device

The filtering of activities generated by nodes of a network while interacting with a device may be performed by evaluating the desirability of the activities (e.g., a spam or not-spam determination of email messages sent by the node) and assigning a trust rating to the node. However, nodes are often identified by network address, and an operator of a node sending undesirable activities may reassign the network address of the node in order to avoid heavy filtering. Instead, nodes may be identified as being controlled by a network entity (e.g., an autonomous system identified in a border gateway protocol routing table.) The network entity is assigned a network entity trust rating based on the trust ratings of the nodes controlled thereby, and an appropriate level of activity filtering based on the network entity trust rating may be selected for subsequent activities received from all nodes controlled by the network entity.

Activity filtering based on trust ratings of network

A computer implemented method for filtering unwanted bulk email in an email system and providing a positive user experience is provided. The method enables protection of email users from unsolicited bulk email using user-provided data on user interactions at both a user storage level and a global level with an email system. Metadata on user interactions with messages is collected. Messages are received by the system and evaluated using a global filter which assigns a score resulting in a message action. The action may be message delivery, message non-delivery or message routing, based on a score assigned by the global filter. When the message is delivered to user storage, the message may be examined relative to the metadata, and may alter the message action to an action different than the message action resulting from the score. Metadata for a plurality of users is returned to the global filter for use in making filtering future messages and modifies the global filter.

Personalized email interactions applied to global filtering

A system and method of managing unsolicited email sent to an email system over a network. Email messages are received at an message at an inbound mail transfer agent. A determination is made as to whether the email message is suspected to be an unsolicited suspect message. One or more queries for additional information on one or more characteristics of the message is initiated. Determinations are made based on replies to the queries before issuing a message accepted for delivery indication to a sending server.

Real-time spam look-up system

A computer implemented system and method to enable protection of email users from unsolicited bulk email using a message delivery delay based on characteristics detected in selected messages. Messages are evaluated for characteristics resembling unsolicited bulk email. A determination is made whether a message passing through the email system exhibits such characteristics and whether to delay the message. Suspect messages may be delayed for a period of time, the delay period being dependent on the characteristics giving rise to a determination to delay. Following the period, additional information received during the delay period characterizing the message is used to determine whether to dispose or deliver the message. Messages evaluated can be inbound to the email system, outbound to other email systems, or moving within the email system.

Delaying inbound and outbound email messages

Network entities controlling a set of nodes may vary by trustworthiness, such as tolerance for nodes that send spam, distribute malware, or perform denial-of-service attacks. A device receiving such activities may identify a trust rating of the network entity and apply appropriately stringent filtering (such as spam evaluation) to activities received from nodes controlled by the network entity. However, a poor trust rating of a network entity may subject a legitimate node controlled by the network entity to inefficiently or unfairly stringent activity filtering. Instead, the device may evaluate the activities of a particular node, assign a trust rating to the node, and if the trust rating of the node is higher than the trust rating of the network entity, apply less stringent activity filtering to the activities of the node, thereby 'rescuing' the node from the more stringent activity filtering applied to the other nodes of the network entity.

Rescuing trusted nodes from filtering of untrusted network entities

Methods for assisting email users manage email messages received in an email account. An event is triggered by an action performed by an email user with respect to an email message in an email account. The event identifies an entity associated with the email message (e.g., sender address, domain, keyword, etc.). A determination is made whether to assist the user manage their email based on a heuristic. The heuristic assigns weights based on prior events associated with the same entity to determine whether the user is interested in receiving emails from the sender. Based on the heuristics, the method may add the sender to the user's block-list or unsubscribe the user from a mailing list.

Email management based on user behavior

In a distributed email system, user preferences respected more effectively by presenting messages marked for deletion to secondary messaging servers having access to user preferences. Messages marked for deletion by inbound servers are presented to secondary level servers having access to user white lists and the choice of whether to delete the suspect message is made by the secondary server.

Honoring user preferences in email systems

Growing community of inventors

San Francisco, CA, United States of America

Mehrdad Bidgoli