By intercepting a natural language communication of a protected party, the communication is monitored, wherein the protected party is a human being. Within the monitored communication using a natural language processing engine, a natural language interaction between the protected party and a second party is detected. To determine an interaction pattern, the natural language interaction is analyzed. The interaction pattern includes data derived from the monitored communication, metadata of the protected party, and metadata of the second party. Using the interaction pattern and an interaction behavior model, an adverse result of the natural language interaction is predicted, wherein the adverse result comprises an economic loss to the protected party. By notifying the protected party, the predicted adverse result is intercepted.

A mobile device with a display, processor(s), and memory: identifies a retail machine configured for wireless communications based on broadcasted information transmitted by the retail machine and including an identifier corresponding to the retail machine; transmits the identifier to a server and receives from the server an electronic communication including a promotional offer for products or services offered by the retail machine; displays the promotional offer; detects selection of a promotional offer; receives a notification from the retail machine that a product or service was provided by the retail machine for a user of the mobile device; transmits confirmation information associated with the notification to the server, receives promotion validation information from the server indicating validation of the promotional offer; and based on the promotion validation information, displays information confirming application of the promotional offer.

A feature extraction unit extracts, from an advertising request to view an online advertisement, client information on a client as a transmission source of the advertising request and publisher information on a website of a publisher who displays advertising, and calculates a predetermined feature amount using the client information and the publisher information with respect to a plurality of advertising requests including at least a benign advertising request, and a determiner generation unit generates a determiner that determines whether an advertising request is malignant or not by using the calculated feature amount.

In an example, sets of event information associated with events may be identified. The events may include intentional click events, accidental click events and/or skip events. Accidental click probabilities associated with the accidental click events and/or the skip events may be determined. Machine learning model training may be performed, using the sets of event information associated with the events and labels associated with the events, to generate a first machine learning model. The labels may include second labels associated with the intentional click events and/or third labels associated with the accidental click events and/or the skip events. The second labels may correspond to an intentional click classification. The third labels may be based upon the accidental click probabilities. Click probabilities associated with content items may be determined using the first machine learning model. A content item may be selected for presentation via a client device based upon the click probabilities.

A software and/or hardware facility for scoring the quality of traffic to a site accessible via the Internet or other network. The facility may generate training set data and use the training set data to identify parameters indicative of fraudulent traffic to a site and reduce the effect of fraudulent traffic advertisers and publishers. The facility may score the quality of traffic and determine combinations of parameters that are indicative of the quality of traffic to the site. Traffic to the site may be scored based on the combination of parameters associated with the one or more sessions. Lower scores are indicative of traffic having little value to a publisher, advertiser, or third party; higher scores are indicative of traffic having greater value.

A method, product and system for automatic fraud engagement adjustment. The method comprises, based on monitoring of engagements and conversions, determining a segment-specific estimated quality score of a traffic segment; determining an observation-based pair-specific quality score for the traffic segment and for a specific campaign; and automatically performing mitigating fraudulent engagements in the traffic segment by reducing, in real-time, a reward for engagements in the traffic segment with respect to the specific campaign, whereby aggregative reward mitigates rewards for fraudulent engagements without specifically identifying which engagements are fraudulent.

Methods and systems for matching a consumer to benefits offered by enabling organizations provide flexibility and utility to consumers in the marketplace for various products. Information about benefits and enabling organizations are provided and stored in a memory of a computer system. A search query including consumer interest data of a consumer, or results of such a search query, are received. The enabling organization information, benefit information, and search query or information related to the search query results are analyzed automatically in the computer system to determine whether any enabling organization to which the consumer is affiliated is offering a benefit for the consumer that is applicable to the consumer interest data. Also determined is whether a coupon is applicable to the consumer interest data and if the coupon can be aggregated with the benefit.

A method of reducing a future amount of electronic fraud alerts includes receiving data detailing a financial transaction, inputting the data into a rules-based engine that generates an electronic fraud alert, transmitting the alert to a mobile device of a customer, and receiving from the mobile device customer feedback indicating that the alert was a false positive or otherwise erroneous. The method also includes inputting the data detailing the financial transaction into a machine learning program trained to (i) determine a reason why the false positive was generated, and (ii) then modify the rules-based engine to account for the reason why the false positive was generated, and to no longer generate electronic fraud alerts based upon (a) fact patterns similar to fact patterns of the financial transaction, or (b) data similar to the data detailing the financial transaction, to facilitate reducing an amount of future false positive fraud alerts.

The present teaching generally relates to removing perturbations from predictive scoring. In one embodiment, data representing a plurality of events detected by a content provider may be received, the data indicating a time that a corresponding event occurred and whether the corresponding event was fraudulent. First category data may be generated by grouping each event into one of a number of categories, each category being associated with a range of times. A first measure of risk for each category may be determined, where the first measure of risk indicates a likelihood that a future event occurring at a future time is fraudulent. Second category data may be generated by processing the first category data and a second measure of risk for each category may be determined. Measure data representing the second measure of risk for each category and the range of times associated with that category may be stored.

Opt-out systems and methods for tailored advertising are disclosed herein. An example method includes registering an endpoint with a service provider hosting an opt-out service that allows users to opt-out of tailored advertising from the endpoint, receiving a first request from a user including an email address, generating a hashed representation of the email address according to a hashing algorithm selected for the endpoint, transmitting a second request to the endpoint, the second request including the hashed representation of the email address, and receiving an acknowledgment that the endpoint has processed the second request. When the second request is processed the user does not receive the tailored advertising from the endpoint.