Marchex, Inc.

Ziad Ismail

Jason S Flaks

Chris Kolbegger

Matthew Berk

Govindaraj Ramanathan

Bryan Rieger

Darren Spehr

Tim Graber

Amanda Morrison

Govind Ramanathan

John Busby

Ambrose Sterr

A method and system that performs cross-channel correlation of user identifiers with consumer telephone numbers. The system receives impression data characterizing the exposure of users to mechanisms for contacting businesses, the impression data including associated phone number and a date and time for each of the exposures. The system also receives call data describing telephone calls to businesses, the call data including a caller telephone number, a callee telephone number, and a date and time for each of the calls. Based on matching impression telephone numbers and call data callee numbers, the system forms correlations between corresponding user identifiers and caller telephone numbers. Correlations are also assigned a confidence level, based on the date and time of the corresponding exposures and telephone calls, that reflects the likelihood that a user associated with the correlated user identifier is the same as the user associated with the correlated caller telephone number.

Cross-channel correlation of consumer telephone numbers and user identifiers

A method and system that performs cross-channel advertisement targeting based on consumer telephone numbers. The system utilizes a targeting database to determine which consumers should be re-engaged on behalf of a business. The targeting database correlates a telephone number associated with a consumer with a masked user identifier associated with the tracking of online behavior of that consumer. The targeting database may include a confidence level representing the likelihood of correspondence between the telephone number and masked user identifier. The targeting database is used by the system to target advertisements to consumers. A telephone number of a consumer is used to identify a masked identifier of the consumer. Advertisements are then targeted to the consumer using the masked identifier. The stored confidence level may be used by the system to control the aggressiveness of re-targeting.

Correlated consumer telephone numbers and user identifiers for advertising retargeting

A system and method for monitoring telephone calls to detect fraudulent activity and take corrective action is described. The system receives a group of telephone calls having associated call characteristics and analyzes the group of telephone calls to identify and store a first set of distributions of call characteristics that are indicative of normal activity, fraudulent activity, or indeterminate activity. The system receives one or more subsequent telephone calls to be analyzed. The system analyzes the received one or more telephone calls to identify a second set of distributions of call characteristics associated with the received telephone call. The system then compares the second set of distributions of call characteristics to the stored first set of distributions of call characteristics to assess a probability that the one or more received telephone calls represents normal, fraudulent, or indeterminate activity. If the assessed probability of fraudulent activity exceeds a threshold, the system takes appropriate corrective action, such a flagging the fraudulent call or withholding a financial incentive associated with the fraudulent call.

Identifying call characteristics to detect fraudulent call activity and take corrective action without using recording, transcription or caller ID

A facility and method for analyzing and classifying calls without transcription. The facility analyzes individual frames of an audio to identify speech and measure the amount of time spent in speech for each channel (e.g., caller channel, agent channel). Additional telephony metrics such as R-factor or MOS score and other metadata may be factored in as audio analysis inputs. The facility then analyzes the frames together as a whole and formulates a clustered-frame representation of a conversation to further identify dialog patterns and characterize call classification. Based on the data in the clustered-frame representation, the facility is able to make estimations of call classification. The correlation of dialog patterns to call classification may be utilized to develop targeted solutions for call classification issues, target certain advertising channels over others, evaluate advertising placements at scale, score callers, and to identify spammers.

System and method for analyzing and classifying calls without transcription

A facility and method for analyzing and classifying calls without transcription via keyword spotting is disclosed. The facility uses a group of calls having known outcomes to generate one or more domain- or entity-specific grammars containing keywords and related information that are indicative of particular outcome. The facility monitors telephone calls by determining the domain or entity associated with the call, loading the appropriate grammar or grammars associated with the determined domain or entity, and tracking keywords contained in the loaded grammar or grammars that are spoken during the monitored call, along with additional information. The facility performs a statistical analysis on the tracked keywords and additional information to determine a classification for the monitored telephone call.

System and method for analyzing and classifying calls without transcription via keyword spotting

A system and method for monitoring telephone calls to detect fraudulent activity and take corrective action is described. The system receives a first group of telephone calls having associated voice characteristics and analyzes the first group of telephone calls to identify and store a first set of distributions of voice characteristics that are indicative of normal activity, fraudulent activity, or indeterminate activity. The system receives a second group of telephone calls to be analyzed. The system analyzes the second group of telephone calls to identify a second set of distributions of voice characteristics associated with the second group of telephone calls. The system then compares the second set of distributions of voice characteristics to the stored first set of distributions of voice characteristics to assess a probability that one or more telephone calls in the second group of telephone calls represents normal, fraudulent, or indeterminate activity. If the assessed probability of fraudulent activity exceeds a threshold, the system takes appropriate corrective action, such a flagging the fraudulent call or withholding a financial incentive associated with the fraudulent call.

Analyzing voice characteristics to detect fraudulent call activity and take corrective action without using recording, transcription or caller ID

A facility and method for analyzing and classifying calls without transcription. The facility analyzes individual frames of an audio to identify speech and measure the amount of time spent in speech for each channel (e.g., caller channel, agent channel). Additional telephony metrics such as R-factor or MOS score and other metadata may be factored in as audio analysis inputs. The facility then analyzes the frames together as a whole and formulates a clustered-frame representation of a conversation to further identify dialogue patterns and characterize call classification. Based on the data in the clustered-frame representation, the facility is able to make estimations of call classification. The correlation of dialogue patterns to call classification may be utilized to develop targeted solutions for call classification issues, target certain advertising channels over others, evaluate advertising placements at scale, score callers, and to identify spammers.

A call tracking system and method that estimates a number of calls associated with a publication channel. The system uses a sampling algorithm to perform the estimation. The sampling algorithm selects a group of advertisements to serve as a sample group, and determines a distribution of calls for each of the publication channels associated with the sample group. The distribution of calls from the publication channels is assumed to be the same for all advertisements, and the data from the sample group is used to model the performance across all advertisements. The selected advertisements may be associated with one or more advertisers. Pooled or dynamic signal processing methods may also be used to estimate a number of calls associated with a publication channel. The number of calls associated with a publication channel may be utilized to determine the efficiency of, or calculate the revenue share associated with, an advertising campaign.

Call tracking system utilizing a sampling algorithm

A call tracking system and method that uses a pooling algorithm to manage a pool of telephone numbers that are utilized in advertisements. The pooling algorithm allows adjustments to be made to the pool in order to achieve a desired degree of call tracking accuracy performed by the system. The pooling algorithm may adjust the pool in terms of size, quality, or other metric, and assign phone numbers so as to meet the desired accuracy requirements. While additional numbers in a pool may increase accuracy, fewer numbers result in lower cost, and a balance may be struck based on the requirements of an advertiser. When a phone number is to be provided for an advertising campaign, the phone number may be selected from the pool randomly, in round-robin fashion, or according to criteria related to expected accuracy.

Call tracking system utilizing a pooling algorithm

A call tracking system and method that uses an automated filtering function to increase accuracy of call tracking. In some embodiments, the system utilizes a spam blocking module, such as a challenge-response test (e.g., a CAPTCHA), a blacklist for callers sharing certain criteria indicative of robo-dialed or spam calls, or other similar spam filter to block unwanted calls from being routed to an advertiser. By using a spam blocking module, the amount of noise in the call tracking system can be reduced and the attribution of calls correspondingly more accurate. In some embodiments, an interactive voice response (IVR) module is utilized to reduce the noise in the system by filtering or blocking unwanted calls. By utilizing an automated filtering function, the disclosed system improves the accuracy of call tracking and allows advertisers to better track the performance of advertising campaigns that they undertake.

Growing community of inventors

Seattle, WA, United States of America

Ziad Ismail