IP Library › Granted Patent US 12,380,465
Granted Patent B2
US 12,380,465 · App. 17/450,490 · Granted Aug 5, 2025

Adaptive lead generation for marketing

Inventors: Pavan Korada (San Rafael, CA); Sunpreet Singh Khanuja (San Jose, CA); Weiwei Zhang (Palo Alto, CA); Bharat Goyal (San Jose, CA)
Assignee: Zeta Global Corp.
G06Q30/0243G06F16/24578G06F16/9535G06F30/20G06Q30/016G06Q30/0251
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,380,465
App. No.
17/450,490
Granted
Aug 5, 2025
Kind
B2
Abstract

Various examples are directed to systems and methods for adaptively generating leads. A marketing system may determine that a first lead score for a first lead is greater than a first lead score threshold and determine that a second lead score for a second lead is less than the first lead score threshold. The marketing system may generate a set of filtered leads including the first lead information from the first lead. The marketing system may determine a scrub rate that describes a portion of first execution cycle data having lead scores greater than the first lead score threshold and determine that the scrub rate is greater than an analysis window scrub rate by more than a scrub rate threshold. The marketing system may select a second lead score threshold that is lower than the first lead score threshold.

Claims (59)

1. A system comprising at least one processor and a memory in communication with the at least one processor, wherein the system is programmed to:

receive, by the at least one processor, first execution cycle data comprising a first lead and a second lead from a lead interface, wherein the first lead comprises first lead information describing a first potential customer and the second lead comprises second lead information describing a second potential customer;

determine, by the at least one processor, that a first lead score for the first lead is greater than a lead score threshold;

determine, by the at least one processor, that a second lead score for the second lead is less than the lead score threshold;

generate, by the at least one processor, a set of filtered leads including the first lead information based on the first lead score;

determine, by the at least one processor, a scrub rate, wherein the scrub rate describes a portion of the first execution cycle data having lead scores lower than the lead score threshold, wherein the scrub rate is a ratio of a number of customers removed from the system;

determine a mean scrub rate of a plurality of historical scrub rates to generate an analysis window scrub rate;

determine whether a scrub rate threshold is more than two standard deviations higher than the mean scrub rate;

automatically adjust the lead score threshold using an adjustment evaluator on the at least one processor in response to determining that the scrub rate threshold is more than two standard deviations higher than the mean scrub rate;

determine, by the adjustment evaluator, that the scrub rate is greater than an analysis window scrub rate by more than the scrub rate threshold;

determine, by a guard-rail enforcer component, that a number of score threshold adjustments do not exceed a predetermined number of score threshold adjustments in a predetermined time period before automatically adjusting the lead score threshold further using the adjustment evaluator in response to determining that the scrub rate is greater than the analysis window scrub rate by more than the scrub rate threshold;

in response to adjusting the lead score threshold, determine that an application of the adjusted lead score threshold is permitted by a limitation rule determined by the guard-rail enforcer component;

send a message to an administrative user before generating the set of filtered leads; and

transmit, by the at least one processor, data to the filtered leads.

2. The system of claim 1 , further programmed to:

determine an average scrub rate for a second plurality of leads received during an analysis window; and

determine the scrub rate threshold based at least in part on the average scrub rate.

3. The system of claim 1 , wherein the system is further programmed to determine a scrub rate for a plurality of lead scores for leads received during an analysis window.

4. The system of claim 1 , wherein the first execution cycle data comprises leads with a first common value for a first lead category, and wherein the first execution cycle data comprises leads with a second common value for a second common lead value.

5. A method for adaptively generating leads, the method performed by at least one processor, comprising:

receiving, by the at least one processor, first execution cycle data comprising a first lead and a second lead from a lead interface, wherein the first lead comprises first lead information describing a first potential customer and the second lead comprises second lead information describing a second potential customer;

determining, by the at least one processor, that a first lead score for the first lead is greater than a lead score threshold;

determining, by the at least one processor, that a second lead score for the second lead is less than the lead score threshold;

generating, by the at least one processor, a set of filtered leads including the first lead information based on the lead score of the first lead;

determining, by the at least one processor, a scrub rate, wherein the scrub rate describes a portion of the first execution cycle data having lead scores lower than the first lead score threshold, wherein the scrub rate is a ratio of a number of customers removed;

determining a mean scrub rate of a plurality of historical scrub rates to generate an analysis window scrub rate;

determining whether a scrub rate threshold is more than two standard deviations higher than the mean scrub rate;

automatically adjust the lead score threshold using an adjustment evaluator on the at least one processor in response to determining that the scrub rate threshold is more than two standard deviations higher than the mean scrub rate;

determining, by the adjustment evaluator, that the scrub rate is greater than an analysis window scrub rate by more than the scrub rate threshold;

determining, by a guard-rail enforcer component, that a number of score threshold adjustments do not exceed a predetermined number of score threshold adjustments in a predetermined time period before automatically adjusting the lead score threshold further using the adjustment evaluator in response to determining that the scrub rate is greater than the analysis window scrub rate by more than the scrub rate threshold;

in response to adjusting the lead score threshold, determining that an application of the adjusted lead score threshold is permitted by a limitation rule determined by the guard-rail enforcer component;

sending a message to an administrative user before generating the set of filtered leads; and

transmitting, by the at least one processor, data to the filtered leads.

6. The method of claim 5 , further comprising:

determining an average scrub rate for a second plurality of leads received during an analysis window; and

determining the scrub rate threshold based at least in part on the average scrub rate.

7. The method of claim 5 , further comprising:

determining a scrub rate for a plurality of lead scores for leads received during an analysis window.

8. The method of claim 5 , wherein the first execution cycle data comprises leads with a first common value for a first lead category, and wherein the first execution cycle data comprises leads with a second common value for a second common lead value.

9. A non-transitory machine-readable medium containing instructions which, when read by a machine, cause the machine to perform operations comprising:

receiving, by at least one processor, first execution cycle data comprising a first lead and a second lead from a lead interface, wherein the first lead comprises first lead information describing a first potential customer and the second lead comprises second lead information describing a second potential customer;

determining, by the at least one processor, that a first lead score for the first lead is greater than a lead score threshold;

determining, by the at least one processor, that a second lead score for the second lead is less than the lead score threshold;

generating, by the at least one processor, a set of filtered leads including the first lead information based on the lead score of the first lead;

determining, by the at least one processor, a scrub rate, wherein the scrub rate describes a portion of the first execution cycle data having lead scores lower than the first lead score threshold, wherein the scrub rate is a ratio of a number of customers removed;

determining a mean scrub rate of a plurality of historical scrub rates to generate an analysis window scrub rate;

determining whether a scrub rate threshold is more than two standard deviations higher than the mean scrub rate;

automatically adjust the lead score threshold using an adjustment evaluator on the at least one processor in response to determining that the scrub rate threshold is more than two standard deviations higher than the mean scrub rate;

determining, by the adjustment evaluator, that the scrub rate is greater than an analysis window scrub rate by more than the scrub rate threshold;

determining, by a guard-rail enforcer component, that a number of score threshold adjustments do not exceed a predetermined number of score threshold adjustments in a predetermined time period before automatically adjusting the lead score threshold further using the adjustment evaluator in response to determining that the scrub rate is greater than the analysis window scrub rate by more than the scrub rate threshold;

in response to adjusting the lead score threshold, determining that an application of the adjusted lead score threshold is permitted by a limitation rule determined by the guard-rail enforcer component;

sending a message to an administrative user before generating the set of filtered leads; and

transmitting, by the at least one processor, data to the filtered leads.

10. The non-transitory machine-readable medium of claim 9 , wherein the operations further comprise:

determining an average scrub rate for a second plurality of leads received during an analysis window; and

determining the scrub rate threshold based at least in part on the average scrub rate.

11. The non-transitory machine-readable medium of claim 9 , wherein the operations further comprise:

determining a scrub rate for a plurality of lead scores for leads received during an analysis window.

12. The non-transitory machine-readable medium of claim 9 , wherein the first execution cycle data comprise leads with a first common value for a first lead category, and wherein the first execution cycle data after adjusting the lead score threshold, determine that an application of the adjusted lead score threshold is permitted by a limitation rule determined by the guard-rail enforcer component comprises leads with a second common value for a second common lead value.

Assignments (3)
NOTICE OF GRANT OF SECURITY INTEREST IN PATENTS Recorded Aug 30, 2024
From: ZETA GLOBAL CORP.; ZSTREAM ACQUISITION LLC
To: BANK OF AMERICA, N.A., AS ADMINISTRATIVE AGENT
Reel/Frame 068822/0154 →
CHANGE OF NAME Recorded Nov 4, 2021
From: ZETA INTERACTIVE CORP.
To: ZETA GLOBAL CORP.
Reel/Frame 058024/0013 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 4, 2021
From: KORADA, PAVAN; KHANUJA, SUNPREET SINGH; ZHANG, WEIWEI; GOYAL, BHARAT
To: ZETA INTERACTIVE CORP.
Reel/Frame 058024/0177 →
Continuity (3)
Continuation 15594104 · May 12, 2017
Provisional Application 62336514 · May 13, 2016
Related Publication 20220027943A1 · Jan 27, 2022
References Cited (113)
US 6792399B1 · Phillips · 2004 [cited by examiner]
US 7003476B1 · Samra et al. · 2006 [cited by applicant]
US 7949588B2 · Willis · 2011 [cited by applicant]
US 8271313B2 · Williams · 2012 [cited by examiner]
US 8577736B2 · Swinson et al. · 2013 [cited by applicant]
US 10032174B2 · Hoff · 2018 [cited by applicant]
US 10157352B1 · Chan et al. · 2018 [cited by applicant]
US 10242068B1 · Ross · 2019 [cited by examiner]
US 10387833B2 · Swinson et al. · 2019 [cited by applicant]
US 10395217B1 · Lovejoy · 2019 [cited by applicant]
US 11144949B2 · Korada et al. · 2021 [cited by applicant]
US 11227304B2 · Korada et al. · 2022 [cited by applicant]
US 11354700B2 · Korada et al. · 2022 [cited by applicant]
US 11972455B2 · Korada et al. · 2024 [cited by applicant]
US 20040103017A1 · Reed et al. · 2004 [cited by applicant]
US 20060242000A1 · Giguiere · 2006 [cited by applicant]
US 20070219848A1 · Hubsher · 2007 [cited by examiner]
US 20070233561A1 · Golec · 2007 [cited by examiner]
US 20070244741A1 · Blume · 2007 [cited by examiner]
US 20080288361A1 · Rego et al. · 2008 [cited by applicant]
US 20090048859A1 · McCarthy · 2009 [cited by examiner]
US 20110082759A1 · Swinson · 2011 [cited by examiner]
US 20110231230A1 · Christon et al. · 2011 [cited by applicant]
US 20110258016A1 · Barak · 2011 [cited by examiner]
US 20110258049A1 · Ramer et al. · 2011 [cited by applicant]
US 20110264479A1 · Birr · 2011 [cited by applicant]
US 20110276507A1 · O'Malley · 2011 [cited by examiner]
US 20110307382A1 · Siegel · 2011 [cited by examiner]
US 20120323695A1 · Stibel · 2012 [cited by examiner]
US 20130066676A1 · Williams · 2013 [cited by examiner]
US 20140046880A1 · Breckenridge et al. · 2014 [cited by applicant]
US 20140149161A1 · Hedges · 2014 [cited by examiner]
US 20140149178A1 · Hedges · 2014 [cited by examiner]
US 20140200993A1 · Murphy · 2014 [cited by examiner]
US 20140214482A1 · Williams · 2014 [cited by examiner]
US 20140236708A1 · Wolff · 2014 [cited by examiner]
US 20140249873A1 · Stephan · 2014 [cited by examiner]
US 20140278981A1 · Mersov et al. · 2014 [cited by applicant]
US 20140316883A1 · Kitts · 2014 [cited by examiner]
US 20150142713A1 · Gopinathan · 2015 [cited by examiner]
US 20150186926A1 · Chittilappilly et al. · 2015 [cited by applicant]
US 20150213503A1 · Friborg, Jr. · 2015 [cited by examiner]
US 20150248693A1 · Dubey · 2015 [cited by examiner]
US 20150379647A1 · Gupta · 2015 [cited by examiner]
US 20160071117A1 · Duncan · 2016 [cited by examiner]
US 20160210657A1 · Chittilappilly · 2016 [cited by examiner]
US 20160217476A1 · Duggal · 2016 [cited by examiner]
US 20170206571A1 · Dhawan · 2017 [cited by examiner]
US 20170300933A1 · Mascaro · 2017 [cited by examiner]
US 20170329881A1 · Korada et al. · 2017 [cited by applicant]
US 20170330220A1 · Korada et al. · 2017 [cited by applicant]
US 20170345054A1 · Sinha · 2017 [cited by examiner]
US 20180060744A1 · Achin et al. · 2018 [cited by applicant]
US 20190251593A1 · Allouche · 2019 [cited by examiner]
US 20190318378A1 · Korada et al. · 2019 [cited by applicant]
US 20220092635A1 · Korada et al. · 2022 [cited by applicant]
US 20220245667A1 · Korada et al. · 2022 [cited by applicant]
US 20240320704A1 · Korada et al. · 2024 [cited by applicant]
The model of Internet marketing program considering 2ls (Year: 2005). [cited by examiner]
Community-Based Recommender Systems: Analyzing Business Models from a Systems Operator's Perspective (Year: 2009). [cited by examiner]
Tianyong Wang, The model of Internet marketing program considering 2ls, 2005 (Year: 2005). [cited by examiner]
Pei-Yu Chen, Community-Based Recommender Systems: Analyzing Business Models from a Systems Operator's Perspective, 2009 (Year: 2009). [cited by examiner]
“U.S. Appl. No. 15/594,104, Response filed Jan. 26, 2021 to Final Office Action mailed Oct. 26, 2020”, 13 pgs. [cited by applicant]
“U.S. Appl. No. 15/594,104, Response filed Jun. 2, 2020 to Final Office Action mailed Jan. 20, 2020”, 12 pgs. [cited by applicant]
“U.S. Appl. No. 15/594,284, Corrected Notice of Allowability mailed Nov. 3, 2021”, 9 pgs. [cited by applicant]
“U.S. Appl. No. 15/594,284, Final Office Action mailed May 24, 2021”, 12 pgs. [cited by applicant]
“U.S. Appl. No. 15/594,284, Final Office Action mailed Aug. 4, 2020”, 11 pgs. [cited by applicant]
“U.S. Appl. No. 15/594,284, Non Final Office Action mailed Jan. 16, 2020”, 12 pgs. [cited by applicant]
“U.S. Appl. No. 15/594,284, Non Final Office Action mailed Dec. 31, 2020”, 12 pgs. [cited by applicant]
“U.S. Appl. No. 15/594,284, Notice of Allowance mailed Oct. 27, 2021”, 13 pgs. [cited by applicant]
“U.S. Appl. No. 15/594,284, Response filed Mar. 31, 2021 to Non Final Office Action mailed Dec. 31, 2020”, 7 pgs. [cited by applicant]
“U.S. Appl. No. 15/594,284, Response filed Apr. 16, 2020 to Non Final Office Action mailed Jan. 16, 2020”, 9 pgs. [cited by applicant]
“U.S. Appl. No. 15/594,284, Response filed Sep. 22, 2021 to Final Office Action mailed May 24, 2021”, 8 pgs. [cited by applicant]
“U.S. Appl. No. 15/594,284, Response filed Dec. 4, 2020 to Final Office Action mailed Aug. 4, 2020”, 8 pgs. [cited by applicant]
“U.S. Appl. No. 16/453,471, Applicant Interview Summary filed Feb. 7, 2022”, 1 pg. [cited by applicant]
“U.S. Appl. No. 16/453,471, Examiner Interview Summary mailed Jan. 7, 2022”, 2 pgs. [cited by applicant]
“U.S. Appl. No. 16/453,471, Final Office Action mailed Feb. 25, 2021”, 39 pgs. [cited by applicant]
“U.S. Appl. No. 16/453,471, Non Final Office Action mailed Sep. 25, 2020”, 38 pgs. [cited by applicant]
“U.S. Appl. No. 16/453,471, Non Final Office Action mailed Nov. 2, 2021”, 27 pgs. [cited by applicant]
“U.S. Appl. No. 16/453,471, Notice of Allowance mailed Jan. 25, 2022”, 23 pgs. [cited by applicant]
“U.S. Appl. No. 16/453,471, Response filed Aug. 25, 2021 to Final Office Action mailed Feb. 25, 2021”, 12 pgs. [cited by applicant]
“U.S. Appl. No. 16/453,471, Response Filed Jan. 25, 2021 to Non Final Office Action mailed Sep. 25, 2020”, 12 pgs. [cited by applicant]
“U.S. Appl. No. 16/453,471, Response filed Dec. 2, 2021 to Non Final Office Action mailed Nov. 2, 2021”, 11 pgs. [cited by applicant]
“Sales pipeline win propensity prediction: A regression approach”, (2015), 5 pgs. [cited by applicant]
Aggour, Kareem, et al., “Mining company networks for marketing insights and sales leads”, IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, (2013), 805-812. [cited by applicant]
U.S. Appl. No. 17/538,647, filed Nov. 30, 2021, Adaptive Real Time Modeling and Scoring. [cited by applicant]
“U.S. Appl. No. 17/538,647, Examiner Interview Summary mailed Jun. 30, 2023”, 2 pgs. [cited by applicant]
“U.S. Appl. No. 17/538,647, Response filed Jul. 14, 2023 to Final Office Action mailed Apr. 14, 2023”, 10 pgs. [cited by applicant]
“U.S. Appl. No. 17/538,647, Final Office Action mailed Apr. 14, 2023”, 17 pgs. [cited by applicant]
“U.S. Appl. No. 17/538,647, Response filed Nov. 20, 2023 to Non Final Office Action mailed Aug. 24, 2023”, 11 pgs. [cited by applicant]
“U.S. Appl. No. 17/538,647, Notice of Allowance mailed Dec. 27, 2023”, 8 pgs. [cited by applicant]
“U.S. Appl. No. 15/594,104, Advisory Action mailed Mar. 9, 2020”, 5 pgs. [cited by applicant]
“U.S. Appl. No. 15/594,104, Final Office Action mailed Jan. 2, 2020”, 31 pgs. [cited by applicant]
“U.S. Appl. No. 15/594,104, Final Office Action mailed Oct. 26, 2020”, 31 pgs. [cited by applicant]
“U.S. Appl. No. 15/594,104, Non Final Office Action mailed Jun. 24, 2020”, 32 pgs. [cited by applicant]
“U.S. Appl. No. 15/594,104, Non Final Office Action mailed Sep. 30, 2019”, 26 pgs. [cited by applicant]
“U.S. Appl. No. 15/594,104, Notice of Allowance mailed Jun. 10, 2021”, 23 pgs. [cited by applicant]
“U.S. Appl. No. 15/594,104, Response filed Feb. 27, 2020 to Final Office Action mailed Jan. 2, 2020”, 11 pgs. [cited by applicant]
“U.S. Appl. No. 15/594,104, Response filed Jun. 26, 2019 to Restriction Requirement mailed May 23, 2019”, 6 pgs. [cited by applicant]
“U.S. Appl. No. 15/594,104, Response filed Nov. 19, 2019 to Non-Final Office Action mailed Sep. 30, 2019”, 15 pgs. [cited by applicant]
“U.S. Appl. No. 15/594,104, Response Filed Sep. 24, 2020 to Non Final Office Action mailed Jun. 24, 2020”, 13 pgs. [cited by applicant]
“U.S. Appl. No. 15/594,104, Restriction Requirement mailed May 23, 2019”, 7 pgs. [cited by applicant]
Dubiel, Jorg, “Promoting target models by potential measures”, (2010), 13 pgs. [cited by applicant]
Ramakrishnan, et al., “Automatic sales lead generation from web data”, IEEE, Computer society, Proceedings of the 22nd international conference on Data engineering., (2006), 10 pgs. [cited by applicant]
“U.S. Appl. No. 17/538,647, Non Final Office Action mailed Aug. 24, 2023”, 22 pgs. [cited by applicant]
“U.S. Appl. No. 17/538,647, Non Final Office Action mailed Dec. 28, 2022”, 16 pgs. [cited by applicant]
“U.S. Appl. No. 17/538,647, Response filed Mar. 23, 2023 to Non Final Office Action mailed Dec. 28, 2022”, 9 pgs. [cited by applicant]
“U.S. Appl. No. 17/538,647, Supplemental Amendment & Response filed Mar. 28, 2023”, 10 pgs. [cited by applicant]
U.S. Appl. No. 17/727,662, filed Apr. 22, 2022, Adaptice Lead Generation for Marketing. [cited by applicant]
“U.S. Appl. No. 18/620,239, Preliminary Amendment filed Jun. 11, 2024”, 7 pgs. [cited by applicant]
“U.S. Appl. No. 18/620,239, Non Final Office Action mailed Jan. 22, 2025”, 16 pgs. [cited by applicant]
“U.S. Appl. No. 17/727,662, Notice of Allowance mailed Feb. 20, 2025”, 16 pgs. [cited by applicant]
Luciano, Patrick, “Increasing loyalty using predictive modeling in Business-to-Business Telecommunication”, Elsevier, (Jun. 10, 2015), 15 pgs. [cited by applicant]