# US 8,751,300 B2 · Pixel cluster transit monitoring for detecting click fraud > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 8,751,300 B2 - Document ID: US8751300B2 - Status: Granted - Kind: B2 - Application number: 11/767,034 - Filed: 2007-06-22 - Published: 2008-12-25 - Granted: 2014-06-10 - Earliest claimed: 2007-06-22 - Assignees: International Business Machines Corporation - Applicants: Patrick O'Sullivan; Edith H. Stern; Robert C. Weir; Barry E. Willner - Inventors: Patrick O'Sullivan; Edith H. Stern; Robert C. Weir; Barry E. Willner - Web page: https://patentgrep.com/patent/US8751300B2 ## CPC - G06Q 30/0241: Advertisements - G06Q 10/101: Collaborative creation, e.g. joint development of products or services - G06Q 30/02: Marketing; Price estimation or determination; Fundraising - G06Q 30/0248: {Avoiding fraud} - G06Q 30/0254: {based on statistics} - G06F 3/04812: Interaction techniques based on cursor appearance or behaviour, e.g. being affected by the presence of displayed objects - G09G 5/08: Cursor circuits - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G09G: ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION (arrangements for transferring data between digital computers and displays G06F3/14; static indicating arrangements comprising an association of a number of separate sources or light control cells G09F9/00; static indicating arrangements comprising integral associations of a number of light sources H01J, H01K, H10H, H05B33/12; scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission, details thereof H04N1/00) ## Abstract Detecting click fraud that includes a processing device that receives data related to a cursor movement towards an advertisement displayed on a web page. The processing device analyzes the cursor movement data and determines a confidence level useable in the determination of click fraud, the confidence level responsive to the analysis of the cursor movement. The received data includes data that the cursor on the web page has transited at least one pixel cluster on the web page prior to a clicking the advertisement. In one embodiment, a click fraud is detected when the click occurred without the cursor crossing a pixel cluster, and no click fraud occurring when the click occurred after the cursor crossed a pixel cluster. ## Claims ### Claim 1 A method for detecting click fraud comprising receiving, by a processing device, data related to a cursor movement towards an advertisement displayed on a web page; receiving, by the processing device, cursor movement data that the cursor on the web page has transited at least one pixel cluster of a plurality of pixel clusters on the web page prior to a click on the advertisement, each pixel cluster comprising boundaries and the pixel clusters form a perimeter around the advertisement so the cursor has to move across the boundaries of the at least one pixel cluster to reach the advertisement; analyzing, by the processing device, the cursor movement data; and determining, by the processing device, a confidence level used m the determination of click fraud, said confidence level being responsive to the analysis of the cursor movement. ### Claim 2 (depends on 1) The method according to claim 1, further comprising determining the confidence level based on at least the transiting, and the clicking, the confidence level being used m the determination of click fraud. ### Claim 3 (depends on 2) The method according to claim 2, further comprising receiving data regarding a measured speed of the cursor transiting each pixel cluster and factoring the measured speed data into the confidence level determination. ### Claim 4 (depends on 2) The method according to claim 2, further comprising receiving data related to the click on the advertisement when the advertisement has been displayed initially for a short time duration m one of a transparent or an invisible font, the click on the advertisement during the short time duration data being factored into the confidence level determination. ### Claim 5 (depends on 1) The method according to claim 1, further comprising analyzing the cursor movement data by determining whether the click occurred without crossing the at least one pixel cluster, and determining a click fraud when the click occurred without the cursor crossing the at least one pixel cluster and no click fraud occurring when the click occurred after the cursor crossed the at least one pixel cluster. ### Claim 6 (depends on 1) The method according to claim 1, further comprising receiving data captured by mechanisms associated with each pixel cluster regarding pixel clusters transited by the cursor movement. ### Claim 7 A processing device comprising: a processor, a memory associated with the processor, a module stored on the memory that receives data related to a cursor movement towards an advertisement displayed on a web page when executed by the processor, the module receiving cursor movement data that the cursor on the web page has transited at least one pixel cluster of a plurality of pixel clusters on the web page prior to a click on the advertisement, each pixel cluster comprising boundaries and the pixel clusters form a perimeter around the advertisement so the cursor has to move across the boundaries of the at least one pixel cluster to reach the advertisement; a module stored on the memory that analyzes the cursor movement data when executed by the processor, and a module stored on the memory that determines a confidence level used m the determination of click fraud when executed by the processor, said confidence level being responsive to the analysis of the cursor movement. ### Claim 8 (depends on 7) The device according to claim 7, wherein data related to the click on the advertisement when the advertisement has been displayed initially for a short time duration m one of a transparent or an invisible font is received and factored into the confidence level determination. ### Claim 9 (depends on 7) The device according to claim 7, further comprising the module analyzing the cursor movement data by determining whether the click occurred without crossing a pixel cluster, and determining a click fraud when the click occurred without the cursor crossing a pixel cluster and no click fraud occurring when the click occurred after the cursor crossed a pixel cluster. ### Claim 10 (depends on 7) The device according to claim 7, further comprising mechanisms associated with the pixel clusters on the web page that are configured to capture data regarding the pixel clusters being transited by the cursor movement. ### Claim 11 (depends on 7) The device according to claim 7, further comprising the processor receiving data related to at least one of a view duration of the web page from the time it was initially loaded to the time of the clicking on the advertisement, a measured speed of the cursor transiting each pixel cluster, or the click on the advertisement when the advertisement has been displayed initially for a short time duration in one of a transparent or an invisible font, each of the view duration data, the measured speed data, and the click on the advertisement during the short time duration data being used in the analysis to determine the confidence level. ### Claim 12 (depends on 11) The device according to claim 11, further comprising the processor determining the confidence level based on the timing, the transiting, and the clicking, the confidence level being used in the determination of a click fraud. ### Claim 13 A computer program product comprising a non-transitory computer useable storage medium having computer useable program code embodied therewith, the computer useable program code comprising: computer useable program code configured to receive data related to a cursor movement towards an advertisement displayed on a web page; computer useable program code configured to receive cursor movement data that the cursor on the web page has transited at least one pixel cluster of a plurality of pixel clusters on the web page prior to a click on the advertisement, each pixel cluster comprising boundaries and the pixel clusters forming a perimeter around the advertisement so the cursor has to move across the boundaries of the at least one pixel cluster to reach the advertisement; computer useable program code configured to analyze the cursor movement data, and computer useable program code configured to determine a confidence level used in the determination of click fraud, said confidence level being responsive to the analysis of the cursor movement. ### Claim 14 (depends on 13) The computer program product according to claim 13, further comprising computer useable program code configured to determine the confidence level based on at least transiting, and clicking on the advertisement, the confidence level being used m the determination of the confidence level useable m the determination of click fraud. ### Claim 15 (depends on 13) The computer program product according to claim 13, further comprising computer useable program code configured to receive data regarding a measured speed of the cursor transiting each pixel cluster and factoring the measured speed data into the confidence level determination. ### Claim 16 (depends on 13) The computer program product according to claim 13, further comprising computer useable program code configured to receive data related to the click on the advertisement when the advertisement has been displayed initially for a short time duration in one of a transparent or an invisible font, the click on the advertisement during the short time duration data being factored into the confidence level determination. ### Claim 17 (depends on 13) The computer program product according to claim 13, further comprising computer useable program code configured to analyze the cursor movement data by determining whether the click occurred without crossing the at least one pixel cluster, and determining click fraud when the click occurred without the cursor crossing the at least one pixel cluster and no click fraud occurring when the click occurred after the cursor crossed the at least one pixel cluster. ### Claim 18 (depends on 13) The computer program product according to claim 13, further comprising computer useable program code configured to receive data captured by mechanisms associated with each pixel cluster regarding pixel clusters transited by the cursor movement. ### Claim 19 (depends on 1) The method according to claim 1, wherein the web page has at least one boundary layer generally disposed around the advertisement, and wherein analyzing the cursor movement data comprises determining whether the cursor movement crossed the boundary layer. ### Claim 20 (depends on 19) The method of claim 19, wherein the boundary layer is disposed at varying pixel distances from the advertisement. ### Claim 21 (depends on 19) The method according to claim 19, wherein the boundary layer is disposed based at least in part on a pseudo-random variation. ### Claim 22 (depends on 21) The method according to claim 21, wherein the pseudo-random variation comprises choosing disposition of the boundary layer from a group of possible dispositions. ### Claim 23 (depends on 22) The method of claim 22, wherein the group of possible dispositions comprises disposition of the boundary layer at least partially adjacent the perimeter of the advertisement and disposition of the boundary layer at least partially a predetermined number of pixels from the perimeter of the advertisement. ### Claim 24 (depends on 19) The method according to claim 19, wherein the web page has two or more boundary layers, each boundary layer generally disposed around the advertisement, and wherein analyzing the cursor movement data comprising determining whether the cursor movement crossed each of the boundary layers. ### Claim 25 (depends on 24) The method of claim 24, wherein the two or more boundary layers are each disposed based at least m part on a pseudo-random variation comprising choosing disposition of each of the boundary layers from a group of possible dispositions. ### Claim 26 (depends on 25) The method of claim 25, wherein the group of possible dispositions comprises disposing each of the boundary layers at different predetermined numbers of pixels from the perimeter of the advertisement. ### Claim 27 (depends on 1) The method of claim 1, further comprising moving the cursor to a predefined location when the web page comes up with the advertisement, the cursor being required to be moved by a user completely across the boundaries of the at least one pixel cluster to reach the advertisement. ### Claim 28 (depends on 1) The method of claim 1, further comprising moving the cursor to a predefined location when the web page comes up with the advertisement, the cursor being required to be moved by a user to reach the advertisement. ### Claim 29 (depends on 28) The method of claim 28, further comprising using a list of predefined locations or pseudo-random generated locations for moving the cursor to the predefined location when the web page comes up with the advertisement. ### Claim 30 (depends on 1) The method of claim 1, further comprising providing the plurality of pixel clusters along with the webpage each time the advertisement on the web page is served, wherein a location of each pixel cluster is predetermined when the advertisement is served.