DESC:METHOD AND SYSTEM FOR HARDWARE AND SOFTWARE BASED USER IDENTIFICATION FOR ADVERTISEMENT FRAUD DETECTION
TECHNICAL FIELD
[0001] The present disclosure relates to the field of fraud detection systems and, in particular, relates to a method and system to detect and authenticate fraud in advertisements.
BACKGROUND
[0002] With the advancements in technology over the last few years, users have predominantly shifted towards smartphones for accessing multimedia content. Nowadays, users access content through a number of applications available for download through various online application stores. Businesses (Advertisers) have started focusing on generating revenue by targeting consumers through these applications. In addition, businesses have started investing heavily in doing business through these applications. Moreover, businesses (publishers and/or advertising networks) have started developing capable advertisement applications for serving advertisements through these applications. These advertisements are published in real time or fixed placements through these applications and watched by the users. The advertisers are benefited in terms of internet traffic generated by clicking, taking action like installing or on watching these advertisements. However, certain online publishers and advertising networks working with these publishers take undue advantage of this in order to generate high revenues. These online publishers and advertising networks employ fraudulent techniques in order to generate clicks, or increasing actions like increasing number of application installs for the advertisers through fraudulent means. Typically, these publishers make use of various types of devices which continuously operate in order to perform click spamming and drive installs. This results in a loss of advertisers marketing budget spent as many times these publishers claim a normal user-initiated action (Organic action, e.g. Organic Install) as one initiated by them or at times the clicks or application installs are not driven by humans at all and instead by bots. There is a consistent need to stop publishers from performing such types of click fraud and transaction fraud.
OBJECT OF THE DISCLOSURE
[0003] A primary object of the present disclosure is to provide a method and system to detect fraud in advertisements based on hardware and software elements of a device.
[0004] Another object of the present disclosure is to provide a method and system to authenticate fraud in advertisements based on third party device data.
[0005] Yet another object of the present disclosure provides a method and system to detect fraud in advertisements based on movement or information from hardware elements and software elements such as gyroscope, accelerometer and the like.
[0006] Another object of the present disclosure provides a method and system to detect fraud in advertisements based on finger movements on the device.
[0007] Yet another object of the present disclosure provides a method and system to identify installs as Human or Rack based on movement or information from hardware or software elements of a device.
[0008] Yet another object of the present disclosure is to deter publishers from performing click spamming techniques and driving installs through fraudulent means.
SUMMARY
[0009] The present disclosure provides a computer system. The computer system includes one or more processors and a memory. The memory is coupled to the one or more processors. The memory stores instructions. The instructions are executed by the one or more processors. The execution of instructions causes the one or more processors to perform a method for detection of online advertisement fraud and commerce fraud. The method includes a first step of collecting a first set of data from a plurality of components associated with each device of a plurality of devices in real-time at a fraud detection system. The method includes another step of receiving a second set of data associated with each device of a plurality of third party devices in real-time at the fraud detection system. The method includes yet another step of creating a unique device profile for each device of the plurality of devices at the fraud detection system. The method includes another step of analyzing the first set of data and the second set of data after a periodic interval of time at the fraud detection system. The method includes yet another step of detecting the online advertisement fraud and commerce fraud based on the analysis of the first set of data and the second set of data in real-time at the fraud detection system.
BRIEF DESCRIPTION OF FIGURES
[0010] FIG. 1A illustrates an interactive computing environment between users and one or more components for detection of fraud in advertisements in real time, in accordance with various embodiments of the present disclosure;
[0011] FIG. 1B illustrates a block diagram of each device of a plurality of devices, in accordance with an embodiment of the present disclosure, and
[0012] FIG. 2 illustrates a block diagram of a computing device, in accordance with various embodiments of the present disclosure.
DETAILED DESCRIPTION
[0013] FIG. 1A illustrates an interactive computing environment 100 between a plurality of users 102 and one or more components for detection of online advertisement fraud and commerce fraud in real time, in accordance with various embodiments of the present disclosure. The interactive computing environment 100 includes the plurality of users 102, a plurality of devices 104, a plurality of components 106, a plurality of advertisers 108, a fraud detection system 110, a server 112, a database 114 and a plurality of third party devices 116. Further, the plurality of components 106 includes a plurality of device sensors 106A, a plurality of device biometrics 106B and a plurality of device connectivity components 106C. The online advertisement fraud and commerce fraud detection is performed based on one or more hardware components and one or more software components associated with each device of the plurality of devices 104. In an example, the one or more hardware components include gyroscope sensor, accelerometer sensor, magnetometer, barometer and the like. In another example, the one or more software components include Bluetooth, WiFi, network, infrared and the like. Further, the fraud in advertisements corresponds to click fraud, transaction fraud and the like. The click fraud corresponds to regular or constant clicking by a user or a group of users on an advertisement in order to generate more revenue for a publisher. The transaction fraud takes place when the publisher applies fraudulent techniques to drive fake installs of applications associated with an advertiser in order to generate more revenue. The interactive computing environment 100 shows interaction between various entities for the detection of fraud in advertisements.
[0014] The advertisements are displayed in third party applications developed by application developers. The application developers are known as publishers. The advertisements may include a graphical advertisement, a video advertisement, a banner advertisement and the like. The interactive computing environment 100 shows a relationship between various entities involved in the detection of the online advertisement fraud and commerce fraud. The online advertisement fraud and commerce fraud is detected based on information received from the plurality of components 106 associated with each device of the plurality of devices 104 in real time. The plurality of components 106 includes the one or more hardware components and the one or more software components of each device of the plurality of devices 104. The plurality of device sensors 106A is embedded inside the plurality of devices 104. In an example, the plurality of device sensors 106A includes but may not be limited to gyroscope sensor and accelerometer sensor. Further, each component of the plurality of components 106 interacts with each other to enable detection of the online advertisement fraud and commerce fraud in real time. The interactive computing environment 100 aids in tackling the online advertisement fraud and commerce fraud in applications in real time. The online advertisement fraud in applications refers to use of fraudulent techniques by publishers to generate fake online traffic. The online traffic is faked through techniques such as click fraud, transaction fraud and the like. The click fraud refers to generation of fraudulent clicks through online bots which are not identifiable to the plurality of advertisers 108 who treat the same as genuine online traffic. The transaction fraud refers to enabling application installs by providing some kind of incentive to the plurality of users 102 in real time or making claims of initiating install via fake clicks and bots (as described above in the application).
[0015] Further, a user of the plurality of users 102 is associated with a device of the plurality of devices 104. The plurality of users 102 are individuals or persons who access online multimedia content on respective devices. In addition, the plurality of users 102 may be any individuals or persons who run an application in real time on any platform such as Android, Mac and the like. The plurality of users 102 may be any persons or individuals who are committing the online advertisement fraud and commerce fraud in real time. The plurality of users 102 may be administrators associated with applications running on each device of the plurality of devices 104. The plurality of users 102 may be present at a single location, or at different locations. The plurality of users 102 may be hired by a publisher for performing fraudulent activities such as click spamming, ad driven installs and the like. The plurality of users 102 may belong to any third party which is in direct contract with the plurality of advertisers 108 for enabling display of advertisements. Further, a user of the plurality of users 102 access a publisher on a device of the plurality of devices 104. In an example, the plurality of devices 104 includes smartphone, set-top box, television, voice assistants and the like. In general, the smartphone is an Internet-enabled device for allowing the plurality of users 102 to access the publishers. The publishers are applications who display content to the plurality of users 102. The content may include one or more publisher content, one or more video content and the like. The plurality of devices 104 may or may not be fraudulent devices. The plurality of users 102 may or may not be fraudulent users. The plurality of devices 104 may be utilized by the plurality of users 102 to commit fraud in advertisements displayed in the applications.
[0016] The applications are software applications developed by third-party online publishers. The applications are advertisement supporting applications. The applications may be any type of application such as a gaming application, a utility application, a service based application and the like. The publishers provide space, areas or a part of their application pages for advertising purposes. These areas or spaces on the application pages are referred to as advertisement slots. The application page can have the various advertisement slots depending on the choice of each of the publishers. The publishers advertise products, services or businesses to the plurality of users 102 for generating revenue. Further, each device of the plurality of devices 104 includes the plurality of components 106. The plurality of components 106 includes the plurality of hardware components and the plurality of software components. In an example, the one or more hardware components include the plurality of device sensors 106A embedded inside the plurality of devices 104. In addition, the plurality of device sensors 106A include at least one of gyroscope sensor, an accelerometer sensor, a magnetometer, a proximity sensor, a barometer sensor, a compass, a touch sensor, a GPS sensor, a motion sensor and the like. In general, the accelerometer sensor is a sensor which is used to detect orientation of a device. In addition, the accelerometer sensor measures linear acceleration of movement. Also, the accelerometer sensor measures directional movement of the device. The accelerometer sensor measures a tilting motion of the device. The accelerometer sensor is used for motion sensing gaming in devices.
[0017] In general, the gyroscope sensor adds to information provided by the accelerometer sensor by tracking rotation or twist of the device. The gyroscope sensor measures the angular rotational velocity of the device. Further, the gyroscope sensor aids the accelerometer sensor to determine which way the device is oriented. In addition, the gyroscope sensor is used to maintain and control position, level or orientation of the device based on principle of angular momentum. In addition, each device of the plurality of devices 104 include other sensors which are used for the online advertisement fraud and commerce fraud detection in real time. Further, the plurality of device biometrics 106B include at least one of fingerprint scanner, 3D sensors, face recognition, voice recognition, retina scanner, iris scanner and the like. Furthermore, the plurality of device connectivity components 106C include at least one of Bluetooth, infrared, NFC, WiFi, network, direct cable, USB, wireless charging and the like. The plurality of users 102 accesses the publishers in real time on the plurality of devices 104. The online publishers continuously display advertisements through the applications. The plurality of users 102 encounters the advertisements while accessing the publishers. The advertisements may include text advertisements, video advertisements, graphic advertisements and the like. The plurality of users 102 may click on the advertisements and re-directed to a website of the advertiser associated with the corresponding clicked advertisement. The advertisements are provided by the plurality of advertisers 108. The plurality of advertisers 108 provide advertisements to the publishers for displaying on their application. The advertisements are placed on the advertisement slots in the applications.
[0018] The one or more advertisers purchase the advertisement slots from the one or more publishers. The advertisements may be served based on a real-time bidding technique or a direct contract between the plurality of advertisers 108 and the publishers. The plurality of advertisers 108 may provide the advertisements to advertising networks and information associated with advertising campaigns. The advertisement networks enable display of the advertisements in real time on the applications on behalf of the plurality of advertisers 108. The advertising networks are entities that connect the plurality of advertisers 108 to websites and applications that are willing to serve advertisements. Further, the fraud detection system 110 is associated with the publishers. The fraud detection system 110 is linked with multiple online publishers in real time. The online publishers correspond to the applications (the publishers). The fraud detection system 110 is a platform for detecting click fraud and transaction fraud done by the online publishers in real time. The fraud detection system 110 performs the detection of the online advertisement fraud and commerce fraud in in real time. The fraud detection system 110 performs the online advertisement fraud and commerce fraud detection based on real time data obtained from the plurality of components 106.
[0019] The fraud detection system 110 is associated with the plurality of components 106 in real time. In an embodiment of the present disclosure, the fraud detection system 110 is linked with the plurality of components 106 through the internet. In another embodiment of the present disclosure, the plurality of devices 104 must be connected to the internet through any means in real time. In an embodiment of the present disclosure, the fraud detection system 110 collects a first set of data from the plurality of components 106 in real time. The plurality of components 106 is associated with each device of the plurality of devices 104. The first set of data is received periodically through a communication network present between the fraud detection system 110 and the plurality of devices 104. In an example, the first set of data is associated with data collected from the gyroscope sensor and the accelerometer sensor embedded in each device of the plurality of devices 104. The first set of data is collected for determining a current position of each device of the plurality of devices 104 in terms of angular position, acceleration and the like. The fraud detection system 110 utilizes the first set of data to determine whether each device of the plurality of devices 104 is used to commit the online advertisement fraud and commerce fraud or not. In an example, the first set of data may include device IDs, IP address and the like along with data collected from the plurality of device sensors 106A for each device of the plurality of devices 104. In an embodiment of the present disclosure, the fraud detection system 110 stores the first set of data in the database 114 of the server 112. In an example, the fraud detection system 110 collects the first set of data from the plurality of device sensors 106A and stores the first set of data in the database 114.
[0020] The fraud detection system 110 is associated with the plurality of third party devices 116. The plurality of third party devices 116 may or may not be connected to the plurality of devices 104 in real time. The plurality of third party devices 116 is equipped with wired or wireless communication networks. In an embodiment of the present disclosure, the plurality of third party devices 116 interchange a second set of data with each other and the plurality of devices 104. Each device of the plurality of third party devices 116 interchanges a second set of data with the fraud detection system 110. The second set of data received from the plurality of third party devices 116 is utilized to determine and authenticate the online advertisement fraud and commerce fraud. In an embodiment of the present disclosure, the plurality of third party devices 116 is electronic devices, digital devices, communication devices, watch, headsets, input devices, payment devices, printers, display, storage devices, set top boxes, network devices, home automation devices, speakers and the like. In another embodiment of the present disclosure, the plurality of third party devices 116 include but may not be limited to televisions, radios, smartphones, laptops, desktops, and digital cameras. In yet another embodiment of the present disclosure, the plurality of third party devices 116 includes any other suitable devices of the like. The plurality of third party devices 116 associated with the interactive computing environment 100 is connected devices. In general, connected devices correspond to a plurality of devices connected to one another with the facilitation of communication networks with the facilitation of different wired or wireless protocols. In an example, different wired or wireless protocols include but may not be limited to Bluetooth, NFC, Wi-Fi, broadband and the like. In an embodiment of the present disclosure, the plurality of third party devices 116 are connected to each other with the facilitation of any other suitable communication network of the like. Further, each device of the plurality of third party devices 116 can operate to some extent interactively and autonomously. The fraud detection system 110 receives the second set of data associated with the plurality of third party devices 116 in real-time. In an embodiment of the present disclosure, the received second set of data is associated with the plurality of devices 104. Further, the plurality of third party devices 116 is connected with each other and the plurality of devices 104. The plurality of third party devices 116 and the plurality of devices 104 are equipped with wireless beacon technology. In general, wireless beacon technology corresponds to a technology that allows wireless communication devices to broadcast or receive data within finite distances. The beacon technology consists of two main components: a broadcaster beacon and a receiver beacon. The beacon technology activates and facilitates in data sharing between broadcaster beacon and receiver beacon. The beacon technology activates data sharing as soon as the broadcaster beacon, and the receiver beacon comes in the vicinity of one another. The plurality of third party devices 116 and the plurality of devices 104 act as two main components of the beacon technology. In an embodiment of the present disclosure, the plurality of devices 104 act as broadcaster beacons and the plurality of third party devices 116 act as receiver beacons. In another embodiment of the present disclosure, the plurality of devices 104 act as receiver beacons and the plurality of third party devices 116 act as broadcaster beacons. In addition, the fraud detection system 110 assigns a unique identity to each of the plurality of third party devices 116. In an embodiment of the present disclosure, the fraud detection system 110 assigns a unique identity to each of the plurality of devices 104. In an embodiment of the present disclosure, the plurality of devices communicate with the plurality of third party devices 116 using at least one of WLAN, NFC, Bluetooth, broadband, wireless beacon technology and the like.
[0021] Further, the fraud detection system 110 monitors and analyzes activities and operations of the plurality of devices 104 with facilitation of the plurality of third party devices 116. The fraud detection system 110 receives a plurality of sets of data (the first set of data and the second set of data) associated with the plurality of devices 104 with the facilitation of the plurality of third party devices 116. The fraud detection platform 110 processes and analyzes the first set of data and the second set of data associated with the plurality of devices 104 and the plurality of third party devices 116. The fraud detection system 110 analyzes the first set of data and the second set of data after a periodic interval of time. The fraud detection system 110 analyzes the first set of data and the second set of data with a pre-defined set of data. Further, the pre-defined set of data includes ideal values that must be maintained for each of the plurality of components 106 associated with the each device of the plurality of devices 104. In an embodiment of the present disclosure, the periodic interval of time may be variable or constant according to requirement. In an example, the fraud detection system 110 analyzes the first set of data and the second set of data after the periodic interval of time of 5 hours.
[0022] In an embodiment of the present disclosure, the fraud detection system 110 analyzes duration of time in which the first set of data collected from the plurality of device sensors 106A is zero. In an embodiment of the present disclosure, the fraud detection system 110 detects the online advertisement and commerce fraud if the first set of data collected from the plurality of device sensors 106A is zero for long periods of time. In an example, if the first set of data received from the gyroscope and accelerometer sensor for a device of the plurality of devices 104 is zero for a long period of time, the fraud detection system 110 treats this as the online advertisement fraud and commerce fraud as there is no movement of the device. The fraud detection system 110 detects the same as fraud and may determine that the device from which advertisement traffic is being generated may be used for performing fraud. In an embodiment of the present disclosure, the fraud detection system 110 performs a probabilistic determination of the online advertisement fraud and commerce fraud in real time. The fraud detection system 110 may derive that a particular device is kept at a stationary position or fixed position for a long period of time and is currently used for fraudulent purposes. The fraud detection system 110 may derive that the device might be used for performing click spamming through bot initiated clicks in real time. In an embodiment of the present disclosure, the fraud detection system 110 may perform complex event processing for performing the probabilistic fraud detection.
[0023] Further, the fraud detection system 110 calculates a probabilistic score for detection of the online advertisement fraud and commerce fraud in real time. In an embodiment of the present disclosure, the fraud detection system 110 calculates the probabilistic score for each device of the plurality of devices 104. In another embodiment of the present disclosure, the fraud detection system 110 calculates the probabilistic score for each device of the plurality of third party devices 116. The fraud detection system 110 may immediately block the device IDs or IP addresses through which the fraud is being performed. In an embodiment of the present disclosure, the fraud detection system 110 utilizes the first set of data and the second set of data to determine the online advertisement fraud and commerce fraud. The fraud detection system 110 analyzes the first set of data and the second set of data to detect the online advertisement and commerce fraud using a correlation data. Further, the correlation data includes a positive correlation data and a negative correlation data. The positive correlation data is based on pre-event and post-event data. The positive correlation may occur before any event (say installs) and post event. In an example, the event includes determination of same behavior of the plurality of users 102 with similar finger size. In an embodiment of the present disclosure, the touch sensors can determine hardness of the press, and size of the area pressed which may provide a rough determination of size of the finger. The negative correlation data is based on non-human behavior data. In an example, a touch or swipe without any changes to the accelerometer or gyroscope or compass during the time prior and after the interaction. The fraud detection system 110 takes into account a way the plurality of users 102 hold and interact with the corresponding plurality of devices 104. The fraud detection system 110 checks the same prior to the event and post the event to determine likelihood that the event was performed by the same person. The fraud detection system 110 detects that the online advertisement fraud and commerce fraud has occurred if there is a significant change between the style with which the user has held the device and interacted with the device.
[0024] Further, the fraud detection system 110 detects the online advertisement fraud and commerce fraud based on the analysis of the first set of data and the second set of data in real-time. The fraud detection system 110 detects the online advertisement fraud and commerce fraud based on one or more techniques. The one or more techniques include at least one of cross device mapping, digital fingerprinting and the like. The fraud detection system 110 authenticates the online advertisement fraud and commerce fraud based on the detection. In an embodiment of the present disclosure, each hardware component of the one or more hardware components and each software component of the one or more software components captures the first set of data. Each hardware component and software component sends the first set of data to the server 112 of application or in the cloud for analysis or hashed as a fingerprint. The server 112 controls the method with which the first set of data is sent. In an embodiment of the present disclosure, the accelerometer data can be used individually to determine the behavior of each user of the plurality of users 102. In an example, if the user behavior is random or no movement over a period of time is recorded, then it may be a sign that this is not a human who is interacting with the device. In an embodiment of the present disclosure, the fraud detection system 110 utilizes specific algorithms to filter out machine generated accelerometer behavior versus human based behavior. In an embodiment of the present disclosure, the accelerometer behavior can be used in conjunction with other sensors like touch sensors. In an example, when the user presses on an item on the device, the device moves slightly showing that this is human interaction.
[0025] In an embodiment of the present disclosure, the gyroscope or compass data can be individually used to determine behavior of each user of the plurality of users 102. The gyroscope or compass data may be used to generate an engagement to movement fingerprint. In an example, if there is no tilt or rotation then this is a sign of a non-human user. In an embodiment of the present disclosure, the fraud detection system 110 utilizes specific algorithms to filter out machine generated gyroscope behavior versus human based behavior. In an embodiment of the present disclosure, the gyroscope behavior can be used in conjunction with other sensors like touch sensors. In an example, when the user of the plurality of users 102 presses on an item on the device of the plurality of devices 104, the device rotates slightly showing that this is a human interaction. In addition, if a button is at the bottom of the screen of the device versus the top of the screen, the device will have a different rotation. In an embodiment of the present disclosure, the touch sensor data may be used to detect hardness or footprint of the press of the user on the device. In addition, the touch sensor data may be used to detect characteristics of the swipe / pinch / zoom action. Moreover, the touch sensor data may be used to determine if the user is a human or computer based on a re-captcha. In an embodiment of the present disclosure, the data from network devices or Bluetooth devices may be used for determining whether the user is a human or a computer. In an embodiment of the present disclosure, the fraud detection system 110 may access connected devices and compress a fingerprint of the connected devices to send to the server 112. The fraud detection system 110 may make a probabilistic determination that it is the same user and not a bot if the device has matching Bluetooth devices / network devices. In an example, there is a low chance for a bot of having a connected airpods/Bluetooth devices in use.
[0026] In an embodiment of the present disclosure, the fraud detection system 110 utilizes the first set of data collected from the plurality of components 106 to create a user profile. The user profile can be used to help match pre event (say a click) to post event interactions. In an embodiment of the present disclosure, the fraud detection system 110 employs additional security in order to stop replay attacks which can be used to return the device parameters or change the device parameters. The additional security may help in ensuring that a certain type of randomness is known and devices that just have a robot to reply are blocked from the system. In an embodiment of the present disclosure, the fraud detection system 110 continuously monitors and analyzes the first set of data collected through the plurality of components 106 of each device of the plurality of devices 104. The fraud detection system 110 builds a confidence score for determining whether there is any fraud or not. In an embodiment of the present disclosure, the fraud detection system 110 uses supervised machine learning and non-supervised machine learning. In an embodiment of the present disclosure, the fraud detection system 110 utilizes algorithms to intelligently adapt itself to the continuous change in the data.
[0027] In an embodiment of the present disclosure, the fraud detection system 110 performs the online advertisement fraud and commerce fraud detection in real time. The fraud detection system 110 immediately alerts the plurality of advertisers 108 or merchant or bank about the online advertisement fraud and commerce fraud so that the advertiser can block the flow of payment to the publisher or seller. In an embodiment of the present disclosure, the fraud detection system 110 builds a profile about a list of devices associated with a particular publisher or seller based on the fraud detection through the first set of data and the second set of data received from the plurality of components 106 and block display of advertisements or promotion of products through the particular publisher or supplier. In an example, the fraud detection system 110 may take into account the periodic interval of time in which the gyroscope data or the accelerometer data is null, and when the time exceeds the threshold time, the system can determine that as a fraud. In an embodiment of the present disclosure, the fraud detection system 110 may detect any wrong or misleading information associated with the first set of data collected from the plurality of components 106 in order to not term the same as fraud. In an embodiment of the present disclosure, the fraud detection system 110 may determine fraud based on a combination of the first set of data from the gyrometer, accelerometer, Bluetooth, network, touch sensors, 3D sensors and the like. In an embodiment of the present disclosure, the fraud detection system 110 may take into account a behavior profile of the plurality of users 102 and patterns based on data associated with a daily routine and a time period in which the gyroscope data and accelerometer data is consistent and does not change much and time periods in which the data from these sensors alter too much or not at all. The profiles and patterns may be at individual device levels or a group level.
[0028] In an embodiment of the present disclosure, the fraud detection system 110 takes into account periods of a day when the device data is usually zero or altering too much to determine fraud patterns or incidents. This may show a deviation in usual data trends from the gyroscope and the accelerometer. In an embodiment of the present disclosure, the fraud detection system 110 may take into account a time taken in a change of component data after an application install. If the time taken is above a threshold value, then it may be termed as a fraud. Further, the fraud detection system 110 is linked to the server 112. In an embodiment of the present disclosure, the server 112 controls each and every operation performed by the fraud detection system 110. The server 112 processes the first set of data in real time to determine the online advertisement fraud and commerce fraud. The server 112 includes the database 114. The database 114 may store the first set of data and the second set of data associated with the fraud detection system 110.
[0029] In an embodiment of the present disclosure, the fraud detection system 110 performs authentication of the online advertisement and commerce fraud using cross device mapping. The interactive computing environment 100 integrates the plurality of devices 104 and the plurality of third party devices 116 for authentication of the online advertisement fraud and commerce fraud. The interactive computing environment 100 receives and processes the plurality of sets of data from the plurality of devices 104 for authentication of the online advertisement fraud and commerce fraud. The fraud detection system 110 facilitates in real time authentication of the online advertisement fraud and commerce fraud using cross device mapping. The fraud detection system 110 utilizes the plurality of sets of data received through the plurality of devices 104 in vicinity of a user of the plurality of users 102 to authenticate the online advertisement fraud and commerce fraud by a device of the plurality of devices 104 in real time. The fraud detection system 110 utilizes the plurality of devices 104 to identify one or more device associated with a fraud executing device to facilitate the process of fraud detection and authentication. The plurality of sets of data received from the plurality of devices 104 facilitates to authenticate click fraud and transaction fraud being done in the vicinity of the plurality of devices 104.
[0030] The fraud detection system 110 creates a unique device profile corresponding to each device of the plurality of devices 104. The fraud detection system 110 stores the plurality of sets of data associated with the plurality of devices 104 in corresponding profile of the plurality of devices 104. The unique device profile of the plurality of devices 104 can be used to authenticate the online advertisement and commerce fraud based on cross device mapping. In an embodiment of the present disclosure, the fraud detection system 110 builds a profile related to the preference of advertisements that are preferred on the plurality of devices 104. For example, if an application is downloaded on the device associated with a category not present in the corresponding unique device profile of the device the publisher may be practicing fraud. The fraud detection system 110 stores the plurality of sets of data associated with the plurality of devices 104 in corresponding device profile of the plurality of devices 104. The fraud detection system 110 updates in real time the plurality of sets of data associated with the plurality of devices 104 in the corresponding device profile of the plurality of devices 104. The fraud detection system 110 identifies preferences and patterns in the advertisements responded by the plurality of users 102 of the plurality of devices 104. The fraud detection system 110 processes and analyses the plurality of sets of data to compare and analyze irregularities in the previously recorded preferences and patterns. The fraud detection system 110 stores and updates the plurality of sets of data associated with the plurality of devices 104 to compare and analyze the advertisement fraud and commerce fraud based on previous recorded patterns. The fraud detection system 110 analyzes irregularities and deviation in the patterns and preferences of the plurality of users 102 of a particular device of the plurality of devices 104 to authenticate the online advertisement fraud and commerce fraud.
[0031] The fraud detection system 110 couples the plurality of sets of data associated with the plurality of devices 104 with current location data of device. The fraud detection system 110 receives and analyzes the plurality of sets of data coupled with current location data. The fraud detection system 110 analyzes the plurality of sets of data received from a particular location and vicinity of the particular location to identify the online advertisement fraud and commerce fraud. For example, if the plurality of sets of data received from a particular location and the vicinity of the particular location indicates repeated multiple clicks on one or more advertisements the application fraud is authenticated. The fraud detection system 110 analyzes the plurality of devices 104 in the vicinity of fraud executing device. The fraud detection system 110 authenticates the online advertisement fraud and commerce fraud with the facilitation of the current location data. In an embodiment of the present disclosure, the fraud detection system 110 authenticates advertisements with the facilitation of any other suitable data of the like. The fraud detection system 110 authenticates the online advertisement fraud and commerce fraud with the facilitation of digital fingerprinting. In general, digital fingerprinting is a technology that enables content owners to exercise greater control on content by effective identification, tracking and monitoring across distribution channels while opening additional monetization avenue by exploiting the extended value of digital assets. The fraud detection system 110 monitors the advertisements and advertised content displayed on the plurality of devices 104 with the facilitation of the plurality of third party devices 116. The fraud detection system 110 employs digital fingerprinting to monitored content displayed on the plurality of third party devices 116. The fraud detection system 110 analyzes a variation in advertisements responded by the plurality of users 102 on the plurality of devices 104. The fraud detection system 110 analyses and compares the advertisements viewed by the plurality of users 102 with the unique device profile of the particular user to determine variation and irregularities.
[0032] The fraud detection system 110 determines the publishers performing fraudulent activities in real time. The fraud detection system 110 deters, blocks or intercepts the publishers who generate more clicks and installs by fraudulent means. The fraud detection system 110 may take necessary action against publishers who are generating revenue by fraudulent means. In addition, the fraud detection system 110 blocks publishers who perform fraudulent activities such as click spamming to simulate fake traffic. Moreover, the fraud detection system 110 alerts the plurality of advertisers 108 about the fraudulent publishers in real time. Accordingly, the plurality of advertisers 108 may take appropriate action against the fraudulent publishers. In an embodiment of the present disclosure, the fraud detection system 110 may use ambient audio/sound to detect if each of one or more devices of the plurality of devices 104 is a real phone in a real environment or an emulated phone. The fraud detection system 110 performs a method for authentication of the online advertisement fraud and commerce fraud. The fraud detection system 110 may track online activity of the plurality of users 102 and interaction of the plurality of users 102 with the advertisements in real time. The fraud detection system 110 may track online interaction of the plurality of devices 104 with other devices to facilitate in authentication platform. For example, if a device is authenticated for executing fraud the one or more devices associated with the fraud executing device are examined.
[0033] FIG. 2 illustrates a block diagram of a computing device 200, in accordance with various embodiments of the present disclosure. The device 200 is a non-transitory computer readable storage medium. The device 200 includes a bus 202 that directly or indirectly couples the following devices: memory 204, one or more processors 206, one or more presentation components 208, one or more input/output (I/O) ports 210, one or more input/output components 212, and an illustrative power supply 214. The bus 202 represents what may be one or more busses (such as an address bus, data bus, or combination thereof). Although the various blocks of FIG. 2 are shown with lines for the sake of clarity, in reality, delineating various components is not so clear, and metaphorically, the lines would more accurately be grey and fuzzy. For example, one may consider a presentation component such as a display device to be an I/O component. Also, processors have memory. The inventors recognize that such is the nature of the art, and reiterate that the diagram of FIG. 2 is merely illustrative of an exemplary device 200 that can be used in connection with one or more embodiments of the present invention. Distinction is not made between such categories as “workstation,” “server,” “laptop,” “hand-held device,” etc., as all are contemplated within the scope of FIG. 2 and reference to “computing device.”
[0034] The device 200 typically includes a variety of computer-readable media. The computer-readable media can be any available media that can be accessed by the device 200 and includes both volatile and nonvolatile media, removable and non-removable media. By way of example, and not limitation, the computer-readable media may comprise computer storage media and communication media. The computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. The computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by the device 200. The communication media typically embodies computer-readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media. The term “modulated data signal” means a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. By way of example, and not limitation, communication media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared and other wireless media. Combinations of any of the above should also be included within the scope of computer-readable media.
[0035] Memory 204 includes computer-storage media in the form of volatile and/or nonvolatile memory. The memory 204 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state memory, hard drives, optical-disc drives, etc. The device 200 includes the one or more processors 206 that read data from various entities such as memory 204 or I/O components 212. The one or more presentation components 208 present data indications to a user or other device. Exemplary presentation components include a display device, speaker, printing component, vibrating component, etc. The one or more I/O ports 210 allow the device 200 to be logically coupled to other devices including the one or more I/O components 212, some of which may be built in. Illustrative components include a microphone, joystick, game pad, satellite dish, scanner, printer, wireless device, etc.
,CLAIMS:What is claimed is:
1. A computer system comprising:
one or more processors; and
a memory coupled to the one or more processors, the memory for storing instructions which, when executed by the one or more processors, cause the one or more processors to perform a method for detection of online advertisement fraud and commerce fraud, the computer system comprising:
collecting, at a fraud detection system (110), a first set of data from a plurality of components (106) associated with each device of a plurality of devices (104) in real-time, wherein the plurality of components (106) comprises one or more hardware components and one or more software components of each device of the plurality of devices (104), wherein the plurality of components (106) comprises a plurality of device sensors (106A), a plurality of device biometrics (106B) and a plurality of device connectivity components (106C);
receiving, at the fraud detection system (110), a second set of data associated with each device of a plurality of third party devices (116) in real-time, wherein the plurality of third party devices (116) is connected with each other and the plurality of devices (104), wherein each device of the plurality of third party devices (116) is assigned with a unique identity by the fraud detection system (110);
creating, at the fraud detection system (110), a unique device profile for each device of the plurality of devices (104), wherein the unique device profile stores the corresponding first set of data collected from each device of the plurality of devices (104);
analyzing, at the fraud detection system (110), the first set of data and the second set of data after a periodic interval of time, wherein the first set of data and the second set of data is analyzed with a pre-defined set of data, wherein the analyzing is done to measure deviation in the first set of data and the second set of data from the pre-defined set of data after the periodic interval of time, wherein the analyzing is done using one or more strategies, wherein the analyzing is done to detect the online advertisement and commerce fraud using a correlation data;
detecting, at the fraud detection system (110), the online advertisement fraud and commerce fraud based on the analysis of the first set of data and the second set of data in real-time, wherein the detection is done based on one or more techniques, wherein the one or more techniques comprises of at least one of cross device mapping, and digital fingerprinting.
2. The computer system as recited in claim 1, wherein the plurality of device sensors (106A) comprises of at least one of a gyroscope sensor, an accelerometer sensor, a magnetometer, a proximity sensor, a barometer sensor, a compass, a touch sensor, a GPS sensor and a motion sensor.
3. The computer system as recited in claim 1, wherein the plurality of device biometrics (106B) comprises of at least one of one of fingerprint scanner, 3D sensors, face recognition, voice recognition, retina scanner and iris scanner.
4. The computer system as recited in claim 1, wherein the plurality of device connectivity components (106C) comprises of at least one of bluetooth, infrared, NFC, WiFi, network, direct cable, USB and wireless charging.
5. The computer system as recited in claim 1, wherein the plurality of devices (104) communicate with the plurality of third party devices (116) using at least one of WLAN, NFC, Bluetooth, broadband and wireless beacon technology.
6. The computer system as recited in claim 1, wherein the second set of data is received from each device of the plurality of third party devices (116) to facilitate in the detection of the online advertisement fraud and commerce fraud.
7. The computer system as recited in claim 1, wherein the pre-defined set of data comprises of ideal values that must be maintained for each of the plurality of components (106) associated with each device of the plurality of devices (104).
8. The computer system as recited in claim 1, further comprising calculating, at the fraud detection system (110), a probabilistic score for detection of the online advertisement and the commerce fraud in real-time, wherein the probabilistic score is calculated based on the first set of data collected from the plurality of components (106) associated with each device of the plurality of devices (104) and the second set of data received from each device of the plurality of third party devices (116).
9. The computer system as recited in claim 1, wherein the correlation data comprises of a positive correlation data and a negative correlation data, wherein the positive correlation data is based on pre-event and post-event data, wherein the negative correlation data is based on non-human behaviour data.
10. The computer system as recited in claim 1, wherein the first set of data collected from the plurality of components (106) associated with each device of the plurality of devices (104) is used to create a user profile, wherein the user profile is created in real-time.