System and method for aggregating authentication determined customer data and network data

By aggregating customer data, device data, claim data and online fraud analysis to generate risk scores, banks and financial institutions have solved the problem of fraud identification difficulties in customer certification decisions, improved decision accuracy and customer experience, and reduced risks and losses.

CN119067672APending Publication Date: 2024-12-03JPMORGAN CHASE BANK NA
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411134460.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2017-08-23
Filing Date
2018-08-21
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

Banks and financial institutions fail to effectively utilize customer data in customer certification decisions, resulting in difficulty in identifying fraud and increasing losses and reputation risks.

Method used

A system and method are designed to generate a certification-determined risk score by aggregating customer data, device data, claim data and network fraud analysis to decide whether to allow access to an account. The system includes a computer server and memory, which automatically applies authentication decisions by identifying customer identifiers, retrieving customer profiles, and generating risk scores based on multiple data.

Benefits of technology

Improves the accuracy of customer identification and certification decisions, reduces risks and losses for financial institutions, and improves customer experience and loyalty.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119067672A_ABST
    Figure CN119067672A_ABST
Patent Text Reader

Abstract

Systems and methods for aggregating authentication determined customer data and network data are disclosed. The invention relates to a method and system for aggregating customer data and a network indicator to authenticate a customer. The system comprises: a computer server comprising at least one computer processor and coupled to a memory, the computer server programmed to: receive, via an electronic input, an authorization request from a requester for accessing an account; identifying a customer identifier associated with the authorization request; retrieving a customer profile from a memory using the customer identifier, where the customer profile is based on an aggregation of customer data, customer device data, claim data, and network data; generating a risk score based on an aggregated combination of customer data, customer device data, claim data, and network data to determine whether the requester passes authentication to access the account; and automatically applying the authentication determination to the authorization request.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] This application is a divisional application of Chinese patent application 201880068193.0, filed on August 21, 2018, entitled “System and method for aggregating customer data and network data determined by authentication”. Technical Field

[0002] The present invention generally relates to systems and methods for implementing authentication for retail customers and high net worth customers, and more specifically to systems and methods that aggregate a combination of customer data, device data, claims data, and network fraud analysis to generate authentication determinations. Background Art

[0003] Banks and other financial entities lose millions of dollars each year due to fraud schemes and other attacks. Much of this is attributed to the difficulty in identifying individual customers based on “authentication” decisions before account profiles are changed and transactions are executed. Due to the surge in data breaches involving personal data (such as PI data and PII data), it has become increasingly easier for cybercriminals to impersonate consumers and pose as consumers when interacting with banks, companies, merchants, and other entities. Personally Identifiable Information (PII) represents any data that identifies a specific individual, as well as any information that can be used to distinguish one person from another.

[0004] Currently, due to architectural, infrastructure, operational and other challenges, banks and other financial entities do not leverage all available data elements tied to customers when making authentication decisions in consumer, retail and high net worth individual lines of business. As a result, banks often experience authentication inaccuracies, as cybercriminals regularly impersonate customers and perform unauthorized account changes and subsequent payments, which can have significant monetary and reputational impacts on banks and their customers.

[0005] These and other shortcomings currently exist. Summary of the invention

[0006] According to one embodiment, the present invention relates to a computer-implemented system that aggregates customer data, device data, claims data, and network fraud analysis to generate an authentication determination. The system includes: a memory that stores and maintains a plurality of customer profiles; and a computer server that includes at least one computer processor and is coupled to the memory, the computer server being programmed to: receive an authorization request from a requester for accessing an account via electronic input; identify a customer identifier associated with the authorization request; retrieve a customer profile from the memory using the customer identifier, wherein the customer profile is based on an aggregation of customer data, customer device data, claims data, and network data; the customer data includes customer account data, customer behavior data, and transaction activity data; the customer device data includes device prints associated with the authorization request; the claims data includes pending data and previous data related to one or more improper activity reports; and the network data includes an indication of whether the customer's personally identifiable information has been compromised; generate a risk score based on the aggregated combination of the customer data, customer device data, claims data, and network data to determine whether the requester is authenticated to access the account; and automatically apply the authentication determination to the authorization request.

[0007] The system may include a specifically programmed computer system including one or more computer processors, a mobile device, an electronic storage device, and a network.

[0008] The present invention also relates to a computer-implemented method for aggregating customer data, device data, claims data, and network fraud analysis to generate an authentication determination. The method includes the following steps: receiving an authorization request from a requestor via electronic input for accessing an account; identifying, via a computer processor, a customer identifier associated with the authorization request; using the customer identifier, retrieving a customer profile from a memory component, wherein the customer profile is based on an aggregation of customer data, customer device data, claims data, and network data; the customer data includes customer account data, customer behavior data, and transaction activity data; the customer device data includes device prints associated with the authorization request; the claims data includes pending data and previous data related to one or more improper activity reports; and the network data includes an indication of whether the customer's personally identifiable information has been compromised; generating, via a computer processor, a risk score based on the aggregated combination of the customer data, customer device data, claims data, and network data to determine whether the requestor is authenticated to access the account; and automatically applying, via the computer processor, the authentication determination to the authorization request.

[0009] According to various embodiments of the present invention, the computer-implemented systems, methods, and media described herein provide unique advantages for financial institutions, bank customers, and other entities. This authentication model will greatly improve the accuracy of customer identification and authentication decisions made by financial institutions before allowing non-monetary transactions and monetary transactions to be performed. This will help reduce the risks faced by banks and customers from a reputational and monetary perspective. Other advantages include improved customer experience and reduced losses to financial institutions and loyalty and retention rates of bank customers and consumers due to increased satisfaction with improved accuracy of authentication decisions. These advantages and other advantages will be more fully described in the detailed description below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Reference is now made to the drawings to facilitate a more complete understanding of the present invention. The drawings should not be construed as limiting the present invention but are merely intended to illustrate various aspects and embodiments of the present invention.

[0011] Figure 1 A schematic diagram of a system that aggregates a combination of customer data, device data, claims data, and cyber fraud analytics to generate an authentication determination is shown in accordance with an exemplary embodiment.

[0012] Figure 2 is an exemplary flow chart illustrating a method for aggregating customer data, device data, claims data, and network fraud analysis to generate an authentication determination in accordance with an embodiment of the present invention.

[0013] Figure 3 is an illustration of various types of data that may be used for authentication decisions according to an embodiment of the present invention. DETAILED DESCRIPTION

[0014] The following description is intended to convey an understanding of the present invention by providing specific embodiments and details. However, it should be understood that the present invention is not limited to these specific embodiments and details which are merely exemplary. It should also be understood that, depending on the specific design and other needs, a person of ordinary skill in the art will understand that the present invention can be used for its intended purpose and benefits in many alternative embodiments based on known systems and methods.

[0015] Embodiments of the present invention relate to enhanced authentication systems and methods that aggregate, merge and analyze available data elements across customer identity, transaction, behavior and claims history, and cyber fraud datasets for use in generating risk scores for customer authentication decisions across various entry points and payment channels for individual customers and consumers. Embodiments of the present invention are directed to a risk-based approach that allows banks and other entities to make informed and accurate authentication decisions regarding customer identities.

[0016] Embodiments of the present invention may consider and weigh various data elements and / or factors to develop authentication scores for use by lines of business (LOBs) and / or other teams when identifying customers. Based on risk thresholds and / or confidence levels, the line of business may allow the requesting entity to respond or act accordingly. For example, based on a low risk score or analysis, the line of business may allow such an authentication attempt to pass. Other attempts with higher risk scores may be referenced for step-by-step (e.g., stricter) authentication. In addition, more risky requests that fail authentication may be directed to branches, dedicated service centers, or other options to provide identity authentication with higher confidence. Embodiments of the present invention may provide a tiered access approach. For example, if a customer chooses to participate in a behavior that the bank considers to be riskier (e.g., wire transfer to the first beneficiary, etc.) after successful authentication, the customer may be rerouted to other stricter authentications. According to another scenario, a customer may be limited to a limited number of available behaviors based on a risk score. Another option may involve close monitoring of the customer (after authentication), where available actions may be modified based on the customer's behavior and / or evolving network activity.

[0017] As intelligence sharing in the financial industry increases and becomes more complex, embodiments of the present invention are directed to pushing intelligence feeds directly into authentication decision engines to leverage information in a dynamic manner. Embodiments of the present invention may be directed to reducing the dwell time between the identification of malicious activity associated with data elements shared across the industry and the inclusion of such information in risk-based authentication decisions at entities such as banks, financial institutions, and the like.

[0018] As technology and cross-industry relationships evolve, embodiments of the present invention are intended to utilize data elements that are unique to technology platforms and / or data elements that are unique to other industries associated with such platforms. For example, mobile network operators (including wireless operators), mobile and computing device manufacturers, application developers and operating system providers, and other entities associated with mobile communications (e.g., social media, etc.) and online banking may provide data elements that are useful in bank authentication decisions.

[0019] Embodiments of the present invention may support partnerships between entities with similar concerns and / or interests. Credit bureaus may provide access to binary data points such as indicators related to recent address changes, identity theft, etc. Because data information sharing related to cybercriminal behavior has significant benefits, embodiments of the present invention may further leverage such data.

[0020] The following description provides different configurations and features according to exemplary embodiments. Although certain nomenclature and types of applications / hardware are described, other names and uses of applications / hardware are also possible, and the nomenclature provided is completed only by non-limiting examples. In addition, although specific embodiments are described, it should be understood that the features and functions of each embodiment can be combined in any combination within the capabilities of a person of ordinary skill in the art. The accompanying drawings provide other exemplary details about the present invention. It should also be understood that these exemplary embodiments are provided only as non-limiting examples.

[0021] Various exemplary methods are provided herein by way of example. Because there are multiple ways to perform methods according to the present disclosure, these methods are exemplary. The depicted and described methods can be performed or otherwise implemented by one or a combination of various systems and modules. Each box shown in the method represents one or more processes, decisions, methods or subroutines performed in the exemplary method, and these processes, decisions, methods or subroutines are not necessarily performed in the specific order outlined in the method, and each of them is not necessarily required.

[0022] Figure 1 A schematic diagram of a system according to an exemplary embodiment is shown that aggregates a combination of customer data, device data, claims data, and network fraud analysis to generate an authentication determination. As shown, network 102 can be communicatively coupled with various customer or consumer entities represented by 110, 112, and 114. For example, a customer can represent a consumer or other entity that has a relationship with financial entity 130. A customer can represent a company, a business, or a high net worth individual. In addition, network 102 communicates with financial entity 130 that provides various payment related services and / or other features.

[0023] The financial entity 130 may include an authentication engine 140 that implements logic rules 142 to evaluate whether an authentication request is valid. The authentication engine 140 may aggregate customer data, device data, claims data, and cyber fraud analysis to generate an authentication determination. According to an exemplary embodiment of the present invention, the authentication engine 140 may generate a risk score for the authentication request. The authentication engine 140 may receive data and input from various sources including external sources (e.g., credit reporting agencies, third-party entities, etc.). For example, external sources may include other financial institutions, customers, entities with corresponding or similar authentication data and cyber fraud data.

[0024] The authentication engine 140 may also include a learning engine 143. For example, embodiments of the present invention may be directed to applying a learning algorithm to evaluate whether an authentication request for a particular customer is valid. Embodiments of the present invention may apply machine learning and artificial intelligence algorithms to learn the behavior of customers and keep up with fraudsters and their changing strategies.

[0025] In addition, embodiments of the present invention can apply machine learning to the authentication process to learn from false positives. For example, the system can generate a risk score (or other risk indication) for a customer. By analyzing the customer's behavior and transaction history, the system can apply upper / lower thresholds that can be adjusted up or down. For example, although the authentication request may initially appear risky (e.g., a high risk score), the system may determine that the request is consistent with the customer's past behavior, or that the behavior is expected based on new data (e.g., a new job with additional responsibilities that may require transactions and requests, sudden international travel that requires the customer to be abroad, etc.). Therefore, the initial risk score can be adjusted up or down based on the customer's actions and the developing network analysis. The upper / lower thresholds can be continuously adjusted when new data is available. This method can further address false positives and reduce incorrect rejections of authentication requests.

[0026] The PII database 150 may store and maintain customer data including customer behavior data, customer demographics, customer device data, claims data, biometric data, and / or other personally identifiable information. For example, the PII database 150 may also include IP addresses, geographic locations, email activity and data, etc. The PII database 150 may receive data from various sources both internally and externally.

[0027] The network database 152 may store and maintain network data from clients, past fraud incidents, inferences made from black market activity, and / or other various sources of network-related data. The network database 152 may store data related to fraud incidents, targets (e.g., targeted persons / target groups / target teams), amounts (e.g., currency, threshold amounts, etc.), types of fraudulent requests (e.g., wire transfers), types of targets (e.g., communication channels, emails, etc.), and / or other characteristics or factors. The network database 152 may also identify known bad and known good fraud indicators (including bad / good beneficiaries, bad / good accounts, etc.). The network database 152 may receive data from various sources both internally and externally.

[0028] Analysis / reporting database 154 may store and maintain analysis, reports, trends, and / or other data, etc. The authentication risk analysis and processing described herein may be provided by financial entity 130 and / or by a third party provider represented by 132, where provider 132 may be in partnership with financial entity 130, for example.

[0029] Figure 1The system 100 can be implemented in a variety of ways. The architecture within the system 100 can be implemented as a hardware component (e.g., module) within one or more network elements. It should also be understood that the architecture within the system 100 can be implemented in computer executable software located within one or more network elements (e.g., on a tangible, non-temporary computer-readable medium). The module functions of the architecture within the system 100 can be located on a single device or distributed across multiple devices including one or more centralized servers and one or more mobile units or end-user devices. The architecture depicted in the system 100 is intended to be exemplary and not restrictive. For example, although the connections and relationships between the elements of the system 100 are depicted, it should be understood that other connections and relationships are also possible. As an example, the system 100 described below can be used to implement the various methods herein. The various elements of the system 100 can be referenced when explaining the exemplary methods described herein.

[0030] The network 102 may be a wireless network, a wired network, or any combination of a wireless network and a wired network. For example, the network 102 may include one or more of an Internet network, a satellite network, a wide area network ("WAN"), a local area network ("LAN"), an ad hoc network, a global system for mobile communications ("GSM"), a personal communications service ("PCS"), a personal area network ("PAN"), D-AMPS, Wi-Fi, fixed wireless data, IEEE 802.11a, IEEE 802.11b, IEEE 802.15.1, IEEE 802.11g, IEEE 802.11n, IEEE802.11ac, or any other wired or wireless network for transmitting or receiving data signals. Moreover, the network 102 may support an Internet network, a wireless communication network, a cellular network, Bluetooth, etc., or any combination thereof. The network 102 may further include one or any number of the exemplary types of networks described above that operate as independent networks or operate in cooperation with each other. The network 102 may utilize one or more protocols of one or more network elements to which it is communicatively coupled. The network 102 can convert to or from one or more protocols of the network device. For simplicity, although the network 102 is depicted as one network, it should be understood that according to one or more embodiments, the network 102 can include multiple interconnected networks such as a service provider network, the Internet, a cellular network, a corporate network, or even a home network, or any type of network described above.

[0031] Data may be sent and received via network 102 using standard networking protocols or standard telecommunication protocols. For example, data may be sent using Session Initiation Protocol (“SEP”), Wireless Application Protocol (“WAP”), Multimedia Messaging Service (“MMS”), Enhanced Messaging Service (“EMS”), Short Message Service (“SMS”), Global System for Mobile Communications (“GSM”)-based systems, Code Division Multiple Access (“CDMA”)-based systems, Transmission Control Protocol / Internet Protocol (“TCP / IP”), Hypertext Transfer Protocol (“HTTP”), Hypertext Transfer Secure (“HTTPS”), Real Time Streaming Protocol (“RTSP”), or other protocols and systems suitable for transmitting and receiving data. Data may be sent and received wirelessly, or in some cases may be sent using a wired network or telecommunication connection such as an Ethernet RJ45 / 5-type Ethernet connection, a fiber optic connection, a cable connection, or other wired network connection.

[0032] although Figure 1 Individual devices or components are shown, but it should be understood that multiple such devices may be present to perform various exemplary embodiments. Financial entity 130 may communicate with various entities via communication interface 144 using any mobile or computing device such as a laptop, personal digital assistant, smart phone, smart watch, smart glasses, other wearable device, or other computing device capable of sending or receiving network signals. Communication interface 144 may represent a user interface and / or other interactive communication portal.

[0033] Financial entity 130 may be communicatively coupled to database 150, database 152, database 154. Database 150, database 152, database 154 may include any suitable data structure to maintain information and allow access and retrieval of information. For example, database 150, database 152, database 154 may store data in an organized manner and may be an Oracle database, a Microsoft SQL Server database, a DB2 database, a MySQL database, a Sybase database, an object-oriented database, a hierarchical database, a flat database, and / or other types of databases known in the art to store and organize data as described herein.

[0034] Database 150, database 152, database 154 may be any suitable storage device or devices. The storage may be local, remote, or a combination thereof relative to database 150, database 152, database 154. Database 150, database 152, database 154 may utilize redundant array of independent disks (RAID), striped disks, hot spare disks, tapes, disks, or other computer accessible storage. In one or more embodiments, the storage may be a storage area network (SAN), an Internet Small Computer System Interface (iSCSI) SAN, a Fibre Channel SAN, a Common Internet File System (CTFS), a Network Attached Storage (NAS), or a Network File System (NFS). Database 150, database 152, database 154 may have built-in backup capabilities. Communication with database 150, database 152, database 154 may be performed over a network, or communication may involve a direct connection between database 150, database 152, database 154 and financial entity 130, such as Figure 1 Databases 150, 152, and 154 may also represent cloud storage or other network-based storage.

[0035] Figure 2 is an exemplary flow chart illustrating a method of aggregating customer data, device data, claims data, and cyber fraud analysis to generate an authentication determination according to an embodiment of the present invention. At step 210, a customer authentication process can be initiated. At step 212, a customer identifier and password combination can be identified. At step 214, a customer profile can be retrieved. At step 216, a risk score can be generated. At step 218, based on the risk score, one or more customer authorization actions can be determined. At step 220, the risk score can be applied to one or more channels. At step 222, the system can store and apply feedback analysis for further refinement. Figure 2 The order shown is exemplary only. Figure 2 The process of the present invention shows certain steps performed in a specific order, but it should be understood that the embodiments of the present invention can be practiced by adding one or more steps to the process, omitting steps within the process, and / or changing the order of one or more steps performed. These steps will be described in more detail below.

[0036] At step 210, a customer authentication process may be initiated. Embodiments of the present invention are directed to an improved authentication process that may be applied to payment requests or any request to access data. The authentication process determines the risk associated with the identity or credentials of the entity requesting authentication. For example, the innovative system may apply risk-based decisions to the requesting entity's attempts to access an account or application, perform an account action (e.g., transfer or wire funds, etc.), and / or other processes that require identity authentication or confirmation via various modes of communication (e.g., online, mobile application, telephone, face-to-face, etc.). Risk-based decisions may be applied to a variety of scenarios including point-of-sale transactions, online and face-to-face transactions, access to confidential information, and the like.

[0037] At step 212, a customer identifier and password combination may be identified. For example, the requesting entity may need to enter a customer name and password combination. Other systems may require other forms of identification. This information may then be verified and used to access the customer profile.

[0038] At step 214, a customer profile may be retrieved. The customer profile may include a combination of customer data, device data, credit / claims data, and related network data. Figure 3 Provide additional details.

[0039] At step 216, a risk score may be generated. Embodiments of the present invention may apply customer profile data, including various data elements, to a risk engine to generate a risk score with upper / lower thresholds that may be monitored and maintained. For example, the system may identify that a customer has exceeded a risk score and, therefore, the entity's risk tolerance in terms of certification. Thus, embodiments of the present invention are intended to protect entities (e.g., companies, banks, financial institutions, etc.) as well as consumers and customers.

[0040] While the more data elements that are incorporated into the risk score, the more accurate the risk score, efficiency may not allow for consideration of all available data. Embodiments of the present invention may determine an optimal number and quality of indicators to be used to determine a risk score for a particular authentication request. Embodiments of the present invention may also determine how many indicators and / or which types of indicators are optimal to make a confidence risk based decision. The number and quality of indicators may be based on an initial threshold query regarding the authentication request, entity request, geographic location, etc. According to another embodiment of the present invention, the decision may be applied to all authentication requests. In addition, the decision may be applied to authentication requests that meet criteria, for example, within a predetermined time period, geographic location, request type, etc. Other variations may be applied.

[0041] Embodiments of the present invention may utilize various types of network indicators when making authentication decisions. For example, embodiments of the present invention may incorporate network fraud intelligence indicators such as the IP address from which the authentication request was initiated. The system may also observe whether a customer exhibits signatures indicative of infection with financial malware. For example, there may be efforts to disguise or impersonate banking credentials. By combining various network intelligence indicators, embodiments of the present invention may aggregate various network intelligence indicators to generate a risk score.

[0042] In addition, based on certain considerations about the confidence of the indicators, different weights can be applied in generating (e.g., updating, increasing, decreasing) risk scores. For example, the system can identify emerging trends based on a particular type of fraud indicator. This can involve a particular attack on transactions sent to a foreign city. As a result, a higher weight can be applied to determinations involving that fraud indicator (e.g., transactions involving a foreign city). Moreover, the system can apply a higher risk level to transactions above a certain threshold amount. This can be captured by applying a higher weight to a higher transaction volume. Other variations can be applied.

[0043] At step 218, based on the risk score, one or more customer authorization actions may be determined. The system may identify permitted actions based on the risk score. For example, if the risk is determined to be low, the transaction may proceed. If some risk is involved, the system may allow the transaction to proceed with a monitoring feature on the funds.

[0044] At step 220, the risk score may be applied to one or more channels. Embodiments of the present invention are directed to aggregating specific data elements in the retail and high network individual customer space. Based on the confidence that the requester is who they say they are, embodiments of the present invention may permit actions commensurate with the confidence and consideration of other factors and data. For example, the system may allow the requester to perform certain actions (based on up / down scores) (such as checking balances, checking transactions, or viewing limited transaction history), but may prohibit other actions (such as initiating payment or instant payment functions).

[0045] Embodiments of the present invention may apply a tiered response based on the authentication decision. For example, a response may include: authenticating with full functionality, authenticating with limited functionality, and then not authenticating. Other variations may be applied.

[0046] At step 222, the system may store and apply the feedback analysis for further refinement. The system may continue the refinement process by examining and analyzing known fraudulent transactions as well as known good transactions. The feedback analysis may also focus on customer behavior information so that the system may better understand and predict the customer's payment and transaction behavior. According to another example, a financial institution may identify that a certain payment or other action may appear to be different from a customer's behavior pattern.

[0047] Figure 3 is a diagram of various types of data that may be used for authentication decisions according to an embodiment of the present invention. Figure 3 As shown, embodiments of the present invention may aggregate customer data 310, device data 312, and credit / claims data 314 and network data 316. Data may be received from various sources represented by input 302 (from internal sources) and input 304 (from external sources). Internal sources may represent various lines of business within a company, divisions, subsidiaries, contractors, partners, etc. External sources may include credit bureaus, government entities, third-party providers, competitors in the same or related fields, social media services, network organizations, etc.

[0048] Customer data 310 may include account data, customer demographic data, customer behavior data, and other relevant information. Customer data may include name, address, mobile phone number, birthday, social security number, family data, etc. Embodiments of the present invention may analyze the characteristics of the authentication request itself, such as which authentication (e.g., access to funds, access to information, etc.), the time of authentication (e.g., 2:00 EST), and then compare it with the customer's "normal" or benchmark authentication behavior. The system may apply specific benchmarks to each customer, or apply benchmarks to groups, categories, or types of customers. According to embodiments of the present invention, the system may apply machine learning to identify the expected behavior of the customer, and then establish a range so that when the action exceeds the expected behavior and range, an alert may be issued to the system and the customer's risk score may be further updated or adjusted. For example, if the customer's behavior exceeds expectations, the risk score may be increased by a certain amount.

[0049] The system may consider other types of information (including the customer's tenure). The system may also consider whether there is a co-signer or authorized user associated with the customer, profile, and / or account. If so, the system may determine whether that party has been associated with any negative behavior. The system may also consider whether the customer has security features, such as two-factor authentication enabled. Many companies employ second factor authentication, which involves sending an outbound message or text message to a cell phone to verify the customer's identity. As a result, fraudsters now compromise the customer's mobile phone account in addition to their identity to defeat second factor authentication.

[0050] Customer behavior may include rate and / or frequency of authentication activity; date / time patterns of historical authentication activity (e.g., geographic location of prior authentication activity, etc.); period of most recent non-monetary change to online banking profile; device contact information address changes, and other activity.

[0051] Customer data may also include other types of authentication data including the IP authentication attempt, the location where the attempt originated, and whether the origination data matches historical attempts. The system may also consider country risk scores; whether the IP address is associated with negative activity (or is on a negative list), and whether the IP address is associated with known proxy traffic. Other data may consider whether customer activity corresponds to previous activity, for example, whether the day of the week / time of day is consistent with previous activity.

[0052] Customer data may take into account the customer's presence in a location (such as a branch location), the period of activity, and the type of activity.

[0053] Embodiments of the present invention may apply data points collected as part of the onboarding process for a customer. For example, a financial institution may have an onboarding program to find out the background and expected behavior of a customer. Such information may include financial activity, such as how many wire transfers will be sent in a year; the average daily balance (or range) planned, etc. This information helps the entity determine what may be in-band behavior versus out-of-band behavior. In other words, a customer may go from normal or near-normal behavior to abnormal behavior.

[0054] For example, the system may identify a customer as having a checking account. The customer may also have an online profile that enables the customer to log into an associated website using a username and password combination. The system may retrieve customer information at the point of login as well as the IP address to identify the geographic region and determine in real time whether these elements match the customer's behavior and / or profile. Embodiments of the present invention may aggregate authentication data such as the customer's name, address, date of birth, and compromised or potentially compromised information. This information may include data related to information that is sold (or suspected of being sold) or available in the criminal underground.

[0055] Device data 312 may represent a device print associated with a login attempt. Embodiments of the present invention may also identify customer devices and also determine malware indicators that could indicate a potential compromise or attack. For example, the system may consider device identifiers, device types (e.g., mobile phones, smart phones, personal assistant devices, smart home devices, etc.), device signatures, and / or other customer device data. The system may obtain a specific device signature associated with the requesting entity. For example, a phone type running on a specific operating system may have an attribute that may be associated with a customer and pending claims, even if those claims do not result in fraud or compromise. The system may identify device activity and associate that device activity with a customer profile. This activity may increase (or decrease) the customer's current risk score.

[0056] Embodiments of the present invention may also consider geographic information that may be obtained by a mobile application. The geographic information may refer to an actual location (e.g., city, state, region, etc.). The system may also consider Internet geography to identify a customer's digital footprint. For example, the system may expect a customer's mobile phone to communicate via a known wireless carrier. However, if the communication comes from Digital Ocean, a cloud provider, a VPN space, etc., the system may flag the interaction.

[0057] The system can determine whether the authentication attempt matches historical attempts; whether the attempt is linked to other customers; whether the device is associated with negative behavior or is on a negative list; whether the attempt contains high-risk language attributes, the age of the expected configuration (e.g., operating system, software, software update, release, etc.).

[0058] Device data may also include automatic number identification (ANI) associated with the authentication attempt. For example, the system may determine whether the detected ANI matches historical activity; whether the ANI matches an ANI on a customer profile; whether the ANI is linked to activity of other customers and is on a negative list. The ANI may represent a characteristic of the telecommunications network used to automatically determine the originating phone number. For example, the ANI may represent a reference to a phone number from which a payment instruction was made as well as a modification of an existing instruction.

[0059] The system can also determine whether the customer's geographic location captured via the mobile app matches the location they claimed when asked; whether the location is within a specified distance of the address on their profile; and whether the geographic login information fits past behavioral patterns.

[0060] The system can determine the confidence level of the customer's email provider on record. For example, the system can identify that a particular email provider is favored by cybercriminals. In addition, the system can consider whether the customer has push notifications enabled. Before implementing a device or other non-monetary change to the customer's profile, a push notification can be sent to allow approval / rejection of the proposed change or action. Push notifications can be separated from the Short Message Service (SMS) through the mobile app. By monitoring push notifications, the system can obtain confirmation of changes that criminals routinely perform to support their fraudulent schemes. If a consumer who is being targeted by criminals is notified that a request has been made to update their phone number, address, mobile device, this will provide an opportunity to reject the change and the SMS message can be intercepted. The system can also determine whether the customer presents a signature associated with financial malware. Other actions can be identified.

[0061] Embodiments of the present invention are directed to implementing biometrics in authentication analysis. This may involve implementing and utilizing other technologies when establishing risk-based authentication scores. Embodiments of the present invention may consider biometric authentication that may provide additional weights. In many cases, biometric identifiers may be given additional weights due to their reliability. The system may identify new fraud schemes and learn from known fraud attempts. In an example where a fraudster begins to spoof biometrics, after identifying a fraudulent biometric (or other new type of fraud), the system may identify known fraud and apply machine learning to mark or identify this type of fraud as a new type of threat. The system may then identify similarities in other accounts (based on biometric fraud) and further identify accounts that may be at risk based on similarities to known fraud.

[0062] The system can take into account the voice biometric confidence score. The system can also take into account the overall activity speed. The speed can also be determined over a period of time or based on the type of interaction, etc.

[0063] Embodiments of the present invention may merge authentication data with data from the mobile network operator, the mobile phone operator space, and the email space. Information may be aggregated but not visible to one another. For example, shortly after detecting a change in the mobile operator, the system may notice changes made on a customer's webmail account, and then eventually the customer modifies an online banking account. This series of modifications may strongly indicate that an attacker has retrieved enough information to take over these channels.

[0064] Additional details are provided in co-pending patent applications U.S. Patent No. 15 / 393,836 filed on December 29, 2016 (Attorney Docket No. 72167.001198) and U.S. Serial No. 15 / 397,368 filed on January 3, 2017 (Attorney Docket No. J72167.0020501), the contents of which are incorporated herein by reference in their entirety.

[0065] Credit / claims data 314 may include previous fraud claims and active fraud claims (e.g., age of claim, disposition of claim, etc.) as well as credit rating, credit score, number of open lines of credit, etc. Claims data may include data related to claims made by a customer for unauthorized charges or other activity on an account such as a credit card, checking account, etc. The system may also determine whether a customer has a fraud alert on file with a credit bureau and whether the customer is associated with any credit monitoring for recent account openings.

[0066] Network data 316 may include data related to login credentials previously exposed in data breaches. Network data may also include whether a customer's PII data has been sold in the underground economy, and what elements and time periods of exposure or risk are involved.

[0067] Embodiments of the present invention may access and apply analytics that indicate a customer's personal information has been compromised. This information may be the result of recent data breaches for this entity as well as other entities (e.g., wireless carriers, email providers, retirement accounts, credit cards, debit cards, identity theft, etc.). This analytics may be aggregated to build or update a profile of a consumer.

[0068] The system can determine if the customer has login credentials for third-party websites that have been compromised, which can include social media, other financial entities, webmail, etc. For example, the system can identify that the customer's phone account was compromised during a network breach of the customer's wireless carrier. As a result, the customer's phone account was compromised through an attacker selling or using the customer's identity on the black market. This information can then be used to determine or adjust the risk associated with this customer.

[0069] Embodiments of the present invention may also monitor fraud rates associated with current customers. In other words, an entity may know that the information of a hundred customers has been stolen and is now available in the underground economy. This may lead to an increase in fraud rates associated with those customers. Then, as the fraud rate rises, the system may pay more attention and begin to take action or take remedial measures. In other words, before fraud reaches a critical level, embodiments of the present invention may apply known compromise and recovery efforts and further apply the information to risk-based authentication decisions. This may involve making technology-based decisions about whether a person who attempts to log in to an online banking application to access a checking account is authorized. Embodiments of the present invention may apply elements such as IP addresses associated with fraud or attempted fraud at other financial institutions. These elements may be shared between industry participants and competitors. Elements may also include email addresses such as personal webmail addresses of customers. Embodiments of the present invention may identify that an email address has been compromised because the information was recovered from a previous compromise. The system may identify other data that has been compromised or has been subject to fraud or attack.

[0070] Embodiments of the present invention aggregate authentication data and PII information. The system can proactively retrieve and access stolen personal data and personally identifiable information (PIT) from the black market. The system can recover the stolen information and then use the information for various fraud identification processes.

[0071] Embodiments of the present invention may access information through the black market and further determine that certain accounts and / or personal information are compromised or have a high risk of being compromised. Embodiments of the present invention may maintain and manage a central data repository where various intelligence feeds of different types of information are received into one repository. This information may then be pushed to the appropriate line of business stakeholders to leverage the information in an automated manner.

[0072] The system may consider whether the customer is operating from a device that has or has not been jailbroken, rooted, etc. Other data may relate to whether the customer is associated with an aggregation service, etc. The system may also consider recent activity at merchants or service providers that may have harvested PI / PII for fraudulent purposes (including recent USPS address changes and recent non-monetary changes of mobile carriers).

[0073] Embodiments of the present invention are directed to aggregating information from entities in one industry and other industries. More specifically, embodiments of the present invention can identify discernible patterns within and across industries and apply valuable data sets in risk-based certification decisions.

[0074] Embodiments of the present invention are intended to leverage information across lines of business (even if within an industry, the lines of business are completely different and largely separate). For example, an embodiment of the present invention may identify a retail customer who has a relationship with an entity as an individual product consumer, but the customer is also an employee of a merchant who is an investment banking client of the company. The system may further identify the customer as a user who has the authority to transfer money on behalf of the merchant. Thus, embodiments of the present invention are intended to implement measures to protect customers in the retail space to accurately authenticate them and further leverage them because the system identifies them as users representing merchants in the wholesaler space. In other words, if a fraudster targets them, attempts to impersonate them, and attempts to transfer money for this on the retail side, the system identifies that the fraudster may also target them to transfer funds on behalf of the merchant.

[0075] The foregoing examples illustrate various embodiments of the present invention in one physical configuration; however, it should be understood that various components may be located in remote portions of a distributed network such as a local area network, a wide area network, a telecommunications network, an intranet, and / or the Internet. Thus, it should be understood that, for example, the components of the various embodiments may be combined into one or more devices, collocated on specific nodes of a distributed network, or distributed at various locations in the network. As will be appreciated by those skilled in the art, the components of the various embodiments may be arranged at any location(s) within a distributed network without affecting the operation of the corresponding system.

[0076] As mentioned above, Figure 1A number of communication devices and components are included, each of which may include at least one programmed processor and at least one memory or storage device. The memory may store an instruction set. The instructions may be permanently or temporarily stored in one or more memories of the processor. The instruction set may include various instructions for performing one or more specific tasks (such as those tasks described above). Such an instruction set for performing a specific task may be characterized as a program, software program, software application, app, or software.

[0077] It should be understood that in order to practice the method of the embodiment as described above, the processor and / or memory do not have to be physically located in the same geographical location. That is, each processor and memory used in the exemplary embodiment of the present invention can be located in geographically different locations and connected to communicate in any suitable manner. In addition, it should be understood that each processor and / or memory can be composed of different physical devices. Therefore, the processor does not have to be a single piece of equipment in one location, and the memory does not have to be another single piece of equipment in another location. That is, it is expected that the processor can be two or more devices located in two or more different physical locations. Two different devices can be connected in any suitable manner. In addition, the memory can include two or more parts of the memory in two or more physical locations.

[0078] As described above, instruction sets are used in the processing of various embodiments of the present invention. Figure 1 The server in may include software or a computer program stored in a memory (e.g., a non-transitory computer readable medium containing program code instructions executed by a processor) for performing the methods described herein. The instruction set may be in the form of a program, software, or application. For example, the software may be in the form of system software or application software. For example, the software may also be in the form of a collection of separate programs, a program module in a larger program, or a portion of a program module. The software used may also include modular programming in the form of object-oriented programming. The software tells the processor what to do with the data being processed.

[0079] In addition, it should be understood that the instructions or instruction sets used in the embodiments and operations of the present invention can be suitable forms that allow the processor to read instructions. For example, the instructions forming the program can be in the form of a suitable programming language, which is converted into machine language or target code to allow (one or more) processors to read instructions. That is, a compiler, assembler or interpreter is used to convert the programming code or source code written lines in a specific programming language form into machine language. Machine language is a binary-coded machine instruction that is dedicated to a specific type of processor (e.g., dedicated to a specific type of computer). According to various embodiments of the present invention, any suitable programming language can be used. For example, the programming language used can include assembly language, Ada, APL, Basic, C, C++, COBOL, dBase, Forth, Fortran, Java, Modula-2, Pascal, Prolog, REXX, Visual Basic, JavaScript, etc. In addition, it is not necessary to use a single type of instruction or a single programming language in conjunction with the operation of the system and method of the present invention. Instead, any number of different programming languages ​​can be used as needed or desired.

[0080] Moreover, the instructions and / or data used in the practice of various embodiments of the present invention can utilize any compression or encryption technology or algorithm as needed. The encryption module can be used to encrypt data. In addition, for example, a suitable decryption module can be used to decrypt files or other data.

[0081] In the system and method of exemplary embodiments of the present invention, various "user interfaces" can be utilized to allow users to engage with mobile devices or other personal computing devices. As used herein, a user interface may include any hardware, software, or a combination of hardware and software used by a processor that allows a user to interact with a processor of a communication device. For example, a user interface may be in the form of a dialog screen provided by an application. The user interface may also include any one of the following items: a touch screen, a keyboard, a voice reader, a voice identifier, a dialog screen, a menu box, a list, a check box, a toggle switch, a button, a virtual environment (e.g., a virtual machine (VM) / cloud), or any other device that allows a user to receive information about the operation of a processor when the processor processes an instruction set and / or provides information to the processor. Therefore, a user interface may be any system that provides communication between a user and a processor. For example, the information that a user provides to a processor through a user interface may be in the form of a command, data selection, or some other input.

[0082] The software, hardware, and services described herein may be provided utilizing one or more cloud service models, such as software as a service (SaaS), platform as a service (PaaS), and infrastructure as a service (IaaS), and / or using one or more deployment models, such as a public cloud model, a private cloud model, a hybrid cloud model, and / or a community cloud model.

[0083] Although the above examples are primarily described as using a software application ("app") downloaded to a customer's mobile device, other embodiments of the invention may be implemented using similar techniques, such as using an existing web browser on the customer's mobile device to display the transmission of data.

[0084] Although embodiments of the invention are described herein in the context of a specific implementation in a specific environment for a specific purpose, those skilled in the art will recognize that its usefulness is not limited thereto and that embodiments of the invention may be advantageously implemented in other related environments for similar purposes.

Claims

1. A system for aggregating customer data and network indicators to authenticate a customer, the system comprising: a memory that stores and maintains a plurality of customer profiles; and a computer server comprising at least one computer processor and coupled to the memory, the computer server being programmed to: receiving, via electronic input, an authorization request from a requestor to access an account; identifying a client identifier associated with the authorization request; using the customer identifier, retrieving a customer profile from the memory, wherein the customer profile is based on an aggregation of customer data, customer device data, claims data, and network data; The customer data includes customer account data, customer behavior data and transaction activity data; The client device data includes a device print associated with the authorization request; The claims data includes pending and prior data related to one or more reports of improper activity; and The network data includes an indication of whether the customer's personally identifiable information has been compromised; generating a risk score based on an aggregated combination of the customer data, the customer device data, the claims data, and the network data to determine whether the requestor is authenticated to access the account; as well as An authentication determination is automatically applied to the authorization request.

2. The system according to claim 1, wherein: The accounts include accounts at financial institutions.

3. The system according to claim 1, wherein: The computer processor is programmed to: The risk score is automatically adjusted based on subsequent consumer data and network data.

4. The system according to claim 1, wherein: Network data includes data related to the authentication activities of one or more separate and distinct third-party entities in a common industry.

5. The system according to claim 1, wherein: The network data includes data related to authentication activities from one or more other business lines within a common corporate entity.

6. The system according to claim 1, wherein: The authentication determination includes one or more responsive actions granted to the requestor based on the risk score.

7. The system according to claim 1, wherein: The network data includes the originating IP address.

8. The system according to claim 1, wherein: The network data includes malware indicators.

9. The system according to claim 1, wherein: The network data includes voice biometrics.

10. The system of claim 1, wherein: The computer processor is further programmed to apply learning analytics to predict acceptable behavior for a customer.