Counterfactual analysis of user models for prescriptive output

Abstract

Status influence elements indicated by a behavior model of a target user are identified in response to an indication that the status of a digital identity for the target user is less than a status threshold. Status influence elements indicated behavior models for each of a plurality of users with digital identities that satisfy the status threshold are also identified. Distances between the target user and each user of the plurality of users are calculated and, based on the distance between the target user and a first user of the plurality of users being the shortest calculated distance, the behavior model of the target user is modified according to a status influence element indicated by the respective behavior model for the first user. Instructions for modifying the status of the digital identity for the target user to satisfy the status threshold are generated based on the modified behavior model.

Description

COUNTERFACTUAL ANALYSIS OF USER MODELS FOR PRESCRIPTIVE OUTPUTBACKGROUND

[0001] Maintaining a positive digital identity is crucial in today’s interconnected world, where personal, economic, and professional spheres often intersect online. A well-curated digital identity can qualify an individual for or enable transactions including commercial, financial, insurance-related, healthcare-related, and / or credit-related transactions. For example, the status of a digital identity may dictate whether a user can open a new bank account and / or a new credit card, execute a transaction with a merchant device, and / or the like. The status of a digital identity may be affected by a user model (e.g., online behavior, financial activity, spending patterns, credit utilization, etc.) and / or compromised by nefarious actor s / activity (e.g., identity theft, fraudulent activity, etc.). A user with a digital identity that has been affected by a user model and / or compromised by nefarious activity is routinely unable to receive guidance on how to improve, alter, and / or modify the status of their digital identity.SUMMARY

[0002] Provided herein are system, apparatus, device, method and / or computer program product embodiments, and / or combinations and sub-combinations thereof, for counterfactual analysis of user models for prescriptive output. One or more computing devices may identify a plurality of status influence elements indicated by a behavior model of a target user. Identification of the plurality of status influence elements indicated by the behavior model of a target user may be responsive to an indication that a status of a digital identity for the target user is less than a status threshold for digital identities eligible for a transaction. A respective plurality of status influence elements indicated by a respective behavior model for each user of a plurality of users with respective digital identities that satisfy the status threshold may also be identified. A respective distance between the target user and each user of the plurality of users with respective digital identities that satisfy the status threshold may be calculated based on respective weighted values that represent a degree of influence on eligibility for the transaction assigned to therespective plurality of status influence elements indicated by the respective behavior model for each user of the plurality of users and the plurality of status influence elements indicated by the behavior model of the target user. Based on the respective distance between the target user and a first user of the plurality of users being the shortest calculated distance, the behavior model of the target user may be modified according to at least one of the respective plurality of status influence elements indicated by the respective behavior model for the first user. Instructions for modifying the status of the digital identity for the target user to satisfy the status threshold for digital identities eligible for the transaction may be generated based on the modified behavior model.BRIEF DESCRIPTION OF THE DRAWINGS

[0003] The accompanying drawings are incorporated herein and form a part of the specification.

[0004] FIG. l is a block diagram of an example system for counterfactual analysis of user models for prescriptive output, according to some aspects of this disclosure.

[0005] FIG. 2 is an example similarity graph for counterfactual analysis of user models for prescriptive output, according to some aspects of this disclosure.

[0006] FIG. 3 is a flowchart of an example method for counterfactual analysis of user models for prescriptive output, according to some aspects of this disclosure.

[0007] FIG. 4 is an example computer system useful for implementing various embodiments.

[0008] In the drawings, like reference numbers generally indicate identical or similar elements. Additionally, generally, the left-most digit(s) of a reference number identifies the drawing in which the reference number first appears.DETAILED DESCRIPTION

[0009] Provided herein are system, apparatus, device, method and / or computer program product embodiments, and / or combinations and sub-combinations thereof, for counterfactual analysis of user models for prescriptive output. The status of a digital identity may be affected by a user model (e.g., online behavior, financial activity, spending patterns, credit utilization, etc.) and / or compromised by nefarious actors / activity(e.g., identity theft, fraudulent activity, etc.). Responsive to an identified status of a digital identity, such as a status that falls below a defined threshold, a status that indicates that a digital identity is compromised, and / or the like, prescriptive guidance on how to improve, alter, and / or modify the status of the digital identity may be generated.

[0010] For example, guidance on how to improve a credit score may be provided to a user who is denied approval for a transaction based on a digital identity indicative of the credit score and / or the like. As another example, guidance on how to improve the status of a digital identity may be provided to a user who has had the status of their digital identity damaged due to identity theft and / or related fraudulent activity. Guidance and / or instructive data regarding how to improve, alter, and / or modify the status of a digital identity may be prescriptive and specific to the context of achieving a particular goal (e.g., credit approval, identity protection, etc.). The guidance and / or instructive data may indicate actionable and legitimate behaviors that are feasible for the user to perform / achieve. Further, guidance and / or instructive data may be based on empirically observed data from observed outcomes, such that any forecasted outcome from the implementation of the guidance and / or instructive data is readily realized and may be calibrated to any desired threshold.

[0011] User models (e.g., functional representations of user online activity, social media activity, e-commerce activity, etc.) and / or behavioral models (e.g., functional representations of user credit-related activity, account balances, transaction history, etc.) used in the generation of guidance and / or instructive data may be derived independently from the identification of counterfactuals used to generate the guidance and / or instructive data. For example, for a target user (e.g., a user with a digital identity status that falls below a threshold or intended status, etc.), user data and / or user profile-level data collected from a plurality of sources (e.g., analytic service providers, entity data repositories, telemetry data, etc.) may be used to generate a behavioral model that is paired with the behavioral model of another user with digital identity status influencing elements that best match the user. The paired user may be a user with a digital identity that satisfies a particular threshold or meets a defined goal. Status-influencing elements from the behavioral model of the paired user may be used as counterfactuals for modifying the behavioral model of the target user. The modified behavioral model maybe used to generate guidance for improving, modifying, and / or altering the status of the digital identity of the target user.

[0012] According to some aspects of this disclosure, optimization of the guidance for improving, modifying, and / or altering the status of the digital identity of the target user derived from counterfactual observation may be based on minimizing the sum of incremental model weights required to shift the output of a given observation to above a given modified behavioral model output threshold. As described herein, the system, apparatus, device, method and / or computer program product embodiments, and / or combinations and sub-combinations thereof, for counterfactual analysis of user models for prescriptive output provide precise and granular guidance on how to modify a behavioral model to achieve any desired goal. One or more constraints may be implemented to manage sparsity, proximity, and / or plausibility parameters during counterfactual evaluation and guidance generation to identify a concrete and reasonably achievable path to any desired outcome. These and other advantages are described herein.

[0013] FIG. 1 shows a block diagram of an example system 100 for counterfactual analysis of user models for prescriptive output. System 100 is merely an example of one suitable system environment and is not intended to suggest any limitation as to the scope of use or functionality of aspects described herein. Neither should the system 100 be interpreted as having any dependency or requirement related to any single device / module / component or combination of devices / modules / components described therein.

[0014] According to some aspects of this disclosure, system 100 may include a network 102. According to some aspects of this disclosure, network 102 may include a packet- switched network (e.g., internet protocol-based network), a non-packet switched network (e.g., quadrature amplitude modulation-based network), and / or the like. According to some aspects of this disclosure, network 102 may include network adapters, switches, routers, modems, and the like connected through wireless links (e.g., radiofrequency, satellite) and / or physical links (e.g., fiber optic cable, coaxial cable, Ethernet cable, or a combination thereof). Network 102 may include public networks, private networks, wide area networks (e.g., Internet), local area networks, and / or the like. According to some aspects of this disclosure, network 102 may include a content access network, content distribution network, and / or the like. According to some aspects of this disclosure,network 102 may provide and / or support communication from telephone, cellular, modem, and / or other electronic devices to and throughout the system 100. For example, system 100 may include and support communications between user devices 104A-104N, a computing device 110, and a third-party systems 118 via network 102.

[0015] According to some aspects of this disclosure, user devices 104A-104N may be part of a client and / or user computing system and / or infrastructure. For example, user devices 104A-104N may represent a plurality of user devices in communication and / or interoperability within a client and / or user computing system and / or infrastructure. Although user device 104A is described herein in greater detail, each user device 104A- 104N may be similarly configured.

[0016] According to some aspects of this disclosure, user device 104A may include, for example, a smart device, a mobile device, a laptop, a tablet, a display device, a computing device, or any other device capable of communicating with computing device 110, third- party systems 118, and / or any other device / component of system 100, either described or unshown. User device 104A may include communication module 106 that facilitates and / or enables communication with network 102 (e.g., devices, components, and / or systems of network 102, etc.), computing device 110, and / or any other device / component of system 100. For example, communication module 106 may include hardware and / or software to facilitate communication. According to some aspects of this disclosure, communication module 106 may include one or more of a modem, transceiver (e.g., wireless transceiver, etc.), digital-to-analog converter, analog-to-digital converter, encoder, decoder, modulator, demodulator, tuner (e.g., QAM tuner, QPSK tuner), and / or the like. According to some aspects of this disclosure, communication module 106 may include any hardware and / or software necessary to facilitate communication.

[0017] According to some aspects of this disclosure, User device 104A may include an interface module 108. According to some aspects of this disclosure, interface module 108 enables a user to interact with user device 104, network 102, computing device 110, and / or any other device / component of system 100. Interface module 108 may include any interface for presenting and / or receiving information to / from a user.

[0018] According to some aspects of this disclosure, interface module 108 enables a user to view and / or interact with content, applications, web pages, and / or user interfaces. According to some aspects, interface module 108 may include a web browser (e.g.,Internet Explorer®, Mozilla Firefox®, Google Chrome®, Safari®, or the like). According to some aspects, interface module 108 may include one or more applications including credit management applications, financial applications, e-commerce applications, identity management applications, and / or the like. According to some aspects, interface module 108 may request or query various files from a local source and / or a remote source, such as computing device 110, third-party systems 118, and / or any other device / component of system 100. For example, interface module 108 may facilitate one or more transactions including credit approval transactions, product purchase transactions, communicationbased transactions, and / or the like.

[0019] According to some aspects, interface module 108 may include one or more input devices and / or components, for example, such as a keyboard, a pointing device (e.g., a computer mouse, remote control), a microphone, a joystick, a tactile input device (e.g., touch screen, gloves, etc.), and / or the like. According to some aspects, interaction with the input devices and / or components may enable a user to interact with a user interface generated and / or displayed by the interface module 108 and / or the like. For example, interaction with the input devices and / or components may enable a user to review prescriptive data and / or guidance instructions for modifying, improving, and / or altering a digital identity. According to some aspects, interaction with the input devices and / or components may enable a user to request the generation of prescriptive data and / or guidance instructions for modifying, improving, and / or altering a digital identity.

[0020] According to some aspects of this disclosure, user devices 104A-104N may generate and / or output data / information that may be used to build user profiles and / or behavior profiles for users of the user devices 104A-104N. For example, data indicative of usage of financial or investment applications may be used to indicate financial literacy or involvement, data indicative of the frequency and types of online purchases may be tracked to indicate user spending habits, location data from user devices 104A-104N may indicate and / or be used to infer behavior patterns, data indicative of how users interact on web-based, online, and social media platforms may indicate and / or be used to infer behavior patterns, and / or the like.

[0021] According to some aspects of this disclosure, data / information that may be used to build user profiles and / or behavior profiles for users of the user devices 104A-104N may be collected and / or provided via third-party systems 118. Third-party systems 118 mayinclude a system, compute infrastructure / architecture, and / or software platform configured to access a plurality of software applications, services, and / or data sources. Third-party systems 118 may include, facilitate, and / or support social networks, payment networks, blockchain, e-commerce, financial transactions, payment acceptance / remittance services, content acquisition and delivery services, identity management and security systems, and / or the like.

[0022] Third-party systems 118 may include, access, support, and / or host any applications and / or data through any delivery paradigm, including but not limited to remote or distributed cloud computing solutions, local or on-premises software (“onpremise” cloud-based solutions), cloud-based services, “as a service” models (e.g., content as a service (CaaS), digital content as a service (DCaaS), software as a service (SaaS), managed software as a service (MSaaS), platform as a service (PaaS), backend as a service (BaaS), mobile backend as a service (MBaaS), infrastructure as a service (laaS), etc.), and / or the like. Third-party systems 118 may include and / or support systems including, but not limited to, commercial entities (e.g., merchant devices, e-commerce platforms, etc.), financial institutions and / or finance-supporting institutions (e.g., banks, credit card companies, government agencies, etc.), and / or the like that interact with user devices 104A-104N. Data and / or information communicated between user devices 104A- 104N and third-party systems 118 may be collected and used to generate a user model and / or behavioral model for user devices 104A-104N and / or users of user devices 104A- 104N.

[0023] According to some aspects of this disclosure, computing device 110 may include a server, a cloud-based compute resource, an entity-controlled device, or any other device capable of communicating with user devices 104A-104N, third-party systems 118, and / or any other device / component of system 100, either described or (un)shown. Although shown as a single device, according to some aspects of this disclosure, computing device 110 may be part of a computing system and / or infrastructure, and / or may represent a plurality of computing devices. For example, computing device 110 may represent a plurality of computing devices in communication with user devices 104A-104N, third- party systems 118, and / or any other device / component of system 100.

[0024] According to some aspects of this disclosure, computing device 110 may include communication module 112 that facilitates and / or enables communication with network102 (e.g., devices, components, and / or systems of network 102, etc.), user devices 104A- 104N, third-party systems 118, and / or any other device / component of system 100. For example, communication module 112 may include hardware and / or software to facilitate communication. According to some aspects of this disclosure, communication module 112 may include one or more of a modem, transceiver (e.g., wireless transceiver, etc.), digital-to-analog converter, analog-to-digital converter, encoder, decoder, modulator, demodulator, tuner (e.g., QAM tuner, QPSK tuner), and / or the like. According to some aspects of this disclosure, communication module 112 may include any hardware and / or software necessary to facilitate communication.

[0025] According to some aspects of this disclosure, computing device 110 may include an interface module 114. According to some aspects of this disclosure, interface module 114 enables a user to interact with computing device 110, network 102, user device 104A-104N, third-party systems 118, and / or any other device / component of system 100. Interface module 114 may include any interface for presenting and / or receiving information to / from a user.

[0026] According to some aspects of this disclosure, interface module 114 enables a user to view and / or interact with user data, applications, web pages, and / or user interfaces. According to some aspects, interface module 114 may include a web browser (e.g., Internet Explorer®, Mozilla Firefox®, Google Chrome®, Safari®, or the like). According to some aspects, interface module 114 may include one or more applications including credit management applications, financial applications, e-commerce applications, identity management applications, and / or the like. According to some aspects, interface module 114 may request, receive, or query various files from a local source and / or a remote source, such as user devices 104A-104N, third-party systems 118, and / or any other device / component of system 100. For example, interface module 114 may be used to provide constraints and / or counterfactual data relating to credit approval transactions, product purchase transactions, communication-based transactions, identity security and management, and / or the like, used to build, analyze, and / or modify user models and / or behavioral models.

[0027] According to some aspects, interface module 114 may include one or more input devices and / or components, for example, such as a keyboard, a pointing device (e.g., a computer mouse, remote control), a microphone, a joystick, a tactile input device (e.g.,touch screen, gloves, etc.), and / or the like. According to some aspects, interaction with the input devices and / or components may enable a user to interact with a user interface generated and / or displayed by the interface module 112 to provide constraints and / or counterfactual data relating to credit approval transactions, product purchase transactions, communication-based transactions, identity security and management, and / or the like, used to build, analyze, and / or modify user models and / or behavioral models.

[0028] According to some aspects of this disclosure, to facilitate counterfactual analysis of user models for prescriptive output, computing device 110 may include a counterfactual module 116. Counterfactual module 116 may generate user models (e.g., functional representations of user online activity, social media activity, e-commerce activity, etc.) and / or behavioral models (e.g., functional representations of user credit- related activity, account balances, transaction history, etc.) for users of user devices 104A-104N and / or user devices 104A-104N. According to some aspects of this disclosure, counterfactual module 116 may receive, request, and / or access user information from user devices 104A-104N and / or third-party services 118 to generate user / behavioral models.

[0029] According to some aspects of this disclosure, user / behavioral models may be logical, mathematical, and / or data constructs that represent relationships between different variables or features that influence the status of a digital identity. User / behavioral models capture complex identity usage and behavioral patterns using mathematical functions, algorithms, and / or computational models. For example, according to some aspects of this disclosure, user / behavioral models may include linear models, non-linear models, stochastic models, time-series models, state-space models, agent-based models, and / or the like. User / behavioral models may include both mutable and immutable features (e.g., status influence elements, etc.).

[0030] According to some aspects of this disclosure, counterfactual module 116 may utilize a trained predictive model to identify mutable and immutable features from user data and / or behavioral data. For example, counterfactual module 116 may collect data on a variety of user behaviors and influencers from user devices 104A-104N and third-party systems 118. This can include immutable factors like age, gender, nationality, etc., as well as mutable factors like recent purchase history, location, interactions with various applications, and / or the like. The data collected may be cleaned and / or normalized byaddressing / substituting any missing values, encoding categorical variables, scaling numerical variables, and / or the like.

[0031] According to some aspects of this disclosure, counterfactual module 116 may identify the most relevant factors / features that could influence user identity and / or user behavior. For example, counterfactual module 116 may use correlation matrices, mutual information, wrapper methods, and / or the like to select a subset of features for training the predictive model(s). According to some aspects, counterfactual module 116 may generate new features (e.g., via an iteration of terms between features, etc.) that might capture the relationships between mutable and immutable factors more effectively. Counterfactual module 116 may use one or more methods including, but not limited to, decision tree analysis, random forest analysis, gradient boosting, and / or the like on a training dataset to interpret feature importance. When training and evaluating the predictive model, counterfactual module 116 may use cross-validation to evaluate how well the predictive model generalizes to any unseen data. Immutable features may be identified by identifying those features that show consistent importance across multiple runs and different subsets of the training dataset. Mutable features may be identified by identifying those features that show fluctuating levels of importance over time or across different subsets of the training dataset. As described herein, mutable features are those used by counterfactual module 116 for counterfactual analysis of user models for prescriptive output.

[0032] According to some aspects, counterfactual module 116 may generate guidance and / or instructive data for a given scenario based on relationships between user / behavioral models identified independently from the identification of counterfactual s used to generate the guidance and / or instructive data. For example, for a target user of user device 104A (e.g., a user with a digital identity status that falls below a threshold or intended status, etc.), user data and / or user profile-level data collected from third-party service 118 and user device 104 A (e.g., analytic service providers, entity data repositories, telemetry data, etc.) may be used to generate a behavioral model that is paired with the behavioral model of another user, such as a user of user device 104N, with digital identity status influencing elements that best match the target user of user device 104 A. The paired user of user device 104N may be a user with a digital identity that satisfies a particular threshold or meets a defined goal. Status-influencing elements fromthe behavioral model of the paired user of user device 104N may be used as counterf actuals for modifying the behavioral model of the target user of user device 104 A. The modified behavioral model may be used to generate guidance for improving, modifying, and / or altering the status of the digital identity of the target user of user device 104 A.

[0033] According to some aspects of this disclosure, an algorithm that counterfactual module 116 may utilize for counterfactual analysis of user models for prescriptive output by initially identifying a user (or user device) that satisfies a given threshold and is most similar to a target user (or user device) is provided in Algorithm 1 below. According to some aspects, Algorithm 1 is just an example and other algorithms may be used for facilitating demographic predictions for content items.Algorithm 1Steps:1. Identify a qualifying / quantifying threshold.2. Identify a plurality of users with attributes that satisfy (e.g., score at or above, etc.) the qualifying / quantifying threshold.3. Select a target user based on a trigger condition (e.g., an indication that the target user fails to meet the qualifying / quantifying threshold, etc.)4. Transform features (e.g., digital identity status-influencing elements, etc.) of user behavior for the plurality of users with attributes that satisfy the qualifying / quantifying threshold and the target user into a transformed state. Data preprocessing (e.g., binning, discretization, etc.) is used to transform raw feature values from user / behavioral models for the plurality of users and the target user into bins or intervals. For example, continuous or numerical features are converted into a set of intervals (or "bins") to simplify the data into a model analytical format.5. Identify features eligible for reasonable correction.6. Calculate the pairwise similarity between features of the target user and a user of the plurality of users with attributes that satisfy the qualifying / quantifying threshold.7. For iterate = 1 to N (where N = any number of the plurality of users with attributes that satisfy the qualifying / quantifying threshold), retrieve the most similar digitalidentity status-influencing elements eligible for reasonable correction identified from pairwise similarities.8. Endfor.

[0034] According to some aspects of this disclosure, Algorithm 1 may be represented as an example Equation 1, provided below:Equation 1D = ^=1 / mk- pk

[0035] As used in Equation 1, the variable k represents the number of digital identity status-influencing elements identified as eligible for reasonable correction. For example, for a user with a digital identity status (e.g., a low credit score, etc.) that causes the user to be denied for a loan or similar transaction, an amount of status-influencing elements or characteristics (e.g., number of accounts in collection, credit card utilization, total past due balances, number of trades currently 30-days or more past due, etc.) indicated by a user / behavioral profile of the user that could potentially be adjusted or optimized in some way may be represented by the variable k. As another example, for a user with a digital identity status that has been compromised and / or subjected to identity fraud, an amount of status-influencing elements or characteristics (e.g., type and encryption used for passwords / credentials, protect! on / security software installed on context-related devices, identity monitoring / correction services initiated, etc.) indicated by a user / behavioral profile of the user that could potentially be adjusted or optimized in some way may be represented by the variable k. As used in Equation 1, the variable X represents the combination of transformed values (e.g., categorized as bins, intervals, etc.) for user / behavioral model features (e.g., status-influencing elements, etc.) that apply to a target user (e.g., a user of user device 104A, user device 104A, etc.). As used in Equation 1, the variable K represents transformed values (e.g., categorized as bins, intervals, etc.) for user / behavioral model features (e.g., status-influencing elements, etc.) that apply to different users (e.g., user of user device(s) 104N, user device(s) 104N, etc.) that satisfy a given threshold (e.g., have a credit score above a set level, have not been subject to or recovered from identity theft / fraud, etc.).

[0036] As used in Equation 1, the variable represents the assigned weights used for counterfactual analysis. According to some aspects of this disclosure, assigned weights may be predetermined based on domain-specific goals, knowledge, and / or the like.According to some aspects of this disclosure, assigned weights may be predetermined based on statistical methods including, but not limited to, linear regression to output coefficient values that may be interpreted as weights showing the relative importance of each factor in predicting the outcome. According to some aspects of this disclosure, assigned weights may be predetermined based on a predictive model trained to identify weights for counterfactual analysis based on a type of transaction and / or output goal. According to some aspects of this disclosure, assigned weights may be predetermined based on propensity score matching where status-influencing elements are weighed so that they are comparable in terms of the distribution of observed covariates, based on a request for an optimized behavior model for the type of transaction that indicates the respective weighted values, and / or based on counterfactual information extracted from a behavior model of a model user (e.g., a user with a digital identity that satisfies a status threshold, etc.). According to some aspects of this disclosure, any method of technique may be used to identify and / or determine assigned weights. According to some aspects of this disclosure, any assigned weights may be adjusted and refined.

[0037] As shown in Equation 1, the resulting value D may be interpreted as a summation of the differences in transformed feature values (or binned values) between the target user (e.g., a user of user device 104 A, user device 104 A, etc.) and the average or combined behavior of the users that satisfy the given threshold. The resulting value D quantifies the difference (or degree of similarity) between the target user and the users that satisfy the given threshold with regard to status-influencing elements or characteristics indicated by respective user / behavioral models. An advantage of the result of Equation 1, particularly for improving the technological fields of transaction management, digital identity management, and / or e-commerce is that it allows for guidance instructions (e.g., counterfactual-based credit score improvement guidance, compromised identity recovery / repair guidance, etc.) with deterministic and actionable insights into optimizing user interactions and personalizing user experience to be generated. According to some aspects of this disclosure, as described herein, counterfactual analysis of user models for prescriptive output may include, but is not limited to, Equation 1. According to some aspects of this disclosure, other formulas and / or algorithms may be used for counterfactual analysis of user models for prescriptive output.

[0038] FIG. 2 shows an example a similarity graph 200 for a graphical depiction of an analytical process performed by counterfactual module 116 to identify users / user devices with similar user / behavioral models as a target user to that counterfactual analysis may be performed to provide prescriptive information to the target user for improving, modifying, and / or altering the status of a digital identity for the target user. Similarity graph 200 uses inverted scales and may be derived based on a scenario where a target user of user device 104A is unable to complete a transaction (e.g., being approved for a loan, mortgage, purchase, etc.) due to the status of a digital identity (e.g., a credit score that falls below a threshold, etc.).

[0039] In similarity graph 200 it is assumed a user / behavioral model related to a credit score has two status-influencing elements that may be plausibly modified within a given timeframe to change the status of the digital identity of a target user 202 represented by similarity graph 200. Target user 202 is compared to user 204, user 206, and user 208, each represented in similarity graph 200 with digital identity statuses that satisfy a digital identity status threshold 210 and enable completion of the transaction (e.g., being approved for a loan, mortgage, purchase, etc.).

[0040] Counterfactual module 116 may calculate and / or identify pairwise distances between target user 202 and users 204-208. The shortest distance between the target user 202 and users 204-208 may indicate the counterfactual user with a user / behavioral model with status-influencing elements that may be used to modify the user / behavioral model of the target user 202. As shown in similarity graph 200, user 206 is indicated as a counterfactual user based on the shortest path between user 206 and target user 202. Instructions for modifying the status of the digital identity for target user 202 to satisfy the digital identity status threshold may be generated from a user / behavioral model modified according to mutable status influencing elements of the user / behavioral model of user 206.

[0041] Modifying the user / behavioral model of target user 202 according to the target user according to mutable status influencing elements of the user / behavioral model of user 206 may include replacing at least one status influence element of the user / behavioral model of target user 202 with at least one mutable status influencing elements of the user / behavioral model of user 206. According to some aspects of this disclosure, modifying the user / behavioral model of target user 202 according to themutable status influencing elements of the user / behavioral model of user 206 may include time-shifting an action indicated by at least one status influence element of the user / behavioral model of target user 202 according to timing associated with an action indicated by at least one mutable status influencing elements of the user / behavioral model of user 206. According to some aspects of this disclosure, counterfactual module 116 may use any method to modify the behavior model of a target user according to status influence elements indicated by a behavior model of another user.

[0042] Instructions for modifying the status of the digital identity for target user 202 may include specific, deterministic information describing how to modify the status of the digital identity for target user 202 to satisfy the digital identity status threshold based on empirical data identified from the user / behavioral model of user 206.

[0043] FIG. 3 is a flowchart for a method 300 for counterfactual analysis of user models for prescriptive output, according to aspects of this disclosure. Method 300 can be performed by processing logic that can comprise hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, etc.), software (e.g., instructions executing on a processing device), or a combination thereof. It is to be appreciated that not all steps may be needed to perform the disclosure provided herein. Further, some of the steps may be performed simultaneously, or in a different order than shown in FIG. 3, as will be understood by a person of ordinary skill in the art.

[0044] Method 300 shall be described with reference to FIGs. 1-2. However, method 300 is not limited to those figures or related aspects.

[0045] In 310, computing device 110 identifies a plurality of status influence elements indicated by a behavior model of a target user. For example, computing device 110 may identify the plurality of status influence elements indicated by the behavior model of the target user based on an indication that a status of a digital identity for the target user is less than a status threshold for digital identities eligible for a transaction.

[0046] According to some aspects of this disclosure, the plurality of status influence elements indicated by the behavior model of the target user may be selected as a subset of a larger plurality of status influence elements indicated by the behavior model of the target user based on an indication that plurality of status influence elements are mutable within a timeframe. According to some aspects of this disclosure, the indication that the plurality of status influence elements are mutable within the timeframe may be output bya predictive model trained to evaluate the mutability of status influence elements associated with behavioral models

[0047] In 320, computing device 110 identifies a respective plurality of status influence elements indicated by a respective behavior model for each user of a plurality of users with respective digital identities that satisfy the status threshold.

[0048] In 330, computing device 110 calculates a respective distance between the target user and each user of the plurality of users with respective digital identities that satisfy the status threshold. For example, computing device 110 may calculate the respective distance between the target user and each user of the plurality of users with respective digital identities that satisfy the status threshold based on respective weighted values that represent a degree of influence on eligibility for the transaction assigned to the respective plurality of status influence elements indicated by the respective behavior model for each user of the plurality of users and the plurality of status influence elements indicated by the behavior model of the target user.

[0049] According to some aspects of this disclosure, the respective weighted values assigned to the respective plurality of status influence elements indicated by the respective behavior model for each user of the plurality of users and the plurality of status influence elements indicated by the behavior model of the target user are determined from at least one of: a predictive model trained to identify weights for counterfactual analysis based on a type of the transaction, a request for an optimized behavior model for the type of the transaction that indicates the respective weighted values, or based on counterfactual information extracted from a behavior model for another user with a digital identity that satisfies the status threshold.

[0050] In 340, computing device 110 modifies the behavior model of the target user. For example, computing device 110 may modify the behavior model of the target user based on the respective distance between the target user and a first user of the plurality of users being the shortest calculated distance. Computing device 110 may modify the behavior model of the target user according to at least one of the respective plurality of status influence elements indicated by the respective behavior model for the first user.

[0051] According to some aspects of this disclosure, modifying the behavior model of the target user may include replacing at least one status influence element of the plurality of status influence elements indicated by the behavior model of the target user with at leastone of the respective plurality of status influence elements indicated by the respective behavior model for the first user. According to some aspects of this disclosure, modifying the behavior model of the target user may include time-shifting an action indicated by at least one status influence element of the plurality of status influence elements indicated by the behavior model of the target user according to timing associated with an action indicated by at least one of the respective plurality of status influence elements indicated by the respective behavior model for the first user. According to some aspects of this disclosure, computing device 110 may use any method to modify the behavior model of the target user according to at least one of the respective plurality of status influence elements indicated by the respective behavior model for the first user.

[0052] In 350, computing device 110 generates instructions for modifying the status of the digital identity for the target user to satisfy the status threshold for digital identities eligible for the transaction. For example, computing device 110 may generate the instructions for modifying the status of the digital identity for the target user based on the modified behavior model.

[0053] Various embodiments may be implemented, for example, using one or more well- known computer systems, such as computer system 400 shown in FIG. 4. One or more computer systems 400 may be used, for example, to implement any of the embodiments discussed herein, as well as combinations and sub-combinations thereof.

[0054] Computer system 400 may include one or more processors (also called central processing units, or CPUs), such as a processor 404. Processor 404 may be connected to a communication infrastructure or bus 406.

[0055] Computer system 400 may also include user input / output device(s) 403, such as monitors, keyboards, pointing devices, etc., which may communicate with communication infrastructure 406 through user input / output interface(s) 402.

[0056] One or more of processors 404 may be a graphics processing unit (GPU). In an embodiment, a GPU may be a processor that is a specialized electronic circuit designed to process mathematically intensive applications. The GPU may have a parallel structure that is efficient for parallel processing of large blocks of data, such as mathematically intensive data common to computer graphics applications, images, videos, etc.

[0057] Computer system 400 may also include a main or primary memory 408, such as random access memory (RAM). Main memory 408 may include one or more levels ofcache. Main memory 408 may have stored therein control logic (i.e., computer software) and / or data.

[0058] Computer system 400 may also include one or more secondary storage devices or memory 410. Secondary memory 410 may include, for example, a hard disk drive 412 and / or a removable storage device or drive 414. Removable storage drive 414 may be a floppy disk drive, a magnetic tape drive, a compact disk drive, an optical storage device, tape backup device, and / or any other storage device / drive.

[0059] Removable storage drive 414 may interact with a removable storage unit 418. Removable storage unit 418 may include a computer usable or readable storage device having stored thereon computer software (control logic) and / or data. Removable storage unit 418 may be a floppy disk, magnetic tape, compact disk, DVD, optical storage disk, and / any other computer data storage device. Removable storage drive 414 may read from and / or write to removable storage unit 418.

[0060] Secondary memory 410 may include other means, devices, components, instrumentalities or other approaches for allowing computer programs and / or other instructions and / or data to be accessed by computer system 400. Such means, devices, components, instrumentalities or other approaches may include, for example, a removable storage unit 422 and an interface 420. Examples of the removable storage unit 422 and the interface 420 may include a program cartridge and cartridge interface (such as that found in video game devices), a removable memory chip (such as an EPROM or PROM) and associated socket, a memory stick and USB port, a memory card and associated memory card slot, and / or any other removable storage unit and associated interface.

[0061] Computer system 400 may further include a communication or network interface 424. Communication interface 424 may enable computer system 400 to communicate and interact with any combination of external devices, external networks, external entities, etc. (individually and collectively referenced by reference number 428). For example, communication interface 424 may allow computer system 400 to communicate with external or remote devices 428 over communications path 426, which may be wired and / or wireless (or a combination thereof), and which may include any combination of LANs, WANs, the Internet, etc. Control logic and / or data may be transmitted to and from computer system 400 via communication path 426.

[0062] Computer system 400 may also be any of a personal digital assistant (PDA), desktop workstation, laptop or notebook computer, netbook, tablet, smart phone, smart watch or other wearable, appliance, part of the Internet-of-Things, and / or embedded system, to name a few non-limiting examples, or any combination thereof.

[0063] Computer system 400 may be a client or server, accessing or hosting any applications and / or data through any delivery paradigm, including but not limited to remote or distributed cloud computing solutions; local or on-premises software (“onpremise” cloud-based solutions); “as a service” models (e.g., content as a service (CaaS), digital content as a service (DCaaS), software as a service (SaaS), managed software as a service (MSaaS), platform as a service (PaaS), desktop as a service (DaaS), framework as a service (FaaS), backend as a service (BaaS), mobile backend as a service (MBaaS), infrastructure as a service (laaS), etc.); and / or a hybrid model including any combination of the foregoing examples or other services or delivery paradigms.

[0064] Any applicable data structures, file formats, and schemas in computer system 400 may be derived from standards including but not limited to JavaScript Object Notation (JSON), Extensible Markup Language (XML), Yet Another Markup Language (YAML), Extensible Hypertext Markup Language (XHTML), Wireless Markup Language (WML), MessagePack, XML User Interface Language (XUL), or any other functionally similar representations alone or in combination. Alternatively, proprietary data structures, formats or schemas may be used, either exclusively or in combination with known or open standards.

[0065] In some embodiments, a tangible, non-transitory apparatus or article of manufacture comprising a tangible, non-transitory computer useable or readable medium having control logic (software) stored thereon may also be referred to herein as a computer program product or program storage device. This includes, but is not limited to, computer system 400, main memory 408, secondary memory 410, and removable storage units 418 and 422, as well as tangible articles of manufacture embodying any combination of the foregoing. Such control logic, when executed by one or more data processing devices (such as computer system 400), may cause such data processing devices to operate as described herein.

[0066] Based on the teachings contained in this disclosure, it will be apparent to persons skilled in the relevant art(s) how to make and use embodiments of this disclosure usingdata processing devices, computer systems, and / or computer architectures other than that shown in FIG. 4. In particular, embodiments can operate with software, hardware, and / or operating system implementations other than those described herein.

[0067] It is to be appreciated that the Detailed Description section, and not any other section, is intended to be used to interpret the claims. Other sections can set forth one or more but not all exemplary embodiments as contemplated by the inventor(s), and thus, are not intended to limit this disclosure or the appended claims in any way.

[0068] While this disclosure describes exemplary embodiments for exemplary fields and applications, it should be understood that the disclosure is not limited thereto. Other embodiments and modifications thereto are possible and are within the scope and spirit of this disclosure. For example, and without limiting the generality of this paragraph, embodiments are not limited to the software, hardware, firmware, and / or entities illustrated in the figures and / or described herein. Further, embodiments (whether or not explicitly described herein) have significant utility to fields and applications beyond the examples described herein.

[0069] Embodiments have been described herein with the aid of functional building blocks illustrating the implementation of specified functions and relationships thereof. The boundaries of these functional building blocks have been arbitrarily defined herein for the convenience of the description. Alternate boundaries can be defined as long as the specified functions and relationships (or equivalents thereof) are appropriately performed. Also, alternative embodiments can perform functional blocks, steps, operations, methods, etc. using orderings different than those described herein.

[0070] References herein to “one embodiment,” “an embodiment,” “an example embodiment,” or similar phrases, indicate that the embodiment described can include a particular feature, structure, or characteristic, but every embodiment can not necessarily include the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it would be within the knowledge of persons skilled in the relevant art(s) to incorporate such feature, structure, or characteristic into other embodiments whether or not explicitly mentioned or described herein. Additionally, some embodiments can be described using the expressions “coupled” and “connected” along with their derivatives. These terms are not necessarilyintended as synonyms for each other. For example, some embodiments can be described using the terms “connected” and / or “coupled” to indicate that two or more elements are in direct physical or electrical contact with each other. The term “coupled,” however, can also mean that two or more elements are not in direct contact with each other, but yet still cooperate or interact with each other.

[0071] The breadth and scope of this disclosure should not be limited by any of the above-described exemplary embodiments, but should be defined only in accordance with the following claims and their equivalents.

Claims

WHAT IS CLAIMED IS:

1. A method comprising: identifying a plurality of status influence elements indicated by a behavior model of a target user based on an indication that a status of a digital identity for the target user is less than a status threshold for digital identities eligible for a transaction; identifying a respective plurality of status influence elements indicated by a respective behavior model for each user of a plurality of users with respective digital identities that satisfy the status threshold; calculating, based on respective weighted values that represent a degree of influence on eligibility for the transaction assigned to the respective plurality of status influence elements indicated by the respective behavior model for each user of the plurality of users and the plurality of status influence elements indicated by the behavior model of the target user, a respective distance between the target user and each user of the plurality of users with respective digital identities that satisfy the status threshold; modifying, based on the respective distance between the target user and a first user of the plurality of users being the shortest calculated distance, the behavior model of the target user based on at least one of the respective plurality of status influence elements indicated by the respective behavior model for the first user; and generating, based on the modified behavior model, instructions for modifying the status of the digital identity for the target user to satisfy the status threshold for digital identities eligible for the transaction.

2. The method of claim 1, further comprising sending the instructions for modifying the status of the digital identity for the target user to a user device associated with the target user.

3. The method of claim 1, wherein the plurality of status influence elements indicated by the behavior model of the target user are selected as a subset of a larger plurality of status influence elements indicated by the behavior model of the target user based on an indication that plurality of status influence elements are mutable within a timeframe.

4. The method of claim 3, wherein the indication that the plurality of status influence elements are mutable within the timeframe is output from a predictive model trained to evaluate the mutability of status influence elements associated with behavioral models.

5. The method of claim 1, wherein the respective weighted values assigned to the respective plurality of status influence elements indicated by the respective behavior model for each user of the plurality of users and the plurality of status influence elements indicated by the behavior model of the target user are determined from at least one of: a predictive model trained to identify weights for counterfactual analysis based on a type of the transaction, a request for an optimized behavior model for the type of the transaction that indicates the respective weighted values, or based on counterfactual information extracted from a behavior model for another user with a digital identity that satisfies the status threshold.

6. The method of claim 1, wherein the modifying the behavior model of the target user further comprises at least one of: replacing at least one status influence element of the plurality of status influence elements indicated by the behavior model of the target user with at least one of the respective plurality of status influence elements indicated by the respective behavior model for the first user, or time-shifting an action indicated by at least one status influence element of the plurality of status influence elements indicated by the behavior model of the target user according to timing associated with an action indicated by at least one of the respective plurality of status influence elements indicated by the respective behavior model for the first user.

7. The method of claim 1, wherein the transaction comprises at least one of: qualifying for a financial object, accessing a device, or accessing a resource.

8. A system, comprising: a memory; and at least one processor coupled to the memory and configured to perform operations comprising:identifying a plurality of status influence elements indicated by a behavior model of a target user based on an indication that a status of a digital identity for the target user is less than a status threshold for digital identities eligible for a transaction; identifying a respective plurality of status influence elements indicated by a respective behavior model for each user of a plurality of users with respective digital identities that satisfy the status threshold; calculating, based on respective weighted values that represent a degree of influence on eligibility for the transaction assigned to the respective plurality of status influence elements indicated by the respective behavior model for each user of the plurality of users and the plurality of status influence elements indicated by the behavior model of the target user, a respective distance between the target user and each user of the plurality of users with respective digital identities that satisfy the status threshold; modifying, based on the respective distance between the target user and a first user of the plurality of users being the shortest calculated distance, the behavior model of the target user based on at least one of the respective plurality of status influence elements indicated by the respective behavior model for the first user; and generating, based on the modified behavior model, instructions for modifying the status of the digital identity for the target user to satisfy the status threshold for digital identities eligible for the transaction.

9. The system of claim 8, the operations further comprising sending the instructions for modifying the status of the digital identity for the target user to a user device associated with the target user.

10. The system of claim 8, wherein the plurality of status influence elements indicated by the behavior model of the target user are selected as a subset of a larger plurality of status influence elements indicated by the behavior model of the target user based on an indication that plurality of status influence elements are mutable within a timeframe.

11. The system of claim 10, wherein the indication that the plurality of status influence elements are mutable within the timeframe is output from a predictive model trained to evaluate the mutability of status influence elements associated with behavioral models.

12. The system of claim 8, wherein the respective weighted values assigned to the respective plurality of status influence elements indicated by the respective behavior model for each user of the plurality of users and the plurality of status influence elements indicated by the behavior model of the target user are determined from at least one of: a predictive model trained to identify weights for counterfactual analysis based on a type of the transaction, a request for an optimized behavior model for the type of the transaction that indicates the respective weighted values, or based on counterfactual information extracted from a behavior model for another user with a digital identity that satisfies the status threshold.

13. The system of claim 8, wherein the modifying the behavior model of the target user further comprises at least one of: replacing at least one status influence element of the plurality of status influence elements indicated by the behavior model of the target user with at least one of the respective plurality of status influence elements indicated by the respective behavior model for the first user, or time-shifting an action indicated by at least one status influence element of the plurality of status influence elements indicated by the behavior model of the target user according to timing associated with an action indicated by at least one of the respective plurality of status influence elements indicated by the respective behavior model for the first user.

14. The system of claim 8, wherein the transaction comprises at least one of: qualifying for a financial object, accessing a device, or accessing a resource.

15. A non-transitory computer-readable medium having instructions stored thereon that, when executed by at least one computing device, causes the at least one computing device to perform operations comprising: identifying a plurality of status influence elements indicated by a behavior model of a target user based on an indication that a status of a digital identity for the target user is less than a status threshold for digital identities eligible for a transaction;identifying a respective plurality of status influence elements indicated by a respective behavior model for each user of a plurality of users with respective digital identities that satisfy the status threshold; calculating, based on respective weighted values that represent a degree of influence on eligibility for the transaction assigned to the respective plurality of status influence elements indicated by the respective behavior model for each user of the plurality of users and the plurality of status influence elements indicated by the behavior model of the target user, a respective distance between the target user and each user of the plurality of users with respective digital identities that satisfy the status threshold; modifying, based on the respective distance between the target user and a first user of the plurality of users being the shortest calculated distance, the behavior model of the target user based on at least one of the respective plurality of status influence elements indicated by the respective behavior model for the first user; and generating, based on the modified behavior model, instructions for modifying the status of the digital identity for the target user to satisfy the status threshold for digital identities eligible for the transaction.

16. The non-transitory computer-readable medium of claim 15, the operations further comprising sending the instructions for modifying the status of the digital identity for the target user to a user device associated with the target user.

17. The non-transitory computer-readable medium of claim 15, wherein the plurality of status influence elements indicated by the behavior model of the target user are selected as a subset of a larger plurality of status influence elements indicated by the behavior model of the target user based on an indication that plurality of status influence elements are mutable within a timeframe.

18. The non-transitory computer-readable medium of claim 17, wherein the indication that the plurality of status influence elements are mutable within the timeframe is output from a predictive model trained to evaluate the mutability of status influence elements associated with behavioral models.

19. The non-transitory computer-readable medium of claim 15, wherein the respective weighted values assigned to the respective plurality of status influence elements indicated by the respective behavior model for each user of the plurality of users and the plurality of status influence elements indicated by the behavior model of the target user are determined from at least one of: a predictive model trained to identify weights for counterfactual analysis based on a type of the transaction, a request for an optimized behavior model for the type of the transaction that indicates the respective weighted values, or based on counterfactual information extracted from a behavior model for another user with a digital identity that satisfies the status threshold.

20. The non-transitory computer-readable medium of claim 15, wherein the modifying the behavior model of the target user further comprises at least one of: replacing at least one status influence element of the plurality of status influence elements indicated by the behavior model of the target user with at least one of the respective plurality of status influence elements indicated by the respective behavior model for the first user, or time-shifting an action indicated by at least one status influence element of the plurality of status influence elements indicated by the behavior model of the target user according to timing associated with an action indicated by at least one of the respective plurality of status influence elements indicated by the respective behavior model for the first user.

Images