Artificial intelligence model for facilitating reversed interaction

Abstract

A system can be used to control reversal of an interaction. The system can receive a request to reverse a previously executed interaction. The request can include data relating to a previously executed interaction that may be associated with a. target entity. The system can generate, using an artificial intelligence model that includes a generative artificial intelligence model, risk signals based on the request and the data. The system can determine, based on the risk signals, a risk indicator that represents a. likelihood that the request may be illegitimate. The system can provide a responsive message to control reversal of the previously executed interaction and based on the risk indicator.

Description

Technical Field

[0001] The present disclosure relates generally to risk assessment and interaction control. More specifically, but not by way of limitation, this disclosure relates to using artificial intelligence techniques to determine whether to facilitate reversing a previously conducted interaction. Background

[0002] Various interactions are performed frequently through an interactive computing environment such as a website, a user interface, etc. The interactions may involve transferring resources for, or otherwise based on, content or goods that can be provided via the interactive computing environment. In some cases, a providing entity that provides the content or goods can allow an initiating entity to return the content or the goods, or may otherwise allow the initiating entity7 to reverse a particular interaction to provide the content or the goods back to the providing entity in exchange for the resources initially provided for the content or the goods. Determining whether a request to reverse the particular interaction is legitimate can be difficult. Summary

[0003] Various aspects of the present disclosure provide systems and methods for controlling reversal of an interaction. The system can include a processor and a non-transitory computer-readable medium that includes instructions that are executable by the processor to cause the processor to perform various operations. The system can receive a request to reverse a previously executed interaction. The request can include data relating to a previously executed interaction that may be associated with a target entity. The system can generate, using an artificial intelligence model that can include a generative artificial intelligence model, one or more risk signals based on the request and the data. The system can determine, based on the one or more risk signals, a risk indicator that can represent a likelihood that the request may be illegitimate. The system can provide a responsive message to control reversal of the previously executed interaction and based on the risk indicator.

[0004] In other aspects, a method can be used to control reversal of an interaction. The method can include receiving, by a computing system, a request to reverse a previously executed interaction. The request can include data relating to a previously executed interaction that may be associated with a target emit}'. The method can include generating, by the computing system and by using an artificial intelligence model that can include a generative artificial intelligence model, one or more risk signals based on the request and the data. The method can include determining, by the computing system and based on the one or more risk signals, a risk indicator that can represent a likelihood that the request may be illegitimate. The method can include providing, by the computing system, a responsive message to control reversal of the previously executed interaction based on the risk indicator.

[0005] In other aspects, a non-transitory computer-readable medium can include instructions that are executable by a processing device for causing the processing device to perform various operations. The operations can include receiving a request to reverse a previously executed interaction. The request can include data relating to a previously executed interaction that may be associated with a target entity. The operations can include generating, using an artificial intelligence model that can include a generative artificial intelligence model, one or more risk signals based on the request and the data. The operations can include determining, based on the one or more risk signals, a risk indicator that can represent a likelihood that the request may be illegitimate. The operations can include providing a responsive message to control reversal of the previously executed interaction based on the risk indicator.

[0006] This summary is not intended to identify key or essential filatures of the claimed subject matter, nor is it intended to be used in isolation to determine the scope of the claimed subject matter. The subject matter should be understood by reference to appropriate portions of the entire specification, any or all drawings, and each claim.

[0007] The foregoing, together with other features and examples, will become more apparent upon referring to the following specification, claims, and accompanying drawings. Brief Description of Drawings

[0008] FIG. 1 is a block diagram illustrating an example of a computing environment in which artificial intelligence techniques can be used to determine whether a request for reversing an interaction is legitimate according to certain aspects of the present disclosure.

[0009] FIG. 2 is a flowchart illustrating an example of a process for using artificial intelligence techniques to determine whether a request for reversing an interaction is legitimate according to certain aspects of the present disclosure.

[0010] FIG, 3 is a flowchart illustrating an example of a process for determining a risk assessment indicator using artificial intelligence techniques according to certain aspects of the present disclosure.

[0011] FIG. 4 is a block diagram of an example of an architecture of an artificial intelligence-based model that can be used to determine whether a request for reversing an interaction is legitimate according to certain aspects of the present disclosure.

[0012] FIG. 5 is a block diagram depicting an example of a computing system suitable for implementing aspects of the techniques and technologies presented herein. Detailed Description

[0013] Certain aspects described herein for using an artificial intelligence model to determine whether to facilitate reversing a previously executed interaction can address one or more of the foregoing issues. For example, the artificial intelligence model, which may include one or more supervised machine-learning models, one or more unsupervised machine-learning models, one or more generative artificial intelligence models, or any combination thereof, can be used to determine one or more risk signals associated with a request to reverse a previously executed interaction. In some examples, the one or more risk signals may be or include one or more scores that indicate a likelihood that one or more parameters of the request are legitimate or not legitimate. The one or more risk signals can be used to determine a risk indicator that may be a score that indicates a likelihood of the request being fraudulent or otherwise being associated with malicious behavior. The risk indicator can be used to facilitate a decision regarding whether to allow, challenge, or deny the request. For example, the risk indicator can be included in a responsive message to a query' for evaluating the request in which the responsive message can be used to allow, challenge, or deny the request. In another example, the risk indicator can be used as an input into an algorithm that controls whether to allow, challenge, or deny the request.

[0014] Reversing an interaction can involve a receiving entity, or a target entity, returning content or goods to a providing entity and the providing entity returning resources provided by the receiving entity to the receiving entity7. In some examples, reversing the interaction can involve an interaction between the receiving entity and the providing entity that is opposite a previously executed interaction between the receiving entity and the providing entity. The providing entity may have a predetermined algorithm, heuristic, or policy for initiating or otherwise allowing the reverse interaction to occur. In some examples, the predetermined algorithm, heuristic, or policy may involve challenging at least a portion of requests received to reverse a previously executed interaction. But, determining which requests to challenge or otherwise deny may be difficult due to a volume of the requests, due to lack of data associated with the requests, due to a lack of computational capacity, or the like.

[0015] In some examples, a receiving entity may initiate an interaction with a providing entity in which the receiving entity provides resources to the providing entity in exchange for content or goods from the providing entity. The interaction may be legitimate. For example, the receiving entity may use legitimate authentication credentials, such as to log on to an interactive computing environment, to provide authorization to transfer the resources, and the like, to initiate and cany out the interaction. Additionally or alternatively, the interaction may be successful such that the providing entity may successfully provide the content or the goods to the receiving entity-subsequent to receiving the resources. But, the receiving entity7 may, for example at a later time, request a reverse interaction that may be intended to reverse the previously executed interaction. In some examples, the request for initiating the reverse interaction may be legitimate: a reverse interaction policy of the providing entity may be properly followed by the receiving entity, the content or goods may be defective, the receiving entity may intend to return the content or goods without malicious intent, etc. In other examples, however, the request to initiate the reverse interaction may be associated with malicious intent. For example, the receiving entity may be attempting to receive the resources transferred for the content or the goods without intending to return the content or the goods to the providing entity. A large number of requests to initiate reverse interactions may be legitimate, and identifying the malicious requests may be difficult.

[0016] An artificial intelligence model can be used to identify a malicious request to initiate a reverse interaction or to otherwise determine a risk associated with allowing a reverse interaction to proceed based on a received request. The artificial intelligence model can include one or more machine-learning models that may include a clustering model, a graph mining model, a generative artificial intelligence model, such as a large language model, or any combination thereof. The artificial intelligence model may receive historical data, such as historical interaction data, historical item data, or the like, and at least a portion of the artificial intelligence model may be trained to output the one or more risk signals, the risk indicator, or a combination thereof.

[0017] A computing system can include the artificial intelligence model or may otherwise be communicatively coupled with the artificial intelligence model and capable of executing the artificial intelligence model. The computing system may receive a query, for example from a client computing system, and the query may indicate a request by the client computing system for the computing system to determine whether a request to initiate a reverse interaction is legitimate. The computing system may receive input data, for example associated with the request, that can be provided to the artificial intelligence model. In some examples, the input data can include historical reverse interaction data, historical data associated with a receiving entity that submitted the request for the reverse interaction, data and metadata about the reverse interaction, other suitable data that can be input into the artificial intelligence model, or any combination thereof. A first portion of the input data may be labeled, and a second portion of the input data may be unlabeled. The first portion of the input data may be provided to one or more supervised machinelearning models included in the artificial intelligence model to cause the one or more supervised machine-learning models to generate a first set of risk signals based on the labeled data. The second portion of the input data may be provided to one or more unsupervised machine-learning models included m the artificial intelligence model to cause the one or more unsupervised machine-learning models to generate a second set of risk signals based on the unlabeled data. A third portion of the input data may include historical item data, real-time item data, or a combination thereof, and the third portion of the input data may be provided to a generative artificial intelligence model included in the artificial intelligence model to cause the generative artificial intelligence model to generate a third set of risk signals based on the item data.

[0018] The first set of risk signals, the second set of risk signals, and the third set of risk signals may be combined or otherwise analyzed by the computing system to generate a risk indicator. In some examples, the first set of risk signals may include a first set of scores, based on labeled data, that indicate parameters that affect a likelihood of a request for initiating a reverse interaction being associated with malicious intent. Additionally or alternatively, the second set of risk signals may include a second set of scores, based on unlabeled data, that indicate parameters that affect a likeli hood of a request for initiating a reverse interaction being associated with malicious intent. And, the third set of risk signals may include a third set of scores, based on item data, that classify item data and indicate item parameters that affect a likelihood of a request for initiating a reverse interaction being associated with malicious intent. The first set of scores, the second set of scores, the third set of scores, or any combination thereof can be received as input by the computing system, or any sendee, model, or algorithm thereof, and can be used to generate the risk indicator. In some examples, the risk indicator may be or include a single score, or a set of scores, that indicates a likelihood of the request to initiate the reverse interaction being associated with malicious intent. A higher risk indicator may indicate a higher likelihood of the request being associated with malicious intent, and a lower risk indicator may indicate a lower likelihood of the request being associated with malicious intent, though the reverse, or any other scoring scheme, is also possible.

[0019] The risk indicator can be used to control the reverse interaction. For example, the computing system can generate a responsive message to the query from the client computing system, and the computing system can transmit the responsive message to the client computing system. The responsive message may include the risk indicator, insights derived from the risk indicator, a recommendation relating to whether to allow, challenge, or deny the request, or any combination thereof. The client computing device can receive the responsive message and determine whether to allow, challenge, or deny the request based on the responsive message or any information included therein. In other examples, the computing system can use the risk indicator, for example as input into a separate model, separate service, or separate algorithm, to control, for example directly or indirectly, the reverse interaction. In a particular example, the computing system can use the risk indicator to determine that a likelihood of the request being associated with malicious intent exceeds a threshold risk value, and the computing system can control the reverse interaction by challenging or denying the reverse interaction. In another particular example, the computing system can use the risk indicator to determine that the likelihood of the request being associated with malicious intent does not exceed a threshold risk value, and the computing system can control the reverse interaction by allowing the reverse interaction to proceed.

[0020] The request may be transmitted via an interactive computing environment. The interactive computing environment can be provided by a client computing system. For example, the client computing system can be, or may be controlled by, an entity that may provide software as a service, infrastructure as a service, one or more different types of goods, or other suitable goods or services accessible by a user computing system that can be used or otherwise accessed by a receiving entity. In some examples, the interactive computing environment can include a user interface. The receiving entity can use the user computing system to request access to a particular user interface that can be used to request the interaction, to request the reverse interaction, or the like. In some examples, the interactive computing environment can include one or more websites or sub-pages thereof For example, the interactive computing environment can include a secure website provided by the client computing system. The secure website can include cloud computing storage or other resources, and the client computing system can control access of the target entity’ to the secure website via a profile of the target entity' and, optionally, other suitable security techniques such as multi-factor authentication, username / password combinations, etc.

[0021] In some examples, the artificial intelligence techniques can be used for other suitable purposes in addition to, or alternative to, controlling or otherwise facilitating a decision with respect to the reverse interaction. For example, the artificial intelligence techniques can be used to verify an identity of the target entity, to determine whether to provide real-world goods and / or scrwccs on behalf of the target entity or other entities, and the like. The artificial intelligence techniques can involve applying one or more risk signals to a linked graph to determine, for example with respect to an online interaction or reverse interaction or a real-world interaction, a likelihood that the request submitted by the receiving entity’ is genuine. In another example, a client, such as a provider of restricted or regulated goods or services, can use the artificial intelligence techniques to determine whether to provide the restricted or regulated goods or services to the receiving entity. In some examples, the artificial intelligence techniques can be generally used for digital enablement of an interaction with respect to the receiving entity and one or more real-world items.

[0022] Certain aspects described herein, which can include generating one or more risk signals, a risk indicator, or a combination thereof using an artificial intelligence model, and providing a responsive message using the risk indicator, can improve at least the technical fields of controlling a reverse interaction, access control for a computing environment, or a combination thereof For instance, by generating and transmitting the responsive message, the risk assessment computing system can cause a reverse interaction to be controlled more accurately. The responsive message may be used to better predict whether the request for initiating the reverse interaction is legitimate, and using the responsive message may yield fewer malicious reverse interactions than if the responsive message is not used. And, transmitting the responsive message facilitates a practical application of the artificial intelligence techniques described herein by facilitating control of a real-world process such as the reverse interaction. Additionally or alternatively, by using the risk indicator generated using artificial intelligence techniques, a risk assessment computing system may provide legitimate access to the interactive computing environment using fewer computing resources compared to other risk assessment systems or techniques. For example, the risk indicator can be determined using less data about the receiving entity than other techniques, which may rely on identifying data such as fingerprints, facial scans, and the like. By using less data, (i) memory usage, (li) processing time, (hi) network bandwidth usage, (iv) response time, and the like for controlling access to the interactive computing environment is reduced, and functioning of a computing device is improved. Accordingly, the risk assessment computing system improves the access control for computing environment by reducing memory' usage, processing time, network bandwidth consumption, response time, and the like with respect to controlling access to the interactive computing environment using at least the artificial intelligence techniques described herein.

[0023] These illustrative examples are given to introduce the reader to the general subject matter discussed here and are not intended to limit the scope of the disclosed concepts. The following sections describe various additional features and examples with reference to the drawings in which like numerals indicate like elements, and directional descriptions are used to describe the illustrative examples but, like the illustrative examples, should not be used to limit the present disclosure. Operating Environment Example for Artificial Intelligence Techniques for Determining Whether a Request to Reverse an Interaction is Legitimate

[0024] Referring now to the drawings, FIG. 1 is a block diagram illustrating an example of a computing environment 100 in which artificial intelligence techniques can be used to determine whether a request for reversing an interaction is legitimate according to certain aspects of the present disclosure. FIG. 1 illustrates examples of hardware components of a risk assessment computing system 130 according to some aspects. The risk assessment computing system 130 can be a specialized computing system that may be used for processing large amounts of data, such as for controlling access to an interactive computing environment 107, for facilitating control of a reverse interaction between a target entity (e.g., a receiving entity) and a providing entity, for determining a likelihood that a request submitted by the receiving entity is legitimate, etc., using a large number of computer processing cycles. The risk assessment computing system 130 can include a risk assessment server 118 for validating risk assessment data from various sources. In some examples, the risk assessment computing system 130 can include other suitable components, servers, subsystems, and the like.

[0025] The risk assessment server 118 can include one or more processing devices that can execute program code, such as a risk assessment application 114, a risk prediction model 120, an artificial intelligence model 121, and the like. The program code can be stored on a non-transitory computer-readable medium or other suitable medium. The risk assessment server 118 can perform risk assessment validation operations or access control operations for validating or otherwise authenticating, for example using other suitable modules, services, models, components, etc. of the risk assessment server 118, received data such as entity data, item data, and interaction data (e.g., historical data 125, etc.), and the like received from user computing systems 106, client computing systems 104, external data systems 109, one or more data repositories, or any suitable combination thereof. In some examples, the risk assessment application 114 can authenticate the request, or facilitate authentication of the request, by utilizing real-time data 124, the historical data 125, any information determined therefrom, or by utilizing any other suitable data.

[0026] The real-time data 124 may be received by the external data systems 109, though the real-time data 124 may be received from other suitable sources. The historical data 125 can be determined or stored in one or more network-attached storage units on which various repositories, databases, or other structures are stored. An example of these data structures can include the entity data and interaction data repository 123. Additionally or alternatively, a training dataset 126 can be stored in the entity data and interaction data repository 123. In some examples, the training dataset 126 can be used to train the artificial intelligence model 121, one or more machine-learning models, which may include a supervised machine-learning model, an unsupervised machine-learning model, a generative artificial intelligence model, and the like, included therein, etc. The artificial intelligence model 121 can be trained to generate one or more risk signals based on the real-time data 124, the historical data 125, or a combination thereof, and the artificial intelligence model 121, or any model included therein, can be trained to determine a risk indicator based at least in part on the one or more risk signals to control access to the interactive computing environment 107 using the risk indicator, to facilitate control of a reverse interaction requested by a receiving entity, or to otherwise provide digital enablement for the receiving entity, etc.

[0027] Network-attached storage units may store a variety of different types of data organized in a variety of different ways and from a variety of different sources. For example, the network-attached storage unit may include storage other than primary storage located within the risk assessment server 118 that is directly accessible by processors located therein. In some aspects, the network-attached storage unit may include secondary, tertiary, or auxiliary storage, such as large hard drives, servers, and virtual memory, among other types of suitable storage. Storage devices may include portable or non-portable storage devices, optical storage devices, and various other mediums capable of storing and containing data. .A machine-readable storage medium or computer-readable storage medium may include a non-transitory medium in winch data can be stored and that does not include carrier waves or transitory electronic signals. Examples of a non-transitory medium may include, for example, a magnetic disk or tape, optical storage media such as a compact disk or digital versatile disk, flash memory, memory devices, or other suitable media.

[0028] Furthermore, the risk assessment computing system 130 can communicate with various other computing systems. The other computing systems can include user computing systems 106, such as smartphones, personal computers, etc., client computing systems 104, and other suitable computing systems. For example, user computing systems 106 may transmit, such as in response to receiving input from the receiving entity, requests for accessing the interactive computing environment 107, requests for initiating reverse interactions, or the like to the client computing systems 104. In response, the client computing systems 104 can send authentication queries, risk assessment queries, or the like to the risk assessment server 118, and the risk assessment server 118 can receive data about the reverse interaction, historical data, or the like for generating risk signals, determining a risk indicator, or a combination thereof. While FIG. 1 illustrates that the risk assessment computing system 130 and the client computing systems 104 are separate systems, the risk assessment computing system 130 and the client computing systems 104 can be one system. For example, the risk assessment computing system 130 can be a part of the client computing systems 104, or vice versa.

[0029] As illustrated in FIG. 1, the risk assessment computing system 130 may interact with the client computing systems 104, the user computing systems 106, or a combination thereof via one or more public data networks 108 to facilitate interactions between users of the user computing systems 106 and the interactive computing environment 107. For example, the risk assessment computing system 130 can facilitate the client computing systems 104 providing a user interface to the user computing system 106 for receiving various data from the user. The risk assessment computing system 130 can transmit validated risk assessment data, for example a risk indicator, scores, a responsive message, etc., to the client computing systems 104 for providing, challenging, or rejecting, etc. access of the target entity to the interactive computing environment 107, for facilitating a decision with respect to the reverse interaction, or the like. In some examples, the risk assessment computing system 130 can additionally communicate with third-party systems, such as external data systems 109, to receive risk assessment data, entity data, interaction data, item data, and the like, through the public data network 108. In some examples, the third-party systems can provide real-time, such as streamed, data about the receiving entity, historical data about the receiving entity, etc. to the risk assessment computing system 130.

[0030] Each client computing system 104 may include one or more devices such as individual servers or groups of servers operating in a distributed manner. A client computing system 104 can include any computing device or group of computing devices operated by a seller, lender, provider, or other suitable entity that can provide goods or services. The client computing system 104 can include one or more server devices. The one or more server devices can include or can otherwise access one or more non-transitory computer-readable media.

[0031] The client computing system 104 can further include one or more processing devices that can be capable of providing an interactive computing environment 107, such as a user interface, etc., that can perform various operations. The interactive computing environment 107 can include executable instructions stored in one or more n on-transitory computer-readable media. The instructions providing the interactive computing environment can configure one or more processing devices to perform the various operations. In. some examples, the executable instructions for the interactive computing environment can include instructions that provide one or more graphical interfaces. The graphical interfaces can be used by a user computing system 106 to access various functions of the interactive computing environment 107. For instance, the interactive computing environment 107 may transmit data to and receive data, such as via the graphical interface, from a user computing system 106 to shift between different states of the interactive computing environment 107, where the different states allow one or more electronic interactions between the user computing system 106 and the client computing system 104 to be performed.

[0032] In some examples, the client computing system 104 may include other computing resources associated therewith (e.g., not shown in FIG. 1), such as server computers hosting and managing virtual machine instances for providing cloud computing services, server computers hosting and managing online storage resources for users, server computers for providing database services, and others. The interaction between the user computing system 106, the client computing system 104, and the risk assessment computing system 130, or any suitable sub-combination thereof may be performed through graphical user interfaces, such as the user interface, presented by the risk assessment computing system 130, the client computing system 104, other suitable computing systems of the computing environment 100, or any suitable combination thereof. The graphical user interfaces can be presented to the user computing system 106. Application programming interface (API) calls, web service calls, or other suitable techniques can be used to facilitate interaction between any suitable combination or subcombination of the client computing system 104, the user computing system 106, and the risk assessment computing system 130.

[0033] A user computing system 106 can include any computing device or other communication device that can be operated by a user or entity, such as the receiving entity, which may include a consumer or a customer. The user computing system 106 can include one or more computing devices such as laptops, smartphones, and other personal computing devices. A user computing system 106 can include executable instructions stored in one or more non-transitory computer-readable media. The user computing system 106 can additionally include one or more processing devices configured to execute program code to perform various operations. In various examples, the user computing system 106 can allow a user to access certain online services or other suitable products, services, or computing resources from a client computing system 104, to engage in mobile commerce with the client computing system 104, to obtain controlled access to electronic content, such as the interactive computing environment 107, hosted by the client computing system 104, etc.

[0034] In some examples, the target entity can use the user computing system 106 to engage in an electronic interaction, or an electronic reverse interaction, with the client computing system 104 via the interactive computing environment 107. The risk assessment computing system 130 can receive a request, for example from the user computing system 106, to access the interactive computing environment 107 and, subsequently, to initiate a reverse interaction, and can use data, such as the real-time data 124, the historical data 125, or any other suitable data or signals determined therefrom, to generate a responsive message to facilitate a decision regarding whether to allow the reverse interaction, to challenge the reverse interaction, to deny the reverse interaction, etc. An electronic interaction between the user computing system 106 and the client computing system 104 can include, for example, the user computing system 106 being used to request products from the client computing system 104, and so on, and a reverse interaction may be the electronic interaction in reverse such as the user computing system 106 being used to request resources from the client computing system 104 in exchange for resources previously provided by the user computing system 106. An electronic interaction between the user computing system 106 and the client computing system 104 can also include, for example, one or more queries for a set of sensitive or otherwise controlled data, accessing online financial sendees provided via the interactive computing environment 107, submitting an online credit card application or other digital application to the client computing system 104 via the interactive computing environment 107, operating an electronic tool, such as a content-modification feature, an applicationprocessing feature, within the interactive computing environment 107, etc.

[0035] In some examples, an interactive computing environment 107 implemented through the client computing system 104 can be used to provide access to various online functions. As a simplified example, a user interface or other interactive computing environment 107 provided by the client computing system 104 can include electronic functions for requesting computing resources, online storage resources, network resources, database resources, real-world items or goods, or other types of resources.

[0036] A user computing system 106 can be used to request access to the interactive computing environment 107 provided by the client computing system 104, to request a reverse interaction via the interactive computing environment 107, or the like. The client computing system 104 can submit a request, such as in response to a request made by the user computing system 106 to access the interactive computing environment 107 or to initiate a reverse interaction, for risk assessment to the risk assessment computing system 130 and can selectively grant or deny access to various electronic functions, or the reverse interaction, based on risk assessment performed by the risk assessment computing system 130. Based on the request, the risk assessment computing system 130 can determine one or more risk signals or a risk indicator for data associated with the request provided by a receiving entity, which may submit or may have submitted the request via the user computing system 106. Based on a risk indicator determined using the artificial intelligence model 121, the risk assessment computing system 130, the client computing system 104, or a combination thereof can determine whether to grant the access request of the user computing system 106 to certain features of the interactive computing environment 107 or whether to allow, challenge, or deny the reverse interaction. The risk assessment computing system 130, the client computing system 104, or a combination thereof can use the risk indicator for other suitable purposes such as identifying a manipulated identity, controlling a real-world interaction, and the like.

[0037] In a simplified example, the system illustrated in FIG. 1 can configure the risk assessment server 118 to be used for controlling access to the interactive computing environment 107, for facilitating a decision regarding whether to allow the reverse interaction, or the like. The risk assessment server 118 can receive data about a receiving entity7 that submitted a request via the interactive computing environment 107, for example, based on the information, such as information collected by the client computing system 104 via a user interface provided to the user computing system 106, provided by the client computing system 104 or received via other suitable computing systems. The risk assessment server 118 can additionally or alternatively receive historical reverse interaction data, historical item data, real-time data, and the like relating to the request. The risk assessment server 118 can use the artificial intelligence model 121 to determine one or more risk signals, a risk indicator, or the like for the request based at least in part on the received data. The risk assessment server 118 can transmit the risk indicator, or any responsive message or inference derived therefrom, to the client computing system 104 for use in controlling access to the interactive computing environment 107, for use in facilitating the reverse interaction, or the like.

[0038] The risk indicator, or the responsive message, can be utilized, for example by the risk assessment computing system 130, the client computing system 104, or the like, to determine whether the risk associated with the allowing the reverse interaction to proceed exceeds a threshold, thereby granting, challenging, or denying the request to initiate the reverse interaction. For example, if the risk assessment computing system 130 determines that the risk indicator indicates that risk of allowing the reverse interaction is lower than a threshold value, then the client computing system 104 associated with the service provider can generate or otherwise provide access permission to the user computing system 106 that requested the reverse interaction. The access permission can include, for example, cryptographic keys used to generate valid access credentials or decryption keys used to decrypt access credentials. The client computing system 104 can also allocate resources to the receiving entity and provide a dedicated web address for the allocated resources to the user computing system 106, for example, by adding the user computing system 106 in the access permission. With the obtained access credentials or the dedicated web address, the user computing system 106 can establish a secure network connection to the interactive computing environment 107 hosted by the client computing system 104 and access the resources via invoking API calls, web service calls, HTTP requests, other suitable mechanisms or techniques, etc. Additionally or alternatively, the obtained access credentials or the dedicated web address can be used by the user computing system 106 to initiate the reverse interaction.

[0039] In some examples, the risk assessment computing system 130 may determine whether to grant, challenge, or deny the request made by the user computing system 106 for accessing the interactive computing environment 107 or for initiating the reverse interaction. For example, based on the risk indicator or inferences derived thereof, the risk assessment computing system 130 can determine that the request made by the receiving entity is a legitimate request and may authenticate the request. In other examples, the risk assessment computing system 130 can challenge or deny the reverse interaction if the risk assessment computing system 130 determines that the request made by the receiving entity may not be a legitimate request or may otherwise be associated with malicious intent.

[0040] Each communication within the computing environment 100 may occur over one or more data networks, such as a public data network 108, a network 116 such as a private data network, or some combination thereof. A data network may include one or more of a variety' of different types of networks, including a wireless network, a wired network, or a combination of a wared and wireless network. Examples of suitable networks include the Internet, a personal area network, a local area network (“LAN”), a wade area network (“WAN”), or a wireless local area network (“WLAN”). A wireless network may include a wireless interface or a combination of wireless interfaces. A wired network may include a w'ired interface. The wired or wireless networks may be implemented using routers, access points, bridges, gateways, or the like, to connect devices m the data network.

[0041] The number of devices depicted in FIG. 1 is provided for illustrative purposes. Different numbers of devices may be used. For example, while certain devices or systems are shown as single devices in FIG. 1, multiple devices may instead be used to implement these devices or systems. Similarly, devices or systems that are shown as separate, such as the risk assessment server 118 and the entity data and interaction data repository 123, etc., may be instead implemented in a single device or system. Similarly and as discussed above, the risk assessment computing system 130 may be a part of the client computing system 104. Artificial Intelligence Techniques for Determining Whether a Request for Reversing an Interaction is Legitimate

[0042] FIG. 2 is a flow chart illustrating an example of a process 200 for using artificial intelligence techniques to determine whether a request for reversing an interaction is legitimate according to certain aspects of the present disclosure. One or more computing devices, such as the risk assessment computing system 130, may implement operations illustrated in FIG. 2 by executing suitable program code such as the artificial intelligence model 121, the risk prediction model 120, or the like. For illustrative purposes, the process 200 is described with reference to certain examples depicted in the figures. Other implementations, however, are possible.

[0043] At block 202, the process 200 involves receiving a request to reverse a previously executed interaction. The request may be generated by a user computing system 106 in response to receiving input from a target entity, which may be or include a receiving entity. The previously executed interaction may include an interaction between the receiving entity and a providing entity in which the receiving entity provided the providing entity with resources in exchange for one or more items. Reversing the previously executed interaction may involve the receiving entity requesting a return of the resources in exchange for returning the one or more items. The request can include data relating to the previously executed interaction that is associated with the target entity. For example, the data can include labeled historical data relating to historical reversed interactions, unlabeled historical data relating to historical reversed interactions, historical item data relating to items associated with historical reversed interactions, other suitable data, or any combination thereof.

[0044] The labeled historical data can include historical requests to reverse corresponding historical interactions, outcomes of the requests, outcomes of allowing the corresponding historical interactions to be reversed, and the like. The outcomes may be labeled. The labeled historical data can include a set of historical requests that include information (e.g., identity data) about the entities submitting the historical requests, information (e.g., a number of resources involved with the requests, a time of the requests, etc.) about the requests, and the like. Additionally or alternatively, the labeled historical data can include a first set of outcomes of the requests corresponding to the set of historical requests. Each outcome of the first set of outcomes of the requests can include an indication of whether the corresponding request was granted, challenged, or denied. Additionally or alternatively, the labeled historical data can include a second set of outcomes of historical, allowed, reversed interactions. Each outcome of the second set of outcomes can include an indication of whether the corresponding, allowed, reversed interaction was successful. For example, a reverse interaction in which the receiving entity properly returned the items may be labeled as a successful reversed interaction, and a reverse interaction in which the receiving entity' properly returned the items may be labeled as an unsuccessful reversed interaction.

[0045] The unlabeled historical data can include historical requests to reverse corresponding historical interactions, outcomes of the requests, outcomes of allowing the corresponding historical interactions to be reversed, and the like. The outcomes may be unlabeled or may otherwise lack data or context to allow the outcomes to be confidently labeled. The unlabeled historical data can include a set of historical requests that include information (e.g., identity data) about the entities submitting the historical requests, information (e.g., a number of resources involved with the requests, a time of the requests, etc.) about the requests, and the like. Additionally or alternatively, the unlabeled historical data can include a first set of outcomes of the requests corresponding to the set of historical requests. Each outcome of the first set of outcomes of the requests can include an indication of whether the corresponding request w'as granted, challenged, or denied. Additionally or alternatively, the unlabeled historical data can include a second set of outcomes of historical, allowed, reversed interactions. Each outcome of the second set of outcomes may be unlabeled.

[0046] The historical item data can include a set of item data having descriptions about the items. For example, the historical item data can include a first list that includes items offered for sale, whether historically or in real-time, that may be similar or identical to one or more items involved in the request. .Additionally or alternatively, the historical item data can include a second list that includes descriptions of corresponding items in the first list. The descriptions may be text-based descriptions that may be copied from item listings, may be derived from reviews or interactions, or the like.

[0047] At block 204, the process 200 involves generating one or more risk signals based on the request using an artificial intelligence model 121. The artificial intelligence model 121 may include one or more machine-learning models, one or more generative models, or the like to provide functionality' for the artificial intelligence model 121. For example, the artificial intelligence model 121 can include one or more supervised machine-learning models, one or more unsupervised machine-learning models, one or more generative artificial intelligence models, or the like. The one or more supervised machine-learning models may include a random forest model, an attribute model, and so on. The one or more unsupervised machine-learning models may include a clustering model or other suitable unsupervised machine-learning model. The one or more generative artificial intelligence models may include a large language model or other suitable types of generative artificial intelligence models.

[0048] The risk assessment computing system 130 may receive the request, and the data included therein, and may selectively provide the data to the artificial intelligence model 121 to generate the one or more risk signals. For example, the labeled historical data may be used to train the supervised machine-learning model, the unlabeled historical data may be used by the unsupervised machine-learning model to generate clusters of the unlabeled historical data, and the historical item data may be provided to the generative artificial intelligence model to cause the generative artificial intelligence model to generate classifications for items included in the historical item data. Additionally or alternatively, the data relating to the receiving entity and to the request to reverse the previously executed interaction can be provided to the artificial intelligence model 121. The artificial intelligence model 121 can receive the input and can generate the one or more risk signals. For example, the artificial intelligence model 121 can map at least a first portion of the input to at least a first portion of output based on a trained, supervised machine-learning model included in the artificial intelligence model 121. Additionally or alternatively, the artificial intelligence model 121 may cluster at least a second portion of the input to generate at least a second portion of the output, for example based on a similarity score between the clustered second portion and clustered historical interaction data. Additionally or alternatively, the artificial intelligence model 121 may generate at least a third portion of the output that includes one or more classifications for items associated with the request to reverse the previously executed interaction.

[0049] In some examples, the one or more risk signals may be the first portion of the output, the second portion of the output, and the third portion of the output. In other examples, the one or more risk signals may be derived from the first portion of the output, the second portion of the output, and the third portion of the output. For example, the artificial intelligence model 121, or the risk prediction model 120, may generate one or more risk indicator scores based on the first portion of the output, the second portion of the output, and the third portion of the output. In a particular example, the mapped output from the first portion of the output may be assigned a first score based on the historical reversed interaction data, the clustered output from the second portion of the output may be assigned a second score based on the historical clusters of data associated with the historical reversed interactions, and the item classifications may be assigned a third score based on the classifications of historical item data. The one or more risk signals may be or include the first score, the second score, and the third score, or other scores or information.

[0050] At block 206, the process 200 involves determining a risk indicator based on the one or more risk signals generated by the artificial intelligence model 121. In some examples, the artificial intelligence model 121 may receive the one or more risk signals as input and may generate the risk indicator, for example by combining the one or more risk signals, by mapping the one or more risk signals to the risk indicator, or otherwise suitably generating the risk indicator based on the one or more risk signals. In other examples, the artificial intelligence model 121 may generate the one or more risk signals and may transmit the one or more risk signals to a separate model, sendee, module, or the like, such as the risk prediction model 120, for facilitating determination of the risk indicator. The risk indicator may be or include a score that indicates a likelihood of the request, submitted by the receiving entity for reversing the previously executed interaction being associated with malicious intent. For example, a large or high risk indicator may indicate that there is a large risk of the request being associated with malicious intent and that, if initiated, the reverse interaction may not be successful. Additionally or alternatively, a small or low risk indicator may indicate that there is a small or negligible risk of the request being associated with malicious intent and that, if initiated, the reverse interaction may be successful. Other examples, including a reverse of the foregoing, are possible for the risk indicator.

[0051] At block 208, the process 200 involves generating a responsive message that can be used to control a reversal of the previously executed interaction. In some examples, the risk assessment server 118 (or any other suitable module, model, or computing device) can generate, transmit, or a combination thereof the responsive message to a computing device (e.g., the client computing system 104) or any other suitable computing device that can control reversal of the previously executed interaction. The responsive message can vary based on the risk indicator determined at the block 206. For example, the responsive message may indicate that the request for reversing the previously executed interaction is a legitimate request and may recommend granting approval to the request to initiate reversal of the previously executed interaction, based on the request, or may recommend granting access by the receiving entity to the interactive computing environment 107 for initiating reversal of the previously executed interaction. In other examples, the responsive message may indicate that the request is associated with a malicious intent, such as requesting return of resources without intending to return items, and may recommend challenging or denying the request, or reversal of the previously executed interaction, and the like.

[0052] In some examples, the responsive message may be generated and transmitted based on the risk indicator determined at the block 206. The risk indicator can include a credit score, a fraud score, an identity score, other suitable scores indicating risk in one or more multiple dimensions associated with the receiving entity, the request, or any suitable combination thereof, based on the request and based on the artificial intelligence techniques disclosed herein. The risk assessment server 118 can determine, based on the risk indicator generated by the risk prediction model 120 or the artificial intelligence model 121, whether to recommend granting, challenging, or denying the request submitted by the receiving entity, reversal of the interaction originally initiated by the target entity, etc. In some examples, the risk assessment computing system 130 can generate and transmit the responsive message to grant, challenge, or deny the request based on a recommendation provided by the risk prediction model 120 or the artificial intelligence model 121. Techniques for Controlling an Interaction Using Arti ficial Intelligence

[0053] FIG. 3 is a flow chart illustrating an example of a process 300 for determining a risk assessment indicator using artificial intelligence techniques according to certain aspects of the present disclosure. One or more computing devices, such as the risk assessment computing system 130, may implement operations illustrated in FIG. 3 by executing suitable program code such as the artificial intelligence model 121, the risk prediction model 120. and the like. For illustrative purposes, the process 300 is described with reference to certain examples depicted m the figures. Other implementations, however, are possible.

[0054] At block 302, the process 300 involves receiving a risk assessment query' for a target entity, such as the receiving entity, from a remote computing device such as a computing device associated with the target entity. The risk assessment query' can also be received by the risk assessment server 118 from a remote computing device associated with an entity' authorized to request risk assessment of the target entity' or any request submitted thereby. The risk assessment query' may involve a request for determination for whether the target entity, or a request for reversing a previously executed interaction associated therewith, is associated with potentially malicious intent, such as first-party fraud or other types of fraud, or the like.

[0055] At block 304, the process 300 involves accessing a risk prediction model 120 trained or otherwise configured to generate a risk indicator based on one or more risk signals generated using the artificial intelligence model 121. In some examples, the risk prediction model 120 may additionally or alternatively be or include one or more proprietary models (e.g., artificial intelligence models, machine-learning models, etc.), one or more heuristics models, and / or one or more simulation models. The artificial intelligence model 121 can include one or more supervised machine-learning models, one or more unsupervised machine-learning models, one or more generative artificial intelligence models, or the like, and the artificial intelligence model 121 may be trained on, or receive as input, data such as entity data, identity' data, historical interaction data, historical item data, and the like. Additionally or alternatively, one or more risk signals can be generated by the artificial intelligence model 121 as described at least with respect to the block 204. Examples of entity data can include identity data, such as name, address, etc., and examples of interaction data can include a time of interaction, a number of resources associated with the interaction, a success status of a corresponding interaction or reversal thereof, etc. The risk indicator can indicate a level of risk associated with the target entity, or the request associated therewith, and the risk indicator can include indicators such as a credit score or fraud score of the target entity. In some examples, a linked graph can be used to determine the risk indicator. For example, the risk prediction model 120 can traverse the linked graph, can execute one or more clustering or other suitable machine-learning models on the linked graph, and the like to determine the risk indicator.

[0056] At block 306, the process 300 involves computing a risk indicator for the target entity based on the one or more risk signals. In some examples, the risk prediction model 120 can be used to determine the risk indicator, though in other examples, other components or models (e.g., the artificial intelligence model 121) of the risk assessment computing system 130 can be used to determine the risk indicator. The one or more risk signals generated by or otherwise received from the artificial intelligence model 121, can be used as input to the risk prediction model 120. The risk prediction model 120 can generate output by combining the one or more risk signals, can evaluate the one or more risk signals, can compare the one or more risk signals to historical risk signals, or the like. The output of the risk prediction model 120 can be or include the risk indicator for the target entity.

[0057] At block 308, the process 300 involves transmitting a responsive message based on the risk indicator, which may be determined at the block 306. In some examples, the risk assessment server 118, or any other suitable module, model, or computing device, can transmit the responsive message to a computing device, such as the client computing system 104, or any other suitable computing device that can control reversal of the previously executed interaction. The responsive message can vary based on the risk indicator. For example, the responsive message may indicate that the request submitted by the target entity is a legitimate request (e.g., not associated with potentially malicious intent) and may recommend granting approval to the request based on the responsive message. In other examples, the responsive message may indicate that the request submitted by the target entity is likely associated with malicious intent or may otherwise not be associated with legitimate activity and may recommend challenging or denying the request.

[0058] In some examples, the responsive message may be generated and transmitted based on the artificial intelligence model 121. For example, the risk prediction model 120 can generate a risk indicator for the request submitted by the target entity based on one or more risk signals generated by the artificial intelligence model 121, and the risk assessment server 118 can generate the responsive message based on the risk indicator. The risk indicator can include a credit score, a fraud score, an identity score, other suitable scores indicating risk in one or more than one dimension associated with the target entity or the request associated therewith, or any suitable combination thereof. The risk prediction model 120 can generate the risk indicator by applying a clustering model to the one or more risk signals or using other suitable techniques.

[0059] The risk assessment server 118 can determine, based on the risk indicator generated by the risk prediction model 120, whether to recommend granting, challenging, or denying the request submitted by the target entity. In some examples, the risk assessment computing system 130 can generate and transmit the responsive message to grant, challenge, or deny the request based on a recommendation provided by the risk prediction model 120. In other examples, the risk assessment computing system 130 can directly control (e.g., allow, challenge, or deny) reversal of the previously executed interaction based on the responsive message or any data included therein. For example, if the responsive message indicates that the request exceeds a threshold risk value, then the responsive message may control reversal of the interaction by preventing resources from being reversed until the previously exchanged goods, services, content, or like are provided by the receiving entity. Example of an Architecture for Artificial Intelligence Model

[0060] FIG. 4 is a block diagram of an example of an architecture 400 of an artificial intelligence model 121 that can be used to determine whether a request for reversing an interaction is legitimate according to certain aspects of the present disclosure. As illustrated in FIG. 4, the artificial intelligence model 121 can include a supervised machine-1 earning model 412, an unsupervised machine-learning model 414, and a generative artificial intelligence model 416, though the artificial intelligence model 121 may include any suitable, additional or alternative models, services, or the like to provide functionality for the artificial intelligence model 121. The supervised machine-learning model 412 may be communicatively coupled with the unsupervised machine-learning model 414, the generative artificial intelligence model 416, or a combination thereof, or any permutation thereof. Additionally or alternatively, the supervised machine-learning model 412, the unsupervised machine-learning model 414, and the generative artificial intelligence model 416 may be configured to operate in series, in parallel, or in a combination thereof.

[0061] The artificial intelligence model 121 can receive various data and can generate an output based at least in part on the input data. For example, and as illustrated in FIG. 4, the artificial intelligence model 121 can receive entity data 402, interaction data 404, and item data 405. The entity' data 402 may include identity data 408. The identity data 408 can include a name of a target entity, a physical address of the target, entity, a digital address of the target entity, familial members of the target entity', a Social Security' number of the target entity, and any other suitable personally identifiable information for the target entity'. The identity data 408 may be stored in a data repository', such as the entity data and interaction data repository'' 123, and the risk assessment computing system 130 can access the data repository to receive the identity data 408. In other examples, the identity data 408 may be streamed, such as in approximately real-time, to the risk assessment computing system 130 based on streamed interactions.

[0062] The interaction data 404 may include real-time interaction data 410a and historical interaction data 410b, though other suitable data or types of data are possible. Interaction data may include a time or day of a particular interaction, a type or number of resources associated with the particular interaction, separate entities with which the target entity interacts with for the particular interaction, and the like. The real-time interaction data 410a may be generated in approximately real-time and may be streamed or otherwise substantially contemporaneously transmitted to the risk assessment computing system 130. The historical interaction data 410b may be stored in a data repository such as the entity data and interaction data repository 123. The risk assessment computing system 130 can access the data repository to receive the historical interaction data 410b. The interaction data 404 may include labeled data, unlabeled data, or a combination thereof. The item data 405 may include indications of items offered for sale historically or in realtime and may include text-based descriptions of corresponding items.

[0063] The entity data 402, the interaction data 404, the item data 405, or any combination thereof can be transmitted to or otherwise suitably received by the artificial intelligence model 121. In a particular example, the entity data 402, the interaction data 404, and the item data 405 can be streamed to the artificial intelligence model 121. The artificial intelligence model 121 can receive the entity data 402, the interaction data 404, the item data 405, or a combination thereof, and can direct each of the types of input data to each of the models, or a subset thereof, included in the artificial intelligence model 121. The artificial intelligence model 121 may be configured to output or otherwise generate risk signals 418 based on the entity data 402, the interaction data 404, the item data 405, or any combination thereof and by using the supervised machine-learning model 412, the unsupervised machine-learning model 414, the generative artificial intelligence model 416, or any combination thereof. In a particular example, the risk signals 418 may each indicate a likelihood of a particular data point or set of data points of the entity data 402, the interaction data 404, the item data 405, or a combination thereof being associated with potentially malicious intent associated with the request.

[0064] The artificial intelligence model 121, or any component or service (e.g., the risk prediction model 120, etc.) of the risk assessment computing system 130, can determine a risk indicator 420 based at least in part on the risk signals 418. For example, the artificial intelligence model 121 can execute a clustering model on the risk signals 418, or any information derived therefrom, to determine the risk indicator 420. The artificial intelligence model 121 can use any other suitable models or techniques to determine the risk indicator 420 using the risk signals 418. The artificial intelligence model 121 can use the risk indicator 420 to generate the responsive message 406, which may be used to control access of the target entity7 to an interactive computing environment 107, to control a real-world interaction, such as reversal of the previously executed interaction, to control a digital interaction involving the target entity, or any combination thereof Example of Computing System

[0065] Any suitable computing system or group of computing systems can be used to perform the operations for the artificial intelligence techniques described herein. For example, FIG. 5 is a block diagram illustrating an example of a computing device 500, which can be used to implement the risk assessment server 118, the artificial intelligence model 121, or other suitable components of the computing environment 100. The computing device 500 can include various devices for communicating with other devices in the computing environment 100, for example as described with respect to FIG. 1. The computing device 500 can include various devices for performing one or more data consolidation or validation operations, artificial intelligence operations, or other suitable operations, described above with respect to FIGS. 1-4.

[0066] The computing device 500 can include a processor 502 that is communicatively coupled to a memory' 504. The processor 502 can execute computerexecutable program code stored in the memory 504, can access information stored in the memory / 504, or both. Program code may include machine-executable instructions that may represent a procedure, a function, a subprogram, a program, a routine, a subroutine, a module, a software package, a class, or any combination of instructions, data structures, or program statements. A code segment may be coupled to another code segment or a hardware circuit by passing or receiving information, data, arguments, parameters, or memory contents. Information, arguments, parameters, data, etc., may be passed, forwarded, or transmitted via any suitable means including memory sharing, message passing, token passing, network transmission, among others.

[0067] Examples of a processor 502 can include a microprocessor, an applicationspecific integrated circuit (ASIC), a field-programmable gate array (FPGA), or any other suitable processing device. The processor 502 can include any suitable number of processing devices, including one. The processor 502 can include or communicate with a memory' 504. The memory' 504 can store program code that, when executed by the processor 502, causes the processor 502 to perform the operations described herein.

[0068] The memory / 504 can include any suitable non-transitory computer-readable medium. The computer-readable medium can include any electronic, optical, magnetic, or other storage device capable of providing a processor with computer-readable program code or other program code. Non-limiting examples of a computer-readable medium can include a magnetic disk, memory chip, optical storage, flash memory, storage class memory / , ROM, RAM, an ASIC, magnetic storage, or any other medium from which a computer processor can read and execute program code. The program code may include processor-specific program code generated by a compiler or an interpreter from code written in any suitable computer-programming language. Examples of suitable programming language can include Hadoop, C, C++, C#, Visual Basic, Java, Python, Perl, JavaScript, ActionScript, etc.

[0069] The computing device 500 may also include a number of external or internal devices such as input or output devices. For example, the computing device 500 is illustrated with an input / output interface 508 that can receive input from input devices or provide output to output devices. A bus 506 can also be included in the computing device 500. The bus 506 can communicatively couple one or more components of the computing device 500.

[0070] The computing device 500 can execute program code 514 that can include the artificial intelligence model 121, or any other suitable computer model, computer module, computer service, or the like. The program code 514 for the artificial intelligence model 121 and the like may be resident in any suitable computer-readable medium and may be executed on any suitable processing device. For example, as depicted in FIG. 5, the program code 514 for the artificial intelligence model 121 can reside in, or may otherwise be included in, the memory' 504 at the computing device 500 along with the program data 516 associated with the program code 514. Executing the artificial intelligence model 121 can configure the processor 502 to perform one or more of the operations, such as the artificial intelligence operations, described herein.

[0071] In some aspects, the computing device 500 can include one or more output devices. One example of an output device can be the network interface device 510 illustrated in FIG. 5. A network interface device 510 can include any device or group of devices suitable for establishing a wired or wireless data connection to one or more data networks described herein. Non-limiting examples of the network interface device 510 can include an Ethernet network adapter, a modem, etc.

[0072] Another example of an output device can include the presentation device 512 depicted in FIG. 5. A presentation device 512 can include any device or group of devices suitable for providing visual, auditory, or other suitable sensory' output. Non-limiting examples of the presentation device 512 can include a touchscreen, a monitor, a speaker, a separate mobile computing device, etc. In some aspects, the presentation device 512 can include a remote client-computing device that can communicate with the computing device 500 using one or more data networks described herein. In other aspects, the presentation device 512 can be optional.

[0073] The foregoing description of some examples has been presented only for the purpose of illustration and description and is not intended to be exhaustive or to limit the disclosure to the precise forms disclosed. Numerous modifications and adaptations thereof will be apparent to those skilled in the art without departing from the spirit and scope of the disclosure.

Claims

1. A system comprising:a processor; anda non-transitory computer-readable medium comprising instructions that are executable by the processor to cause the processor to perform operations comprising:receiving a request to reverse a previously executed interaction, the request including data relating to a previously executed interaction that is associated with a target entity;generating, using an artificial intelligence model that includes a generative artificial intelligence model, one or more risk signals based on the request and the data;determining, based on the one or more risk signals, a risk indicator that represents a likelihood that the request is illegitimate; andproviding a responsive message to control reversal of the previously executed interaction and based on the risk indicator.

2. The system of claim 1, wherein the artificial intelligence model comprises a supervised machine-learning model and an unsupervised machine-learning model that are communicatively coupled with one another and with the generative artificial intelligence model, and wherein the generative artificial intelligence model comprises a large language model.

3. The system of claim 2, wherein the data further includes labeled historical data relating to historical reversed interactions, and wherein the supervised machine-learning model is configured to receive the labeled historical data as input and to generate at least a portion of the one or more risk signals based on the labeled historical data.

4. The system of claim 2, wherein the data further includes unlabeled historical data relating to historical reversed interactions, and wherein the unsupervised machinelearning model is configured to receive the unlabeled historical data as input and togenerate at least a portion of the one or more risk signals based on clustering the unlabeled historical data.

5. The system of claim 1, wherein the data further includes historical item data relating to items associated with historical reversed interactions, and wherein the generative artificial intelligence model is configured to receive the historical item data and to generate a plurality of item classifications based on the historical item data.

6. The system of claim 5, wherein the operation of determining the risk indicator comprises using the plurality of item classifications to determine a likelihood that the request is legitimate.

7. The system of claim 1, wherein the operations further comprise controlling reversal of the previously executed interaction based on the risk indicator by either allowing the reversal of the previously executed interaction or preventing the reversal of the previously executed interaction.

8. A method comprising:receiving, by a computing system, a request to reverse a previously executed interaction, the request including data relating to a previously executed interaction that is associated with a target entity,generating, by the computing system and by using an artificial intelligence model that includes a generative artificial intelligence model, one or more risk signals based on the request and the data;determining, by the computing system and based on the one or more risk signals, a risk indicator that represents a likelihood that the request is illegitimate; andproviding, by the computing system, a responsive message to control reversal of the previously executed interaction based on the risk indicator.

9. The method of claim 8, wherein the artificial intelligence model comprises a supervised machine-learning model and an unsupervised machine-learning model that are communicatively coupled with one another and with the generative artificial intelligencemodel, and wherein the generative artificial intelligence model comprises a large language model.

10. The method of claim 9, wherein the data further includes labeled historical data relating to historical reversed interactions, and wherein the supervised machine-learning model receives the labeled historical data as input and generates at least a portion of the one or more risk signals based on the labeled historical data.

11. The method of claim 9, wherein the data further includes unlabeled historical data relating to historical reversed interactions, and wherein the unsupervised machinelearning model receives the unlabeled historical data as input and generates at least a portion of the one or more risk signals based on clustering the unlabeled historical data.

12. The method of claim 8, wherein the data further includes historical item data relating to items associated with historical reversed interactions, and wherein the generative artificial intelligence model receives the historical item data and generates a plurality' of item classifications based on the historical item data.

13. The method of claim 12, wherein determining the risk indicator comprises using the plurality of item classifications to determine a likelihood that the request is legitimate.

14. The method of claim 8, further comprising controlling reversal of the previously executed interaction based on the risk indicator by either allowing the reversal of the previously executed interaction or preventing the reversal of the previously executed interaction.15, A non-transitory computer-readable medium comprising instructions that are executable by a processing device for causing the processing device to perform operations comprising:receiving a request to reverse a previously executed interaction, the request including data relating to a previously executed interaction that is associated with a target entity;generating, using an artificial intelligence model that includes a generative artificial intelligence model, one or more risk signals based on the request and the data,determining, based on the one or more risk signals, a risk indicator that represents a likelihood that the request is illegitimate; andproviding a responsive message to control reversal of the previously executed interaction based on the risk indicator.

16. The non-transitory computer-readable medium of claim 15, wherein the artificial intelligence model comprises a supervised machine-learning model and an unsupervised machine-learning model that are communicatively coupled with one another and with the generative artificial intelligence model, and wherein the generative artificial intelligence model comprises a large language model.

17. The non-transitory computer-readable medium of claim 16, wherein the data further includes labeled historical data relating to historical reversed interactions, and wherein the supervised machine-learning model is configured to receive the labeled historical data as input and to generate at least a portion of the one or more risk signals based on the labeled historical data.

18. The non-transitory computer-readable medium of claim 16, wherein the data further includes unlabeled historical data relating to historical reversed interactions, and wherein the unsupervised machine-learning model is configured to receive the unlabeled historical data as input and to generate at least a portion of the one or more risk signals based on clustering the unlabeled historical data.

19. The non-transitory computer-readable medium of claim 15, wherein the data further includes historical item data relating to items associated with historical reversed interactions, wherein the generative artificial intelligence model is configured to receive the historical item data and to generate a plurality of item classifications based on the historical item data, and wherein the operation of determining the risk indicator comprises using the plurality of item classifications to determine a likelihood that the request is legitimate.

20. The non-transitory computer-readable medium of claim 15, wherein the operations further comprise controlling reversal of the previously executed interaction based on the risk indicator by either allowing the reversal of the previously executed interaction or preventing the reversal of the previously executed interaction.

Images