Abstract: A computer-implemented method to generate a hotspot confidence score for a hotspot in a network graph includes, receiving input data, wherein the input data includes a plurality of messages, each message containing a set of message data. The method further includes generating, based on the plurality of messages, a network graph. The method also includes identifying, in the network graph, a first hotspot. The method includes compiling a set of hotspot characteristics for the first hotspot. The method further includes receiving, in response to identifying the first hotspot, a first user feedback. The method also includes, generating, by a learning model, a hotspot confidence score for the first hotspot; and outputting the hotspot confidence score.

Abstract: One or more graphical user interfaces (GUIs) and/or a console management, modeling, and analysis system is described. In some embodiments, the GUI and/or management system can be used to analyze investment purchases and/or sales. In some embodiments, users may be allowed to enter data used to produce dynamic models. In some embodiments, data may be aggregated from various users and/or sources to provide adaptive, dynamic models and/or projections.

Abstract: The disclosed embodiments relate to implementation of a trading system, which may also be referred to as a trading system architecture, having improved performance which further assures transactional determinism under increasing processing transaction loads while providing improved trading opportunities, fault tolerance, low latency processing, high volume capacity, risk mitigation and market protections with minimal impact, as well as improved and equitable access to information and opportunities.

Abstract: The present disclosure relates to methods and systems for providing personalized digital advice. A digital advisor service applies cross-entity historical interaction (e.g., behavior attributes) to one or more predictive models to identify one or more personalized goals for a user. The digital advisor service provides, via an application programming interface, the identified one or more personalized goals to an entity service, enabling the entity service to present the one or more personalized goals.

Abstract: A computer-implemented method includes providing certified financial data indicating financial risk about an individual. The method includes electronically collecting financial account data about the individual from at least one financial source. The method includes transforming the financial account data into a desired format. The method includes validating the financial account data by applying an algorithm engine to the financial account data to identify exceptions, wherein the exceptions indicate incorrect data or financial risk. The method includes marking the exceptions as valid exceptions when output of the algorithm engine validates the exceptions. The method includes confirming the exceptions by collecting additional data and applying the algorithm engine to the additional data.

Abstract: A method receives an electronic image and uses the image as an input to a neural network. Based on a determination that the image represents a document, the method uses the image as an input to another neural network to identify a portion of the document containing an identifier. The method extracts the identifier by performing character recognition on the identified portion and determines whether the identifier is valid by using a validation API to determine whether the identifier is associated with a valid account at an institution. Based on a determination that the identifier is associated with a valid account, the method authorizes a transaction associated with the identifier. Based on a determination that the identifier is not associated with a valid account, the method denies the transaction. The first neural network classifies the electronic image into one of multiple valid document types and an invalid document type.

Abstract: A consumption prediction method includes the following steps: calculating a personal preference correlation coefficient; inputting historical environment data, a historical consumption record and the personal preference correlation coefficient into a first neural network model; a training model is generated by the first neural network model; and determining whether the accuracy rate of the training model is higher than the training threshold. When the accuracy rate of the training model is higher than the training threshold, the training model is regarded as a prediction model.

Abstract: A system for user registration and preference configuration for a data sharing platform is provided. The system comprises a database system containing data relating to a plurality of users and user profile configuration settings relating to the plurality of users and memory storing instructions that, when executed by one or more processors, cause the one or more processors to generate a graphical user interface and provide the graphical user interface over a network to a user device, receive a user profile configuration setting and a designation of at least one experience provider with which to share data of the user, and store, in the database system via associate linking, the user profile configuration setting and the designation of the at least one experience provider with which to share data of the user.

Abstract: A computer system is configured to receive a dataset that includes a plurality of transaction request records and is divisible into a plurality of segments. Each transaction request record includes an individual score calculated by a machine learning algorithm. The computer system also receives a plurality of constraints. The computer system is configured to calculate, using a linear programming algorithm, a decision threshold score for a particular segment of the plurality of segments using the transaction request records. The computer system is configured to provides access to the calculated decision threshold score to a production computer system. The production computer system is configured to use the decision threshold score to evaluate a subsequent transaction request corresponding to the particular segment.

Abstract: A system for generating rate and payment information for a customer receives an inquiry type from a customer relating to a loan or mortgage. The system also receives a value specific to the potential loan or mortgage. In combination with a product and policy database and a pricing/fee database, relevant financial products are determined and provided to the customer. The inquiry type can include buying a property, refinancing a mortgage, improving a property, and/or using funds from a property.

Abstract: Location modeling may be generated for candidate locations based on validated location data. The location models for candidate locations may be based on validated location data associated with wireless access points that is validated using transaction data. Such validation may include comparing an identifier associated with candidate location data received from a client device to an identifier for a transaction account associated with a transaction from transaction data at a candidate location. Matching transaction data and candidate location data may generate validated location data to be used in generating location models for candidate locations.

Abstract: A method, apparatus, and computer readable storage to implement a lending or cash advance system that can be (but is not required to be) integrated with an online commerce site. Sellers on the online commerce site can click a button or tab in their web browser that is visiting the online commerce site and information known to the online commerce site is automatically shared with a potential cash provider. The information can include sales data related to the seller's business on the online commerce site that can be applied to a formula used by a cash provider to evaluate the risk associated with lending the seller cash. A financial account used by the seller can rapidly receive the cash loan (if approved) and payments received by the seller from buyers would go into this financial account which is then used to automatically pay the cash provider back at agreed upon terms.

Abstract: A banking pipeline for processing various transactions for multiple financial instruments is disclosed herein. The pipeline may have three distinct interpreters, a transaction interpreter, a rollup interpreter, and a rules interpreter. Different aspects of the transaction may be performed on separate interpreters and each interpreter may perform its aspect of the transaction before the next interpreter begins.

Abstract: The present disclosure relates to methods, systems, and storage media for detecting events based on updates to node profiles from electronic activities. Exemplary implementations may access an electronic activity transmitted or received via an electronic account associated with a data source provider; generate a plurality of activity field-value pairs; maintain a plurality of node profiles; identify a first state of a first node profile of the plurality of node profiles; update the first node profile using the electronic activity; identify a second state of the first node profile subsequent to updating the first node profile using the electronic activity; detect a state change of the first node profile based on the first state and the second state; determine that the state change satisfies an event condition; and store an association between the first node profile and an event type corresponding to the event condition.

Abstract: A transfer platform can allow users to participate in campaigns based on one or more types of user activity data and corresponding activity values set by the users. The transfer platform can receive the user activity data from one or more sources, such as user devices and data source platforms. Based on received user activity data, and corresponding activity values, the transfer platform can determine transfer amounts to be transferred from one or more source accounts to one or more destination accounts. Accordingly, the transfer platform can implement transfers based on user activity data that indicates user engagement in one or more activity types.

Abstract: A system for managing a financial account in a low cash mode. The system may include a memory storing instructions, and a processor configured to execute the instructions to perform operations. The operations may include providing an interface; providing a notification to a user when a balance in the first account is deemed to be in low cash mode; presenting, when the first account balance is deemed to be in low cash mode, an option for a transfer request; receiving, a selection of the option for the transfer request to connect the first account with a second account; transferring funds from the second account to the first account; notifying the user that funds have been transferred from the second account to the first account; and further notifying the user that the balance in the first account is greater than the threshold value.

Abstract: An example method and system for income determination analysis is disclosed. A document packet of income related documents is converted to an image file. The image file is split into separate documents and the separated documents are classified. An automated scanning tool is selected for the separated documents. Income related data is determined from the separated documents. An interface may be generated based on the confidence of the determined income related data for operator input and validation of the income related data. Multiple models are applied for calculation of income. A virtual panel is provided that incorporates the results of the multiple models to determine if further analysis is required.

Abstract: A method of validating an enterprise phone number service request is provided. The method includes generating, by an enterprise validator, an authentication code corresponding to a phone number and transmitting the authentication code to an enterprise. The method further includes transmitting, by an enterprise to a service provider, a service request that includes the authentication code and identifies a service corresponding to the phone number. The method further includes transmitting, by the service provider to the enterprise validator, a validation request that includes the authentication code and identifies the phone number. The method further includes validating, by the enterprise validator, that the authentication code in the validation request matches the authentication code generated by the enterprise validator; and, upon validation, providing, by the service provider to the enterprise, a service for the phone number.

Abstract: A system including an e-commerce server configured to communicate with a rent-to-own (RTO) management application and a consumer device is disclosed. The e-commerce server includes: i) an e-commerce application configured to provide an e-commerce website to the consumer device, the e-commerce website having a plurality of e-commerce user interfaces including a checkout interface, and ii) a RTO plug-in integrated with the e-commerce application to facilitate a RTO transaction through the e-commerce website. The RTO plug-in is executable by the e-commerce server to: i) integrate a RTO control element in the checkout interface, wherein the RTO control element is selectable to initiate the RTO transaction as a payment option for a good, and ii) after selection of the RTO control element, provide to the consumer device one or more than one RTO user interface received from the RTO management application, to facilitate completion of the RTO transaction through the e-commerce website.

Abstract: Techniques are disclosed for applying a trained machine learning model to incoming voice communications to determine whether the voice communications are genuine or not genuine. The trained machine learning model may identify vocal attributes within the target call and use the identified attributes, and the training, determine whether the target call is genuine or not genuine. An applied trained machine learning model may include multiple different types of trained machine learning models, where each of different types of machine learning models is trained and/or configured for a different function within the analysis.

Abstract: The disclosure describes embodiments of systems, methods, and non-transitory computer readable storage media that enable network transactions between user accounts belonging to different network transaction platforms and unify user account modifications across user accounts on different network transaction platforms. For instance, the disclosed systems can cause two or more network transaction platforms to transmit and/or receive transactional values from one or more intermediary holding accounts upon receiving network transaction requests between user accounts belonging to the two or more network transaction platforms. In addition, the disclosed system can unify user account data on different network transaction platforms by modifying or updating the user account data (e.g., user attributes) by propagating schematized data messages to the one or more other network transaction platforms with instructions to modify or update the user attributes on other user accounts related to the user account.

Abstract: Systems and methods are disclosed for providing non-intrusive advertising content to users. The method includes receiving user input reflecting user content preferences for receiving desired content related to specific topics in lieu of standard advertising content. The method may further include receiving a web request for electronic and then retrieving desired content based on user content preferences. Thereafter, the method may include choosing non-intrusive advertising content and generating one or more datagrams including the desired content and the non-intrusive advertising content. The requested electronic content along with generated datagrams content may then be provided for displaying.

Abstract: Implementations described herein relate to methods, systems, and computer-readable media to determine transaction specific parameters. In some implementations, a method includes receiving a plurality of data records, wherein each data record comprises a plurality of attribute values associated with a transaction, grouping the plurality of data records into two or more clusters, wherein each cluster is associated with a respective set of attribute values, identifying a respective set of rules for each cluster of the two or more clusters, loading the data records and the respective set of rules for each cluster into a respective cache, and analyzing, in parallel with a plurality of program threads that execute on a respective processor associated with the respective cache and without accessing an external memory, such that the cache provides data locality for the data records using the respective set of rules.

Abstract: A network node includes at least one processor, at least one memory, and at least one network interface. The network node is configured to be within a plurality of network nodes communicatively coupled in a peer-to-peer network of network nodes implementing a distributed ledger. The network node is configured to be communicatively coupled to at least one remotely located computing device through the at least one network interface. The at least one processor is configured to determine a split ratio for a new split of security tokens held in at least one address of the distributed ledger. The at least one processor is also configured to store an indication of the split ratio without updating token balances for all of the at least one address in a list of addresses holding at least one of the security tokens.

Abstract: User identities can managed at an organization level, instead of across multiple individual resource accounts. In a resource provider environment, access to various resources and services may require users to have identities with specific resource accounts. Users can instead be associated with organization accounts, or virtual accounts that are not associated with specific resources or services. The organization accounts are attached at the appropriate location(s) in an organizational hierarchy. A user having an organization account can project the identity in any sub-account in the organization hierarchy. This can include any lower-level resource account, or can child accounts under a relevant branch of the hierarchy. A user can validate against the organization account, and receive access to the relevant service or resources using the identity projected in the corresponding resource account.

Abstract: A method for predicting a financial product price based on an accumulation distribution indicator includes the following steps: step S1: inputting, by a user, a ticker symbol; step S2: calculating, by a system, an accumulation distribution indicator value based on daily trade data; step S3: calculating an accumulation distribution interval and an average candlestick; step S4: determining whether the accumulation distribution indicator breaks through the accumulation distribution interval upward or downward; if the accumulation distribution indicator breaks through the accumulation distribution interval upward or downward, going to step S6, otherwise, going to step S5; step S5: displaying a chart with the average candlestick; and step S6: displaying a breakout mark, where the breakout mark is a rising mark if an upward breakout occurs or is a falling mark if a downward breakout occurs, and displaying the chart with the average candlestick.

Abstract: The present invention is a system and method for recording right transfer in blockchain. There are three types of tokens, each of which may include a definition of rights. The rights can also be split or merged during circulation of tokens. The blockchain system ensures totality of rights does not increase nor decrease before and after circulation.

Abstract: A cloud migration framework may include an enterprise application data store that contains electronic records associated with enterprise applications. Each record may include, for example, an electronic record identifier and enterprise application parameters. A data repository stores a catalogue of cloud computing patterns. A back-end application computer server retrieves information from the enterprise application data store and, based on enterprise application parameters, creates a move group representing a subset of the enterprise applications. For each application in the move group, the computer server identifies whether an appropriate cloud computing pattern exists in the catalogue. If an appropriate cloud computing pattern is identified, it is used to automatically create a reference implementation of the enterprise application in a cloud computing environment.

Abstract: An exemplary system according to the present disclosure comprises a computing device that in operation, causes the system to receive financial product or financial portfolio data, map the financial product to a risk factor, execute a risk factor simulation process involving the risk factor, generate product profit and loss values for the financial product or portfolio profit and loss values for the financial portfolio based on the risk factor simulation process, and determine an initial margin for the financial product. The risk factor simulation process can be a filtered historical simulation process.

Abstract: A method, performed by an initiator system, for securely initiating a checkout with an enrolled device includes the steps of receiving, from an untrusted device, a checkout request including a user identifier; determining whether the user identifier is associated with one of a plurality of enrolled devices in an enrolled device database; responsive to a determination that the user identifier is associated with an enrolled device, retrieving user data associated with the user identifier; sending, to the untrusted device, a request for instructions to perform a checkout with the enrolled device; receiving, from the untrusted device, instructions to perform the checkout with the enrolled device; generating a request to perform the checkout with the enrolled device; and initiating a checkout by sending, to a communication system, a request to initiate a checkout with the enrolled device over a secure communications channel.

Abstract: An exemplary system according to the present disclosure comprises a computing device that in operation, causes the system to receive financial product or financial portfolio data, map the financial product to a risk factor, execute a risk factor simulation process involving the risk factor, generate product profit and loss values for the financial product or portfolio profit and loss values for the financial portfolio based on the risk factor simulation process, and determine an initial margin for the financial product. The risk factor simulation process can be a filtered historical simulation process.

Abstract: The system and methods described herein allow users to give their applicant information when seeking to purchase a good with financing from multiple potential lenders, and may be pre-screened by one or more rule sets implemented by a marketplace client in an eligibility analysis to ultimately submit applicant information to a subset of the multiple potential lenders which are found to be suitable for lending to an applicant based on the applicant information, wherein lender microservices are then run in a jailed, firewalled, and self-contained, autonomous environment, and the results of said lender microservices are reported to the user and may be used to change the one or more rule sets implemented by the marketplace client for future pre-screening of applicants.

Abstract: A computer-based method includes receiving an activity data associated with a user; where a first user activity profile of the activity data is associated with: a) a first profile identifier, and b) a first instrument, where the first instrument comprises a first security measure; receiving an authentication request to authenticate an identity of the user; generating a security challenge to identify the user; the security challenge being based on a second user activity profile of the activity data; receiving a security response to the a security challenge from an instrument generation module; the security response comprising a second profile identifier associated with a second instrument; authenticating the user based on the security response; generating a third profile identifier to replace the first profile identifier; instructing the instrument generation module to dispense a third instrument; where the third instrument includes: a) the third profile identifier, and b) a second security measure.

Abstract: Data account management systems and methods are described. A server is in communication with one or more information source systems, at least one user device associated with at least one user and one or more electronic data accounts associated with the user. The server links the electronic data accounts, monitors data among the information source systems and the linked accounts for any changes in activity associated with the user, predicts a behavioral activity of the user via machine learning based on at least one of the monitored data and historical data associated with the user, identifies at least one notification instruction specific to the user based on the predicted behavioral activity, and generates an interactive graphical user interface (GUI) for display on the user device. The interactive GUI presents one or more of the notification instruction and a user profile of the at least one user among the linked accounts.

Abstract: Methods and systems for facilitating photo-based estimation are described. In an aspect, a server is configured to send via a communications module to a remote computing device a first signal comprising a chat interface. The server may receive, via the communications module and from the remote computing device, a second signal representing input received at the remote computing device through the chat interface. The server may identify an account associated with the remote computing device and retrieve policy data associated with the identified account from the data store. The server may automatically evaluate the input and policy data against predetermined criteria to determine whether a claim has a low risk level and, when the claim is determined to have a low risk level, engage a photo-based estimation module.

Abstract: A virtualized blockchain forest includes a plurality of individual blockchains. Each individual blockchain of the plurality includes a blockchain height, a genesis block, and at least one additional block. The virtualized blockchain forest further includes a plurality of participating processors that make up a consensus pool, and a blockchain forest height having a time-sequenced start-to-finish length of blocks among the collective plurality of individual blockchains. The virtualized blockchain forest is configured to aggregate different ones of the plurality of individual blockchains, and is further configured to terminate individual ones of plurality of individual blockchains.

Abstract: Aspects of the disclosure relate to enhanced tracking of processed events. A computing platform may receive event processing identifiers corresponding to a particular event. Using the event processing identifiers, the computing platform may generate event linkage information corresponding to the particular event, and may store the event processing identifiers along with the event linkage information. The computing platform may receive a request to access event lifecycle information corresponding to the particular event. Using the event linkage information, the computing platform may identify a plurality of event processing systems performed actions associated with the particular event. The computing platform may request and receive, from each of the plurality of event processing systems, system-specific event lifecycle information corresponding to the particular event.

Abstract: Systems, methods, and apparatuses for providing a customer a central location to manage permissions provided to third-parties and devices to access and use customer information maintained by a financial institution are described. The central location serves as a central portal where a customer of the financial institution can manage all access to account information and personal information stored at the financial institution. Accordingly, the customer does not need to log into each individual third-party system or customer device to manage previously provided access to the customer information or to provision new access to the customer information. A user additionally is able to have user data and third-party accounts of the user deleted from devices, applications, and third-party systems via a central portal. Restrictions on how user data is used by devices, applications, and third-party systems can be imposed via a central portal.

Abstract: Systems and methods for generation and aggregation of point-of-sale account data and generation of a marketplace platform are disclosed. Transaction information may be utilized to value one or more businesses, and those valuations may be presented to potential buyers in a generated marketplace platform. A remote system may facilitate a sales agreement between a buying merchant and a seller merchant by, for example, transferring funds from a remote system account to the selling merchant's account and accepting repayment from the buying merchant over time. Merging of transaction information and/or user accounts pursuant to the sales agreement may also be performed.

Abstract: A system for reconciling invoices includes: an input port receiving benefits information related to insurance benefits recipients and invoices from one or more benefits vendors; a rules engine enforcing rules on the benefits information, the rules engine being configured to monitor the benefits information for determining exceptions based on the rules; a processing unit including a reconciliation module, the reconciliation module analyzing and comparing each invoice against the benefits information to detect any inaccuracies in each invoice, the inaccuracies being designated as exceptions. For each invoice where there is at least one exception, the processing unit is configured to determine whether to include, exclude, or modify the invoice based on a feedback signal from a client device. In response to the feedback signal indicating exclude, the processing unit calculates an adjusted invoice amount by excluding at least one fee associated with the at least one exception.

Abstract: Disclosed are various aspects of computer-implemented systems and methods for enhancing safety in real estate transactions. In one aspect a user is provisioned with a real estate mobile application with a safety engine on a mobile computing device. Next, the user enters parameters or the application automatically populates parameters based off at least a safety timer limit, a time extension amount, an emergency contact, a timer authentication code, or an emergency code. Next, a user selects a property and visits, wherein the application initiates GPS tracking and checks the user in. The user's property visits, check in and check out are logged and streamed to a database for verification. If the user fails to check out or respond to the timer authentication code an emergency service is alerted and or the device emits an emergency audible sound.

Abstract: The present invention relates to a smart pension management system and a driving method therefor. The smart pension management system comprises: a number-of-accounts calculation unit for calculating the number of pension accounts by using user age information, life expectancy information, and pension indexes; a payment amount determination unit for determining a monthly pension payment by using the number of pension accounts calculated by the number-of-accounts calculation unit; and a payment processing unit for paying, to a user's account, the monthly pension payment determined by the payment amount determination unit, and thus a client can transparently and easily check pension payment details and management situation.

Abstract: Methods for computer generation of graphical user interfaces are disclosed. The interfaces may provide representations of electronic order book data, including prospective orders and the impact of the prospective orders on the order book. Generating the graphical user interfaces can comprise calculating cumulative digital asset purchase order volumes and cumulative digital asset sell order volumes that are available in the order book at each order price. Graphical representations of a prospective order and a post-order order book may be generated and overlaid on the current order book graphical representation.

Abstract: Systems and methods are provided for implementing a machine learning approach to modeling entity behavior. Fixed information and periodically updated information may be utilized to predict the behavior of an entity. By incorporating periodically updated information, the system is able to maintain an up-to-date prediction of each entity's behavior, while also accounting for entity action with respect to ongoing obligations. The system may generate behavior scores for the set of entities. In some embodiments, the behavior scores that are generated may indicate the transactional risk associated with each entity. Using the behavior scores generated, a user may be able to assess the credit riskiness of individual entities and instruct one or more individuals assigned to the entities to take one or more actions based on the credit riskiness of the individual entities.

Abstract: Systems, methods, and apparatuses for providing a central location to manage permissions provided to third-parties and devices to access and use user data and to manage accounts at multiple entities. A central portal may allow a user to manage all access to account data and personal information as well as usability and functionality of accounts. The user need not log into multiple third-party systems or customer devices to manage previously provided access to the information, provision new access to the information, and to manage financial or other accounts. A user is able to have user data and third-party accounts of the user deleted from devices, applications, and third-party systems via a central portal. The user is able to impose restrictions on how user data is used by devices, applications, and third-party systems, and control such features as recurring payments and use of rewards, via a central portal.

Abstract: A multivariate predictive system processes usage based data that includes a database engine that provides access to a plurality of database management systems that mine diverse sources of usage based data. A digital filter selectively filters data streams that include usage based data. A sampler automatically divides the filtered data into sample groups and stores the sample groups in a memory. The sampler divides the filtered data according to insurance rating variables processed by a processor programmed to underwrite an insurance product and rate that insurance product. Some samplers store the divided filter data in a local memory. A multiplier multiples rating factors preprogrammed with the insurance rating variables with a base rate of insurance to determine an insured's insurance premium.

Abstract: Systems and methods to facilitate a customization and proliferation of models are described. The system receives, via a first interface, table information and communicates the table information to a first model. The first model includes logic to process the values to generate a column of predicted values. The system receives a column of predicted values from the first model. The system appends the column of predicted values to the table information to generate appended table information. The system communicates, via a second interface, the appended table information to a second state including a second plurality of models. The sequence of states is associated with a plurality of interfaces including the first interface and the second interface. The interfaces facilitate a customization and proliferation of models.

Abstract: Disclosed are systems and methods for using a transaction to collect additional transaction information. The method may include: receiving transaction information indicating that a transaction of one or more products and/or services has been made by a user from a merchant; when the transaction information is received, scanning a user e-mail account to identify a receipt for the transaction within an e-mail of the user e-mail account, wherein the receipt is indicative of a transaction price; when the receipt for the transaction is identified: extracting information of the one or more products and/or services from the receipt; and based on the extracted information, automatically generating and submitting a price adjustment claim for the one or more products and/or services when a price lower than the transaction price is found; and when the receipt for the transaction cannot be identified: automatically submitting information about a missing receipt to a fraud system.

Abstract: A method employs consumer permissioned financial data to generate an updated credit score following a consumer authorization to access to at least one demand deposit account of the consumer for use in generating the credit score for the consumer. The consumer permissioned financial data may be sourced from any one of a plurality of aggregators where the aggregators employ different data structures for the financial data. The financial data is processed to automatically normalize the data received from an aggregator by applying a common classification system across the plurality of aggregators to classify a first set of data fields; and automatically, regardless of whether an updated credit score is advantageous for the consumer and independent of any further consumer permission, generating the updated credit score using a combination of credit file data for the consumer and the financial data received from the aggregator.

Abstract: A computer system is described that is configured to calculate probable risks of assets being transferred away from an institution that is currently holding the assets. In order to reduce transfers of assets from an institution, the computer system is configured to predict a likelihood of transfer of the asset from the institution based on the client data. The computer system is configured to predict a risk of transfer of the asset that takes into account the value of the asset. For example, particular higher value assets may be more valuable to the financial institution than other assets given a comparable likelihood of transfer. The computer system is further configured to propose and/or prioritize actions, such as potential advising opportunities, to minimize the risk of transfer of the asset from the financial institution.