Abstract: An embodiment for managing peer-to-peer (P2P) donations in an online transaction is provided. The embodiment may include receiving data relating to a donation agreement from a donor. The embodiment may also include selecting one or more authentication techniques to identify a donee. The embodiment may further include generating a unique redemption authentication token for the donee. The embodiment may also include creating a transient donee account including the generated unique redemption authentication token. The embodiment may further include transferring monetary funds to the created transient donee account with instructions to redeem the transferred monetary funds. The embodiment may also include receiving a request from the donee to redeem the transferred monetary funds utilizing the generated unique redemption authentication token. The embodiment may further include in response to determining the donee is able to be verified, approving the received redemption request.

Abstract: Techniques described herein are directed to automated platform-based donation matching and security. An interactive element with data embedded therein is generated and, in response to an interaction with the interactive element, a request to transfer funds from an account of a user to another account associated with a group of one or more users is generated. When the request is received, at least one matching sponsor is identified from context data. A payment service facilitates a transfer of funds from the account of the user to a holding account of a payment service, and the payment service facilitates a transfer of additional funds from an account of the at least one matching sponsor to the holding account. Once a condition has been satisfied, the payment service transfers the funds and the additional funds from the holding account to an account associated with the group of one or more users.

Abstract: The present invention relates to an online pet joint custody method, server, and system. The online pet joint custody method according to the present invention comprises: a first step in which an offline guardian terminal applies a registration of a shared pet by transmitting information of a pet being raised, and a raising condition; a second step in which a shared pet server receives the registration application of the shared pet, and registers the pet as a shared pet; a third step in which an online guardian terminal accesses the shared pet server to identify the information of the pet registered as the shared pet and apply joint custody of the shared pet; and a fourth step in which, when the shared pet server provides the application of joint custody to the offline guardian terminal, and receives an approval on the joint custody from the offline guardian terminal, the shared pet server registers a user of the online guardian terminal as a joint custodian.

Abstract: A method is provided, comprising: obtaining training data including historical transcripts from historical user interactions, and indications of workflow statuses associated with each of the historical transcripts; training a machine learning model to classify transcripts from user interactions based on workflow status using the training data; applying the trained machine learning model to a new transcript from a new user interaction in order to identify a workflow status associated with the new transcript; generating a message to a user associated with the new user interaction based on the identified workflow status; analyzing the new transcript using a natural language processing algorithm to identify one or more triggers associated with the new transcript; modifying one or more parameters associated with the generated message to the user based on the one or more triggers associated with the new transcript; and transmitting the message to a device associated with the user.

Abstract: Methods, systems and computer program products are provided for a machine learning text interpretation model configured to determine customer scenarios, which may be unsupervised. Text (e.g., customer comments) may be processed by a text interpretation model to identify topics. Text features may be processed together or separately (e.g., in parallel flows) to identify one or more sets of topic categories. Text features (e.g., customer pain point comments and customer blocker comments) may be preprocessed, summarized, vectorized, topic modeled, clustered, and analyzed to select topic categories. A topic modeler may be selected from multiple topic modelers based on perplexity scores. The selected topic categories after clustering may be considered top customer scenarios, which are identified after operation of the machine learning (e.g., unsupervised) text interpretation model.

Abstract: The principal object of the embodiments herein is to disclose a systems and methods to enable stakeholders to define one or more holistic measures of composite performance score, to derive an a priori estimate of the composite performance score of the system as well as its components and stakeholders, and continuously update the same in a real-time, trusted and automated manner, by accounting for technical, operational as well as financial performance of the system elements in an automated, trusted, real-time manner. Another object of the embodiments herein is to disclose methods for predicting technical KPIs of LiBs over time for a given LiB asset for the specific operating and environmental conditions in which the battery pack is to be used in.

Abstract: In a general aspect, a method can include receiving, by an electronic device, a visual scene; identifying, by the electronic device, a plurality of elements of the visual scene; and determining, based on the plurality of elements identified in the visual scene, a context of the visual scene. The method can further include applying, based on the determined context of the visual scene, at least one filter to identify at least one element of the plurality of elements corresponding with the at least one filter; and visually indicate, in the visual scene on a display of the electronic device, the at least one element identified using the at least one filter.

Abstract: Programs, systems, and methods for providing cloud-based provisioning, dynamic cost estimation, and automated cost reporting are described herein. In some embodiments, a software application blueprint may be created for providing applications, services, content and integrations to a user through a web service provider. The software application blueprint may comprise product landscapes including templates referencing inventories from a database to obtain elements of the applications, services, content, and integrations. The product landscapes may be connected to a TCO calculator and a TCO reporter for estimating cost and determining prices and reporting costs to the user.

Abstract: An environmental impact management device includes an emission right acquiring unit that acquires emission right data indicating a right to emit a predetermined amount of chemical substance, a load acquiring unit that acquires manufacture load data indicating an amount of the chemical substance emitted by manufacture of an article, and a use fee calculating unit that calculate a use fee of the article on the basis of a price of the emission right data and the amount of the chemical substance emitted by manufacture of the article.

Abstract: A method of setting a listing price for an item is disclosed. One or attributes of the item are determined based on data entered into fields of a listing user interface. One or more additional items are identified based on a comparison of one or more attributes of the one or more additional items with the one or more attributes of the item. Sales information associated with the one or more additional items is determined. A range of suggested prices and at least some of the sales information is incorporated into a selection user interface region of the listing user interface. Based on a selection of a suggested price from the range of suggested prices, a preview of the listing as it would appear in a search results page with the one or more additional items is presented in the listing user interface.

Abstract: Described herein is a method and system for collection creation. The collection is a curated selection of product and/services presented to an online consumer. The products or services are derived from an electronic catalogue of an online store. The collection creation system comprises a processor, a collection creation application module installed on the online store, a database repository of templates, and a memory containing instructions, when executed by the processor, configure the system to apply the templates to the electronic catalog to automatically create curated collections of product items; and to activate the create collections and display the collections to the online consumer. A curated collection consists of a set of defined parameters for a particular theme. Curated collections enable the retailer’s consumers to browse the inventory of the retailer in an intelligent and thematic manner.

Abstract: At least one embodiment of the invention relates to a process for estimating a cabinet installation comprising a series of steps. This includes creating a cabinet brand, creating a pre-set set of layouts. The user then inputs the dimensions and is then provided with an array of suitable layouts based upon the dimensions. Once the user selects a layout and among different brands, the system then creates cost options for furnishing a layout with cabinets.

Abstract: Methods and systems for on-platform purchases are described. A client device may, based on brand information or product information associated with primary content or secondary content, request additional product information.

Abstract: Search techniques are described that support locating and displaying prospective objects in digital images based on a removed object. A digital image, for instance, is received by a computing device as an input depicting a physical environment with various objects and displayed in a user interface. An object depicted by the digital image is removed. An aspect of the removed object is identified. A search system leverages the aspect to locate a prospective object. The prospective object is configured for display within the digital image. As a result, the digital image is displayed in the user interface as having the configured prospective object depicted in the physical environment.

Abstract: One or more systems and/or methods for product similarity detection and recommendation are provided. Users may view articles and/or other content that includes images depicting products that may be of interest to the users. These images are processed using image processing functionality such as computer vision to identify the products depicted by the images. A vector embedding model is used to generate product vector representations of the products. Catalog items that are available from a catalog to supplement the articles and other content may be processed to generate catalog item vector representations. When content (an article) with an image depicting a product is to be displayed to the user, similarity between a product vector representation of the product and the catalog item vector representations is determined in order to identify and display catalog items depicting products that are similar to the product depicted by the image in the content.

Abstract: Disclosed are systems and methods for determining quality of item listings in an online retail environment. A method can include receiving, by a computing system, item listing data having information about items of item categories available in the online retail environment for purchase at computing devices of end consumers, determining, for each of the item categories, one or more quality index scores based on the information included in the item listing data, determining, for each of the item categories, a composite quality index score based on aggregating the quality index scores for the items in each of the item categories, and generating, based on the composite quality index score, output for each of the item categories for presentation on a display screen of a computing device of a retail employee. The quality index scores can quantify quality levels of the item listing data.

Abstract: A method of determining item features and organizing an interface according to the features includes determining a plurality of features of a plurality of items, the plurality of items accessible through an electronic interface, applying a plurality of machine learning models to the determined features, wherein each of the machine learning models calculates a correlation of each feature to characteristic determinative of user selection on the electronic interface, calculating respective Shapley values of each correlation determined by each of the plurality of machine learning models, determining one or more of the item features that are most strongly correlated with the determinative characteristic according to the respective Shapley values, and causing the electronic interface to be organized according to the determined most strongly correlated item features.

Abstract: The present disclosure provides a product recommendation system and method for recommending products to add to a current transaction. The method includes, during a transaction process for one or more products: computing a parcel attribute of an expected parcel for shipping the one or more products, the parcel attribute being a weight or a dimension of the expected parcel, and identifying an applicable shipping rate for delivering the expected parcel. The method also includes determining an attribute increase threshold that corresponds to an increase in the shipping rate that is within a shipping rate increase threshold, identifying additional products each having a corresponding attribute that is within the attribute increase threshold, and generating a recommendation for the additional products in real-time during the transaction process. Responsive to receiving selection of one of the recommendations, including the corresponding additional product in the transaction process.

Abstract: The present invention provides a smart window display comprising: a display; a camera for identifying a user; a communication unit for communicating with an external device; and a control unit, wherein the control unit provides a personalized recommendation on the basis of the physical characteristics and style characteristics of the user identified through the camera, and when a signal to purchase a product in the personalized recommendation is received from the user after the personalized recommendation is provided, performs a payment process for the product.

Abstract: A system for searching one or more images of goods includes a shopping mall server connected to a plurality of user terminals and configured to provide the user terminals with similar goods images matching a plurality of input goods images transmitted from the user terminals as a search result for recommended goods; and an input image analyzer communicationally connected with the shopping mall server and configured to receive information on the plurality of input goods images from the shopping mall server, calculate feature vectors corresponding to the input goods images, and transmit the calculated feature vectors to the shopping mall server. The shopping mall server includes a first database storing goods images for respective goods held by the shopping mall server and feature vectors corresponding to the goods images and a second database storing information on the goods images transmitted from the user terminal.

Abstract: An online system receives a recipe from a customer mobile device. The online system performs natural language processing on the recipe to determine parsed ingredients. For each of one or more of the determined parsed ingredients, the online system maps the parsed ingredient to a generic item. The online system queries a product database with the mapped generic item to obtain one or more products associated with the mapped generic item. The online system applies a machine-learned conversion model to each of the one or more products to determine a conversion likelihood for the product. The conversion model may be trained based on historical data describing previous conversions made by customers presented with an opportunity to add products to an order. The online system selects a product from the one or more products based on the determined conversion likelihoods and adds the selected product to an order.

Abstract: In some cases, a delivery service system may include a handheld electronic device for use with a delivery service (e.g., a grocery delivery service). When operating in a voice input mode, the handheld electronic device may record and store audio data in memory. The stored audio data may be communicated from the handheld electronic device (e.g., via a Wi-Fi connection) to the delivery service for speech processing. When operating in a scanner input mode, the handheld electronic device may record and store item identifier information (e.g., barcode data) in memory. The stored data may be communicated to the delivery service for item identification processing. In some cases, a user interface associated with the delivery service may allow the user to review and confirm an order prior to submission of the order for delivery.

Abstract: Systems and methods for determining whether a transaction between a consumer and a retailer qualifies for the consumer to receive an offer to send a gift received as a result of the transaction to a separate recipient. A gifting service system receives order confirmation details associated with the transaction, and assesses a variety of information from various sources to determine if the transaction qualifies for the offer. If so, the offer to send a gift is presented to the consumer. Once the consumer accepts the offer, the gifting service system obtains various selections and items of information, and sends a gift notification to an intended recipient. The gifting service system interacts with the recipient to obtain various selections and items of information to facilitate delivery of the gift to the recipient.

Abstract: Example gesture based cross-channel commerce retail systems and methods are provided. Some of the example systems and methods permit a consumer to complete a Store Pick Up order, i.e., an order placed by the consumer via computer, mobile device, telephone, fax, mail-order, etc., by gesturing with a mobile device near a digital kiosk and optical sensor at a store pick up location. The mobile device and/or the digital kiosk may display media content to the consumer while the consumer completes the Store Pick Up order. In another example system, a digital kiosk is located in a public area such as an airport, shopping mall, train station, or stadium. The digital kiosk displays media content to the consumer, and the consumer may transfer to a mobile device such media by gesturing with the mobile device near the digital kiosk.

Abstract: Disclosed herein are an apparatus, method, and non-transitory computer readable medium that improves the functioning of the computer. A drop down menu with different options may be rendered for an order associated with a product on which a cursor hovers. In response to a selection of a parameter option, an order for a product is transmitted.

Abstract: A real-time transaction and marketing management system and a method for the same is introduced herein, for usage with a specific social network platform, which utilize at least one image-capturing device to capture live image streaming data of a physical-trading place where a specific physical good is being exhibited, and a remote webserver to produce a number of icons, respectively indicative of marketing information relevant to the specific physical good, on a basis of the live image streaming data, thereby enabling a purchaser/vendor terminal displaying unit to display a dedicated managing webpage thereon which contains an instant physical-trading scene where the icons are inserted for clicking. With the system, marketing steps, good information and client data, of the physical-trading place can be electronization-managed, for accomplishing click-and-mortar transactions, and raising a deal-making rate and a transaction confidence level.

Abstract: Systems and methods are provided for the generation of augmented reality (AR) scenery for a physical item. The AR scenery allows a customer to interact with the physical item in the real-world, while also allowing the customer to view the physical item in a virtual setting that may be tailored to the customer and/or to the physical item. According to an embodiment, an AR scene is generated for a physical item. The AR scene includes computer-generated scenery and at least a portion of an image of the physical item, where the computer-generated scenery is based on information associated with the user and/or the physical item. The AR scene is then displayed on a device.

Abstract: In a device management system 1 including a terminal 20 and a server 10 for managing a device 50 stored in a box 40, the terminal 20 includes: a transmission unit 23 that transmits information associated 5 with the device 50 and user authentication information to the server 10, and the server 10 includes: a unique device code acquisition unit 12 that acquires a unique device code from information associated with the device 50; a lock control unit 13 that instructs the box 40 to unlock; and a login control unit 14 that identifies a user based on the user 10 authentication information and allows the identified user to log in to the device 50 when the box 40 or the device 50 notifies that the device 50 has been taken out with an event indicating that the device 50 has been taken out of the box 40 as a trigger.

Abstract: A rental space management system that can operate a rental space unattended and improve user satisfaction, wherein a rental space management system includes a management server that manages a room and an image capturing unit that monitors a state of the room. The management server includes a state monitor, an original state restoration determiner, and a determination result annunciator. The state monitor causes the image capturing unit to monitor the state of the room. The original state restoration determiner determines whether original state restoration of the room is required by comparing a state at the start of use and a state at the end of use of the room monitored by the state monitor. When the original state restoration determiner determines that the original state restoration is required, the determination result annunciator announces the determination result of the original state restoration determiner to an administrator of the room.

Abstract: Systems and methods for selling virtual items on multiple online sales platforms simultaneously are disclosed. Exemplary implementations may: receive a sales request that indicates the selling user will be offering for sale a particular virtual item through at least two online sales platforms simultaneously; assign ownership of the particular virtual item temporarily to a holding account; generate sales listings of the particular virtual item for publications on the at least two online sales platforms; effectuate the publications of the sales listings; receive indications of offers to purchase the particular virtual item; determine an accepted offer that is accepted; notify the at least two online sales platforms of whether the offers have been accepted or denied; identify a buyer's account of the buying user; effectuate assignment of the ownership of the particular virtual item to the buyer's account.

Abstract: Disclosed embodiments include systems and methods for improving the accuracy of online banking systems. In various embodiments, the system includes a user device capturing receipt information from one or more e-commerce application and a server device for associating captured receipt information with transaction data. The system may include a browser extension for facilitating automatic capture of receipt information and a matching module for associating receipt information with transaction data. In various embodiments, transactions displayed in transaction statements within an online banking application are augmented with item level data including product name, price, and vendor for each product included in a transaction.

Abstract: Systems, methods, and apparatuses for automatically detecting the risk of dealer default are described. A machine learning model may be trained using a gradient boosting technique on a dataset that includes historical lien information, historical dealer information, and historical vehicle default information. Lien information and financing information for vehicles may be received and correlated. Furthermore, a machine learning model may generate aggregate risk scores for dealers. Furthermore, determination of an aggregate risk score that exceeds a threshold risk score may cause the generation of a notification.

Abstract: Systems, methods, and apparatuses for automatically prioritizing unperfected liens are described. A machine learning model may be trained to detect a risk of dealer default. Lien information corresponding to liens for vehicles associated with dealers may be received. Prioritized lien information may be generated based on selection of the liens that satisfy criteria. Financing information for vehicles may be received and correlated with the prioritized lien information. Furthermore, the machine learning model may be used to generate risk scores associated with the liens. The liens may be prioritized based on the aggregate risk scores.

Abstract: Disclosed herein is a personal loan-lending system including, in some embodiments, a personal loan-originating system configured for originating personal loans, a personal loan-servicing system configured for servicing the personal loans, and third-party integration supporting the originating or the servicing of the personal loans. The third-party integration includes one or more application programming interfaces configured for transferring loan-related information between the personal loan-lending system and third parties such as credit bureaus, employment verification providers, or the like. The personal loan-lending system includes one or more server hosts supporting a personal loan-originating application stack and a personal loan-servicing application stack. Also disclosed herein are methods of the personal loan-lending system.

Abstract: An information display system includes a computing system that is configured to implement a user interface, access a first database storing a plurality of loan workout rules, receive loan and borrower data regarding an existing loan, and determine a plurality of loan workout options based on the plurality of loan workout rules and the received loan and borrower data. The plurality of loan workout options are displayed on the user interface.

Abstract: Systems, methods, and computer program products to provide credit decisioning based on graph neural networks. A lending network graph of a plurality of loans may be received, each loan associated with a creditor and one account. A first node of the graph may be associated with a first creditor and the second node may be associated with a first account. A graph neural network may receive a respective message from each node connected to the first node, each message comprising an embedding vector reflecting a current state of the node. The graph neural network may update weights for the first node in a forward pass. The graph neural network may receive a respective message from each node connected to the second node, each message comprising the embedding vector reflecting the current state of the node. The graph neural network may update weights for the second node in a backward pass.

Abstract: A method for facilitating automated predictive analytics of specified pools is disclosed. The method includes receiving, via an application programming interface, a bid list from an exchange platform, the bid list relating to a listing of the specified pools; parsing the bid list to identify pool characteristics for each of the specified pools; retrieving real-time market data that corresponds to each of the specified pools; aggregating historical trade data that relates to each of the specified pools; determining, by using a model, a predicted amount for each of the specified pools based on the identified pool characteristic, the retrieved real-time market data, and the aggregated historical trade data; and outputting, via the application programming interface, the predicted amount to the exchange platform.

Abstract: A dedicated social network for investment, financial news and information framework method, apparatus and system is presented. Users have the ability to include one another in their financial network, exchange financial news cards, assimilate and synthesize knowledge on stock and securities trading. Machine learning based algorithms for search and sort are used. Framework also provides within itself to invoke the trading platform to effectuate trades with appropriate exigency. Active investors and sightseers are participants, such that through their read preferences a mechanism is provided to be able to evaluate and measure the efficacy and accuracy of the news being shared on the financial network.

Abstract: Systems, methods, and computer program products are provided for facilitating high frequency processing using stored models. A method for facilitating high frequency processing using stored models is provided. The method includes receiving a set of code relating to a machine learning model configured to process data. The method also includes generating a model executable file from the set of code relating to the machine learning model. The model executable file is configured to process inputted data using the machine learning model upon execution. The method still further includes storing the model executable file on an in-memory of a local device used to process inputted data.

Abstract: The present invention is a system and method of patent tokenization that provides solutions to the limitations and drawbacks of the current patent system. The present invention implements a procedure to limit exposure and unlock new revenue opportunities through tokenization. The present invention uses blockchain technology to track chain of title, provenance, and can capture and enforce all transactions and encumbrances through smart contracts. Access to this data enables the present invention to introduce additional liquidity into the asset class by tokenizing the backend of relevant transactions, such as patent licenses, patent lending, etc. The present invention applies blockchain technology at the patent market level to transform how IP assets are obtained, managed and transacted. Permissioned Blockchain allows multiple competing parties to operate from the same common database without revealing their data, resulting in increased trust, control and privacy in the transactional process.

Abstract: A method and a system for using differential privacy techniques to provide axe obfuscation with respect to information included in an inventory axe list of available securities is provided. The method includes: obtaining first information to be included in a first inventory axe list to be published on a particular day; retrieving second information included in a second inventory axe list that was published on the previous day and/or several previous days; obfuscating the obtained first information by applying an algorithm based on the difference between the first information and the second information; and publishing the first inventory axe list by transmitting the obfuscated first information to a plurality of intended recipients. The quality of obfuscation may be measured and controlled as a function of desired privacy level and potential cost.

Abstract: Systems and methods for providing trading exclusivity/priority in response to quantity of items traded in electronic trading systems is provided. The method preferably includes receiving an incoming order for the item and determining whether the incoming order matches a current order for the item and satisfies a minimum volume requirement. When the incoming order matches a current order for the item and satisfies a minimum volume requirement, the method includes transacting a trade between the incoming order and the current order and providing a predetermined time period of exclusive trading between a participant associated with the incoming order and a participant associated with the current order.

Abstract: A system for trading a plurality of derivative financial instruments comprises a processor operable to receive a first order to buy a derivative financial instrument that represents a contestant in a contest. The processor is further operable to receive a second order to sell the derivative financial instrument. The processor is further operable to determine a market price based at least in part on the first order and the second order. The processor is further operable to execute a trade at the determined market price. The system further comprises a memory operable to store the first order and/or the second order.

Abstract: Methods, systems and devices for the creation, management and retirement of a carbon-linked security within a distributed ledger system. In an example, a method for administering at least one carbon-linked security product includes receiving a carbon footprint associated with an issuer and a confirmation of a deposit of an underlying security associated with the issuer, calculating a carbon offset amount from a ratio derived from at least the carbon footprint or an issuance of the underlying security, linking the carbon offset amount to the underlying security to create at least one carbon-linked security product, receiving a notification of a corporate action by the issuer, determining that the corporate action has an impact on the ratio, and automatically updating, based on the corporate action and the determining, the carbon offset amount in the distributed ledger.

Abstract: In some embodiments, the instant invention provides for specifically programming a computer machine to perform at lease: receiving, from a trader, a passive indication of interest (IOI) for a financial instrument, where the passive IOI is a bid or an offer and a resting liquidity; classifying the trader as at least: a trading type that is subject to a decline ratio calculation for crossing the passive IOIs, where the decline ratio calculation identifies how many eligible aggressive IOIs have been previously declined by the trader out of a total number of all eligible aggressive IOIs that were offered to such trader; receiving, from another trader, another IOI that is an aggressive IOI, where the aggressive IOI is available to be immediately crossed at the price; and determining, in real-time, an allocation of the aggressive IOI to the trader submitted the passive IOI based on the decline ratio of the trader.

Abstract: Example methods, apparatus, and computer readable storage media are described and disclosed. An example method includes receiving, by a computing device, market data related to a tradeable object. The example method includes displaying, by the computing device, a flexible price-volume indicator, the flexible price-volume indicators aligned with a specific value level in a value axis. The example method includes updating, by the computing device, a display property associated with the flexible price-volume indicator, the display property reflecting a quantity value determined based on the received market data. The example method includes displaying, by the computing device, the flexible price-volume indicator in a differentiated state based on a change in the market data.

Abstract: A Business Method Invention to transact an Independent Inventor's Intangible Assets into Industry of Inventor's native Nation. A Process means to convey license usage to top-most Governmental and Industry leadership agencies and corporations, providing the formation, booking or floating of Treasury Assets, a cash-equivalent ledger item on the Asset-Side of the Balance Sheet. Also, a net-equal tangible value Swap of the pro-se Independent Inventor's IRS-governed Fair Market Value amortization deduction, said Swap to USA Federal or other major municipality, providing Government a tool for Demand-Side economic stimulus, over a fifteen-year period, by distributing Its swap value as per capita US taxpayer or citizen or business tax relief, or synthetic pay raise, or to targeted needs situations. A business method configuring a central bank or Treasury balance asset based upon the financial value of a nation's expired Intangible Assets.

Abstract: The Reinforcement Learning Based Machine Retirement Planning and Management Apparatuses, Processes and Systems (“MRLAPM”) transforms machine learning training input, order optimization input, withdrawal policy optimization input datastructure/inputs via MRLAPM components into machine learning training output, order optimization output, withdrawal policy optimization output outputs. A machine learning training request datastructure structured to specify an optimal policy reward function and a set of training sample configuration datastructures is obtained. A set of training sample datastructures is generated using the optimal policy reward function and a specified training sample configuration datastructure. An optimal policy is determined using a reinforcement learning technique and the generated set of training sample datastructures. An optimal policy datastructure structured to specify parameters that define the structure of the optimal policy is stored.

Abstract: The embodiments herein provide a system and method to analyse properties at a scale on more than 25 distinct factors and assign them a score from 0-100 showing to identify a strong investment on a selected property using artificial intelligence model. The system collects the data various third-party systems by means of API connection, web scraping, store the data and provides the final investment ranking score using the data collected using an AI model that. A primary filter removes the properties that do not meet preliminary criteria from the acquisition pipeline. A web-based application complements the AI model’s scoring by allowing human analysts to evaluate and score the property. The scores provided by the analysts are stored for retraining the AI model. The final investment ranking score is a weighted sum of proximity score, market score and financial score.

Abstract: A computer implemented method and associated hardware provides optimization of a delivery or settlement process for a group of portfolios. Data records, identified in a portfolio data structure, are indicative of obligations between participants. A graph data structure is generated and includes vertex data records representing the participants and edge data records representing the obligations between participants. The graph structure is analyzed for at least one circular path. A first edge washing out at least a portion of the circular path is identified. An update message is generated in response to the first edge.