Abstract: A method for performing a secure payment in an offline mode in an electronic device is provided. The method includes launching a secure application at the electronic device, obtaining a nonce token from an authentication unit of the electronic device, obtaining a nonce signature from a server via a network, entering an offline mode where the electronic device is disconnected from the network, encrypting, by the secure application, a user credential input by a user using the nonce token and the nonce signature, decrypting and validating, by the authentication unit, an encrypted user credential, generating a secure object based on the decrypted user credential and a random number generated by the authentication unit and performing a secure payment based on the secure object.

Abstract: Systems and methods are provided for use in enhancing security associated with services related to payment or banking accounts, in connection with communication between consumers and consumer service call centers associated with the accounts. One exemplary method includes receiving, at a computing device, a request to authenticate a consumer to a payment or banking account from a call center associated with consumer services for the account, and soliciting a biometric from the consumer. The method also includes receiving biometric data from a communication device associated with the consumer relating to the solicited biometric, and confirming the received biometric data based on reference biometric data for the consumer. The method then further includes transmitting an authentication confirmation to the call center, when the received biometric data is confirmed, whereby the call center is able to proceed in providing the consumer services to the consumer with or without security questions.

Abstract: An account management system establishes a facial template for a user based on an image. The user computing device, signed into a payment application at the merchant location, receives an identifier from a merchant beacon device to transmit to the account management system, which transmits payment tokens based on payment account data and facial templates to the merchant POS device for each user signed in at the merchant location. The merchant POS device identifies the user by comparing a captured image of the user against the received facial templates and transmits the payment token to an issuer system. At a later time, the account management system receives, from a user computing device, a subsequent user image and generates a subsequent facial template. If the difference of the subsequent facial template is less than a threshold from the existing facial template, the subsequent facial template is associated with the user account.

Abstract: A device in a data processing system for training machine learning models receives a transaction and forwards it to at least one of a plurality of integrated control action models that use outputs of one model as inputs to other models. The models are machine learning models jointly trained for taking each control action of a plurality of control actions on the transaction to maximize an objective function based on probabilities of the control actions matching corresponding target control actions. The machine learning models include a risk model that outputs risk prediction information for a first control action that indicates whether or not to initiate processing of the transaction. The device further receives the risk prediction information from the risk model, and executes at least the first control action based on the risk prediction information.

Abstract: Technology is disclosed herein for expediting blockchain transactions. More specifically, the technology describes techniques for assessing risk associated with expediting processing of blockchain transactions received by a transaction processing platform. When a determination is made that a transaction can be expedited, the transaction processing platform can expedite the transaction, e.g., locally process the blockchain transaction, prior to receiving a verification or confirmation from the consensus network. In this manner, the transaction processing platform can act like a local cache allowing quick access and operation on permanently stored data within the blockchain with minimal or calculated risk.

Abstract: In one embodiment, a cash machine, such as a casino kiosk or a bank ATM, charges a varying surcharge to patrons requesting cash withdrawals, where the size of the surcharge depends on previous requests for cash-withdrawal transactions. In general, whether or not a previous patron agreed to complete a previously requested cash withdrawal having a specified surcharge may affect the size of the surcharge offered to the next patron requesting a cash withdrawal. For example, if the previous patron completed the previous transaction, then the cash machine might increase the surcharge offered to the next patron and, if the previous patron failed to complete the previous transaction, then the cash machine might decrease the surcharge offered to the next patron. The invention can be applied to types of transactions other than cash withdrawals from cash machines, where customer touchpoints adjust current prices based on the history of previous transactions.

Abstract: A method for contextual authentication based on computing devices includes: storing an account profile related to a transaction account including an account identifier and a timestamp and a device geolocation for at least two computing devices; receiving an authorization request for a payment transaction including the account identifier, a transaction geographic location, and a transaction time; identifying an authentication score for the payment transaction based on a comparison of the transaction time and transaction geographic location to the timestamp and device geographic location for each of the at least two computing devices; and transmitting the identified authentication score and received authorization request to a financial institution associated with the transaction account.

Abstract: A method for providing a gift includes receiving a gift token creation request representative of a selection of a gift recipient and gift limitations from a first computing device. The method includes generating a tokenized PAN associated with a gift account and transmitting the tokenized PAN and gift limitations to a second computing device. The method includes detecting a transaction authorization request that is representative of an attempted transaction at a merchant POS device based on monitoring of transaction authorization data originating from a plurality of merchant POS devices. The transaction authorization request represents an attempted tokenized PAN, an attempted transaction amount and a merchant code. The method includes determining that the attempted tokenized PAN matches the tokenized PAN associated with the gift account.

Abstract: A system and method are disclosed and include databases that store data describing electronic communication between one or more user devices and one or more company devices and a computer. The computer displays a graphical user interface for monitoring communication activity of one or more one or more user devices and one or more company devices, to one or more company devices and monitors communication activity over one or more communication channels. The computer also records and stores the communication activity in the databases. The computer further displays a list of rules, the list of rules comprising triggers, conditions and actions for each of the one or more rules and a flow of each rule associated with the company of the one or more company devices and executes one or more actions responsive to one or more triggers, conditions or actions of each of the one or more rules.

Abstract: Determining relevant dates associated with a purchase of a product and allow for those dates to be sent as a reminder to the purchaser in a commerce environment.

Abstract: In one embodiment, a method is provided. The method comprises: receiving data, automatically generated in an unqualified system, configured to at least one of: control a vehicle management system in a vehicle, and obtain data from the vehicle management system; verifying integrity of the data; if the integrity of the data is verified, then qualifying the data; and if the data is qualified, then providing data to at least one qualified system in the vehicle management system.

Abstract: A method, process, and system for multi-tier resale is discussed here. Acceptance proxies may be distributed to downstream resellers and customers. The acceptance proxies may be registered with a producer who provides a service. The acceptance proxies may be registers directly, or anonymously. Escrow services may ensure each party has fulfilled its contractual obligations before access to the service is granted.

Abstract: A method and a system for publishing contextual content. A method and a system maintain user profile information on a user of referrer content associated with a referrer system, the referrer content including a reference to a referee system. The method and system may transmit the user profile information to the referee system in response to the user using the reference to access the referee system. The referee system is to adapt content, presented to a user when accessing the referee system, based on the received user profile information.

Abstract: In one example, an intent along with a parsed relevant data, associated with a received customer request, is determined. The determined intent and the parsed relevant data is validated and rectified by a validation agent. The extracted relevant data is then verified based on an outcome of the validation and rectification agent by one or more verifying software robots. Applicable rules are then extracted from associated knowledge databases based on the determined intent and the relevant data upon successful validation, rectification, and verification. The rules, associated with the customer request, are then determined from the extracted applicable rules, the determined intent and/or the relevant data. The determined rules are then reviewed by a reviewing agent. A decision is then prepared and sent to the customer based on an outcome of the reviewed determined rules by one or more decision making software robots.

Abstract: An online services system provides monitoring of user interaction with third-party content. The monitoring is performed by a script in a web page provided by the online services system, which script provides a timer invoked when the browser leaves the online services system's page for a page comprising third party content. When the online services system serves the page, the browser reads the HTML to render the page, including the script with the timer. When the user leaves the online services system page, the timer begins, and when the browser returns to a page provided by the online services system, the timer ends and duration information from the timer is provided to the online services system. Applications include measurement of the quality of interaction between users and a third party advertisers, in which time spent viewing third party content is a proxy for the quality of the interaction.

Abstract: The disclosed embodiments provide a system for performing A/B testing for search engine optimization (SEO). During operation, the system divides a set of web pages into a control group, an inbound treatment group, an outbound treatment group, and a full treatment group. Next, the system generates a first set of links from the outbound treatment group to the inbound treatment group and a second set of links within the full treatment group. The system then applies an A/B test to pairs of groups selected from the control group, the inbound treatment group, the outbound treatment group, and the full treatment group. Finally, the system outputs a result of the A/B test for use in assessing an effect of the first and second sets of links on search engine results associated with the set of web pages.

Abstract: Methods and apparatus to generate consumer data are disclosed. An example method of selecting a sample of transaction data corresponding to a membership program includes defining a first type of member of the membership program; defining a second type of member of the membership program; calculating, via a processor, a target for the sample; selecting, via the processor, a first portion of the transaction data for the first type of member in accordance with the target; generating, via the processor, an updated target by recalculating the target with the first portion of the transaction data removed from consideration; and selecting, via the processor, a second portion of the transaction data for the second type of member in accordance with the updated target.

Abstract: A market event identification method, system, and computer program product, include defining a likelihood function that maps a likelihood of a purchase of a product during an event by customers having similar customer features and estimating a likelihood of an event-driven purchase by the customers for each of a plurality of product-event combinations using the defined likelihood function.

Abstract: A method implemented on an electronic computing device includes identifying a user of an augmented reality (AR) device. Profile information is obtained for the user based on the identity of the user. An interactive game is activated on the AR device. The interactive game is tailored to the user based on the profile information. One or more rewards are provided to the user for implementing aspects of the interactive game.

Abstract: A computer device and method for processing informatic data from one or more sensor devices associated with a property covered by an insurance policy. Analysis is performed on the informatic data received from sensor devices to determine a cost associated with operating the insured property. Operational changes are identified and recommended regarding one or more operational aspects of the insured property to achieve a cost savings for operating the insured property. If one or more recommended operational changes are implemented, a cost savings is calculated which is attributable to the one or more operational changes. Monetary funds are transferred from a first financial account to a second financial account associated with a user of the insured property whereby the transfer funds amount is dependent upon the calculated cost savings.

Abstract: A system may include processing logic configured to execute instructions to cause a system to perform operations including receiving, from an intermediate device, data that originated at an endpoint node. The data may be associated with metadata that was associated with the data by the intermediate device. The operations may also include extracting one or more items from the metadata. The operations may include validating an activity of the intermediate device based on the one or more items that were extracted from the metadata.

Abstract: A method for generation and distribution of protected user-specific information includes encrypting, by a processing device of a computer system, using a first encryption key of an encryption key pair, predetermined digits of a payment account number, the encryption yielding an encrypted identifier. The processing device of the computer system then generates a machine-readable code that is encoded with the encrypted identifier and additional data. A transmitting device of the computer system transmits, via an electronic communication, the generated machine-readable code to an electronic device of a user and transmits a second encryption key, of the encryption key pair, to a specialized computer system, wherein the second encryption key is associated with the first encryption key used to yield the encrypted identifier.

Abstract: Systems and methods are described herein for supporting loyalty tiers. According to certain aspects, a custom number of loyalty tiers may be specified. Dynamic tier boundaries may be defined for each tier based upon a specified number of loyalty points, a percentile of total loyalty points, or a combination thereof. Periodic recomputing of tier boundary values can support dynamic loyalty tiers. According to certain other aspects, a user loyalty status may include a current tier and a pending tier. User loyalty points may be updated for a current loyalty activity. The updated user loyalty points may be compared with a point boundary for the pending tier and the user may be updated to the pending tier. Transacting the tier update with the server may be bypassed to reduce tier update latency. Also, immediate access at the client to features associated with the updated current tier may be supported.

Abstract: A method is provided for determining a number of current customers in a queue for a first event; estimating a current wait time of the queue for a new customer based at least on the number of current customers in the queue; predicting a future wait time of the queue for the new customer, if the new customer entered the queue after completing at least one second event prior to entering the queue of the first event, wherein estimating the future wait time is based at least on a probability of one or more future customers performing the at least one second event prior to entering the queue; determining an incentive for the new customer to complete the at least one second event prior to entering the queue based at least on the current wait time and the future wait time; and sending the incentive to the customer.

Abstract: Programmable device processors are configured by aspects of the present invention to automatically generate item offers in response to behavior attributes determined for a person receiving the offer. Said configured processor determines current personality traits for the person from analysis of activity data, identifies geographically proximate transactional channels available for presentment of an offer to the person, and generates an item offer to include attribute values that match a determined personality trait and satisfy a need indicated by demographic data applicable to the person. The configured processor select one of the available transactional channels for presentment of the item offer to the person, in response to determining an indication in the transactional behavior of a higher likelihood of acceptance by the person of the presented offer when presented via the selected transactional channel, relative to presentment via another, unselected one of the currently available transactional channels.

Abstract: A user receiving device including at least one transceiver module, an output module, a control module, and a transaction module. The at least one transceiver module is configured to receive an ad or an offer transmitted from at least one backend device to the user receiving device. The offer is directed to a product and/or service referred to in the ad. The output module is configured to display the ad or the offer on a display. The display is connected to the user receiving device. The at least one transceiver module is configured to receive a response signal transmitted from a mobile device to the user receiving device. The response signal is in response to the offer. The transaction module is configured to perform a transaction between the at least one backend device and a user of the mobile device based on the response signal.

Abstract: Gauging consumer interest of in-person visitors is described. In one or more embodiments, a promotional apparatus having a display screen and a wireless beacon is deployed at a venue. The promotional apparatus presents a video having multiple video segments. During the presentation, the beacon and a mobile device of a venue visitor communicate wirelessly to determine a proximity of the visitor to the display screen. Multiple distances are determined at multiple times. A path of movement can be determined from the distances over time. If the visitor alters a direction of travel to veer toward the screen or stops walking close to the screen, a system infers that the video has engaged the visitor's attention. By linking particular video segments to times at which the mobile device is proximate to the display screen, the system can further infer consumer interest in specific product features being shown at those times.

Abstract: An online system predicts a performance of a content item campaign based on a set of received target parameters from a content item publisher and compares the predicted performance of the content item campaign to predicted performances of comparison campaigns. The comparison campaigns are selected by performing a plurality of simulations on prior content item campaigns to estimate campaign presentation results for each prior content item campaign if presented to users with the sets of test campaign parameters. After generating histograms based on the estimated results, the online system selects prior content item campaigns for the set of comparison campaigns based on changes in histogram positions of the prior content item campaigns. The online system generates a set of estimated campaign presentation results for the content item campaign and the set of comparison campaigns for comparison.

Abstract: An approach is provided for determining a product value score. Features of a product are identified. Ranking data for each identified feature is collected. The ranking data includes popularity, stability, availability, and memory usage of each feature. Additional data for each feature are determined. The additional data includes an importance, a conversion rate, and a marketing impact of each feature. Based on the ranking data and the additional data, normalized data is generated according to characteristics of the features. Based on a data science prediction analysis which uses the identified features, weights of the features are determined. Based on initial results of the data science prediction analysis, a key product is selected from a set of products. Based on the key product and the weights, product value scores of products in the set of products are determined.

Abstract: A markdown budget user interface is provided that implements access to large-scale computational resources capable of concurrently manipulating a number of multi-million item data sets and that allows a retailer to specify inputs. The inputs include a markdown budget constraint that applies across all retailer stores, a group of store-product data sets that each include initial prices and markdown start prices of different combinations of products within all of the retailer stores, and a markdown objective, selected from a group including profit, revenue, and sales volume, to be maximized within the markdown budget constraint. The inputs are received from the retailer using the markdown budget user interface and the large-scale computational resources are invoked to determine a markdown recommendation that includes an indication of the store-product data sets that satisfy both the markdown budget constraint and the markdown objective. The markdown recommendation is provided to the retailer.

Abstract: Social media networking applications, web sites, and services creates implicit relationships between users based on their interest or participation in real-world and optionally virtual or online activities in addition to explicitly defined peer relationships. User profiles, activity entities, and expressions may be associated with metadata to assist in searching and navigation. Metadata is implicitly associated with user profiles, activity entities, expressions, or other data entities based on user behavior using metadata collector. A metadata collector is a poll, survey, list, questionnaire, census, test, game, or other type of presentation adapted to solicit user interaction. A metadata collector is associated with metadata elements. When users interact with a metadata collector, their user profiles and the data entities included in their interactions become associated with the metadata elements of the metadata collector. These metadata element associations may then be used for any purpose.

Abstract: An automatic system facilitates selection of media properties on which to display an advertisement, responsive to a profile collected on a first media property, where a behavioral-targeting company calculates expected profit for an ad correlated with the profile and arranges for the visitor to be tagged with a tag readable by the selected media property. The profit can be calculated by deducting, from the revenues that are expected to be generated from an ad delivered based on the collected profile, at least the price of ad space at a media property where the BT company might like to deliver ads to the profiled visitor. When the calculated profit is positive (i.e., not a loss), the BT company arranges for the visitor to be tagged with a tag readable by the selected media property through which the BT company expects to profit.

Abstract: A method is provided that grants users global control of the display of advertisements on a digital content platforms (DCP), as the primary user objection to digital advertising may be solved when content providers grant users control of the quality and relevance of ads for preferred products and services, and when and how often these ads are displayed. The DCP allows users to verbally communicate with a Voice User Interface (VUI), on a device such as a mobile phone, tablet, personal computer, laptop and TV. The VUI system performs speech recognition, and thereby sends the user request to display advertisements. In addition, the VUI may be vocally initiated by the user to remove advertisements. The method prompts users to engage in advertising for preferred products and services through paradigm shifts in permission-based marketing, e-commerce, and gamification.

Abstract: Commerce is suggested based on sensory outputs associated with a mobile device. The sensory outputs may represent any parameter, such as physical location or visual gaze. A product in a merchant's inventor may then be recommended, based on the sensory outputs.

Abstract: Communication network architectures, systems and methods for supporting a network of mobile and/or static nodes. As a non-limiting example, various aspects of this disclosure provide communication network architectures, systems, and methods for supporting a dynamically configurable communication network comprising a complex array of both static and moving communication nodes (e.g., the Internet of moving things, autonomous vehicle networks, etc.). For example, various aspects of this disclosure provide communication network architectures, systems and methods for managing digital advertising campaigns in a network of moving things (e.g., including manually operated and/or autonomous vehicles, etc.). As a non-limiting example, vehicle mobility and/or context may be utilized to effectively distribute and control distribution of ad campaigns. Additionally, various aspects of this disclosure provide systems and methods by which such ad campaigns may be specified (or defined) by a user.

Abstract: A method comprises providing an interface permitting a first user to control activation of a mobile information channel through which the first user can share access to content with a plurality of additional users, activating the mobile information channel responsive to input received from the first user via the interface, inserting content provided by the first user into the mobile information channel, receiving additional content relating to the mobile information channel from one or more of said additional users via one or more respective mobile devices associated with at least one wireless network, inserting at least a portion of the additional content into the mobile information channel, and integrating into the mobile information channel information associated with at least one wireless networking functionality of said at least one wireless network.

Abstract: A method, system and computer program product for facilitating customers to upgrade their hardware or software. An electronic problem ticketing system of a software/hardware vendor receives a request from a customer to open a problem ticket to service a designated version/model of the software/hardware product. The ticketing system acquires the number of users utilizing the software/hardware product requested to be serviced for various versions/models of the software/hardware product. A graphical diagram is generated depicting the number of users utilizing the software/hardware product requested to be serviced for various versions/models of the software/hardware product. A hyperlink to a social media website that contains information of the benefits of using a latest version or model of the software or hardware product is inserted in the graphical diagram, where after displaying such information, an instruction is received from the user to upgrade the software or hardware product.

Abstract: A campaign server disclosed herein includes a graphic user interface (GUI) and underlying campaign server functionality that together enable a user to build, execute and analyze the results of a campaign with increased ease and accuracy. The campaign server advantageously includes a segmentation engine which operates to dynamically update target segment population data. The campaign server GUI enables the user to construct the campaign content and to launch the campaign towards members of the dynamically updated target segment. The campaign server further operates to collect and present campaign results to the user.

Abstract: Embodiments disclosed herein can leverage dynamic data, fields and implied information from online media (e.g., web sites, mobile apps, Internet of things, bots, etc.) to create a universal variable map and automatically generate deep-linked ads utilizing the universal variable map, linking any arbitrary online media to any other arbitrary online media. The automatically generated deep-linked ads can be inserted into any ad server and served out from there in real-time. A deep-linked ad thus presented to a user can take the user from a starting page on one site or application where the ad is displayed directly to a resulting page such as a checkout page on another site or mobile application, with pertinent information already pre-populated, and action already initiated for the user.

Abstract: Embodiments disclosed herein can leverage dynamic data, fields and implied information from online media (e.g., web sites, mobile apps and other forms of online media) to create a universal variable map and automatically generate deep-linked ads utilizing the universal variable map, linking any arbitrary online media to any other arbitrary online media. The automatically generated deep-linked ads can be inserted into any ad server and served out from there in real-time. A deep-linked ad thus presented to a user can take the user from a starting page on one site or application where the ad is displayed directly to a resulting page such as a checkout page on another site or mobile application, with pertinent information already pre-populated, and action already initiated for the user.

Abstract: A method for automating interactions with enterprises includes: receiving, through a user interface, a natural language request from a customer; determining a customer intent from the natural language request; conducting an automated interaction by: determining, by a personal bot controller circuit, an enterprise to service the customer intent; loading an enterprise library for interacting with an application programming interface (API) of the enterprise, the enterprise library including one or more library functions; identifying a library function for servicing the customer intent from among the one or more library functions; generating a request based on the identified library function and the customer intent; transmitting the generated request to the enterprise to initiate an interaction; receiving a response from the enterprise; and notifying the customer of a result of the interaction.

Abstract: A method for controlling a charge transfer of an electric vehicle using an electric vehicle charging station, a mobile device, and a cloud server is disclosed. The method includes: receiving, at a mobile device, a message for an electric vehicle of a user directly from the electric vehicle charging station, wherein a user of the mobile device is associated with the electric vehicle to be charged; sending, from the mobile device, the message for the electric vehicle of the user directly to the cloud server; in response to a charging control signal being authorized using identification information and credit account information received from the mobile device, receiving the charging control signal from the cloud server via the mobile device at the electric vehicle charging station, wherein the charging control signal is configured to adjust a parameter used to draw electric power from the electric vehicle charging station; and adjusting the charge transfer based on the adjusted parameter.

Abstract: A method for managing payments made as part of an employee-liable expense reimbursement program is described. A plurality of employees are enrolled in the program and submit requests for reimbursement for expenses related to a service provided to the employees by a service provider for which the employees are liable. The method includes receiving, by the computer system, requests for reimbursement and aggregating the requests for reimbursement scheduled for payment within a predefined time period and associated with the service provider. The method also includes generating an invoice that includes a payment amount to be paid to the employee for subsequent payment to the service provider. The method also includes automatically requesting funds from an employer of the plurality of employees for the payment amount included in the invoice and electronically transferring funds associated with the employer to the service provider or alternatively, to the employee for subsequent payment to the service provider.

Abstract: A method for receiving a payment includes receiving information for a transaction with a merchant over the network, wherein the transaction includes an incomplete online transaction associated with a user account. A location of a user device that is associated with the user account is then retrieved, and a payment location is determined that is within a predetermined distance of the location of the user device. The payment location is then sent over the network to the user device. The user of the user device may then go to the payment location to provide payment information offline to a payment location device (e.g., by presenting a payment card to the payment location device provider, providing cash, etc.). That payment information is then received over the network from the payment location device and, in response, the online transaction is completed.

Abstract: Systems, methods and non-transitory computer-readable storage mediums are disclosed for cloud computing engineering, solar PV (SPV) or solar PV with storage (SPV/S) system configuration, pricing, quoting, advertising messaging, sales lead generation, and content marketing.

Abstract: Systems and methods for managing print services for a customer are described herein. In one example, managing print services for a customer comprises receiving contract data of a managed print services (MPS) contract and collecting device details related to customer devices of the customer. Further, for each of the customer devices, at least one service program to which the customer device is entitled is identified based on the received contract data and the collected device details.

Abstract: One variation of a method for fulfilling custom food orders includes: in response to request for a custom food order from a patron through an ordering portal executing on a computing device, retrieving a location of the computing device; identifying a set of food assembly apparatuses within a threshold distance of the location of the computing device; aggregating a list of ingredients currently loaded into the set of food assembly apparatuses; in response to selection of a particular ingredient in the list of ingredients for the custom food order, removing ingredients, from the list of ingredients, unique to a food assembly apparatus not currently loaded with the particular ingredient; selecting a particular food assembly apparatus, from the set, currently loaded with a set of ingredients specified in the custom food order; and inserting the custom food order into a food order queue assigned to the particular food assembly apparatus.

Abstract: According to one or more embodiments, apparatus, systems and methods are provided for facilitating commerce. In some embodiments, an apparatus (e.g., a central computer) facilitates posting of an item for sale by receiving a digital image of an item for sale, receiving an audio description (e.g., included in an audio file) of the item, and providing an indication of the description to at least one potential buyer. In one embodiment, the digital image and the audio description are received from a mobile phone.

Abstract: Systems and methods for a mobile electronic system that gathers and analyzes odors, airborne chemicals and/or compounds. A signature or representation of the odors, airborne chemicals and/or compounds can be generated. Extrinsic data associated with the odors, airborne chemicals and/or compounds or capturing the odors, airborne chemicals and/or compounds can be identified. A model can be generated based on the representation and the extrinsic data. Filters can be generated based on the extrinsic data. The model can be searched for candidate matches, solutions, or other results based on the representation and the filters. Results can be generated based on the search and candidate matches.

Abstract: Systems and methods to seed a search are described. The system identifies a seed listing included in listings that describe items being offered for sale on a network-based marketplace. The system identifies a seed filter context based on the seed listing and probabilities. The probabilities describe occurrences of attribute-value pairs in a plurality of listings that respectively describe items that were previously transacted on the network-based marketplace. The system extracts values from the seed listing based on the seed filter context. The system initializes the seed filter context based on the values and generates search results based on the seed filter context. The search results include a second plurality of listings that are identified from the first plurality of listings. Finally, the system communicates interface information to a client machine including the seed filter context and at least one listing from the second plurality of listings.