Systems and methods for converting marketplace transaction infrastructure into ai-driven collaborative social commerce networks

A system that integrates marketplace and social graph data to form Al-derived peer groups and provide predictive analytics addresses the lack of collaborative commerce networks, enhancing user interactions and merchant insights while preserving privacy and consent.

WO2026240978A1PCT designated stage Publication Date: 2026-11-19FOMINE ALEXEI
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
PCT/US2026/025365
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2025-05-31
Filing Date
2026-04-27
Publication Date
2026-11-19

AI Technical Summary

Technical Problem

Conventional marketplaces and social platforms fail to convert transaction histories into social commerce graphs, lacking collaborative commerce networks that integrate user, product, and merchant interactions while preserving privacy and consent, and existing recommendation engines do not leverage Al to form peer groups or provide predictive analytics.

Method used

A computer-implemented system that authenticates marketplace accounts, synchronizes transaction records, links them to social graphs, constructs commerce graphs, generates Al-derived peer groups, and provides conversational shopping assistance while ensuring privacy and consent, using layers for authentication, synchronization, graph construction, group formation, and merchant analytics.

Benefits of technology

Enables the creation of collaborative social commerce networks that enhance user interactions, provide personalized recommendations, and generate predictive merchant analytics, all while maintaining user privacy and consent, thereby improving group-level demand insights and engagement.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure US2026025365_19112026_PF_FP_ABST
    Figure US2026025365_19112026_PF_FP_ABST
Patent Text Reader

Abstract

A computer-implemented system and method convert marketplace transaction infrastructure into a collaborative social commerce network. A marketplace account authentication layer authenticates users with marketplace accounts, and a transaction synchronization layer retrieves marketplace transaction history. A social graph linkage layer links marketplace transaction data with social graph relationships, and a commerce graph construction layer generates graph nodes and edges representing users, products, merchants, sellers, transactions, and social relationships. An AI group-formation engine generates peer groups using marketplace transaction data and social graph data. A collaborative commerce object generator produces purchase feeds, product discussions, group recommendations, and social shopping objects. Recommendation and reward-state engines generate recommendations and update incentives based on engagement. A conversational AI assistant supports shopping interactions, and a merchant analytics layer generates group-level and graph-level commerce insights. Privacy, consent, encryption, anonymization, and optional edge preprocessing protect user data.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] Attorney Ref. No. 0252-11758-5

[0002] - 1 -

[0003] SYSTEMS AND METHODS FOR CONVERTING MARKETPLACE TRANSACTION INFRASTRUCTURE INTO AI-DRIVEN COLLABORATIVE SOCIAL COMMERCE NETWORKS

[0004] Technical Field

[0005] The present disclosure relates generally to a computer system, and more particularly, the disclosure relates to computer-implemented systems and methods for transforming marketplace transaction infrastructure into graph-linked collaborative social commerce networks by authenticating marketplace accounts, synchronizing transaction records, linking social graph identifiers, constructing commerce graphs, generating Al-derived peer groups, generating collaborative commerce objects, updating reward states, providing conversational shopping assistance, and generating merchant analytics.

[0006]

[0007] of the Prior Art

[0008] Large marketplace platforms contain extensive purchase, order, seller, product, review, subscription, return, and browsing history. However, conventional marketplaces generally treat such data as transaction records within isolated marketplace databases. They do not convert marketplace transaction history into a social commerce graph that connects users, products, sellers, merchants, categories, communities, and peer groups for collaborative commerce interactions.

[0009] Social platforms, by contrast, contain friend, follower, messaging, group, and community relationships, but they often lack structured, verified marketplace transaction context. A social platform user may discuss products manually, but such discussions are typically disconnected from actual transaction histories, purchase similarity, merchant data, or marketplace product graphs.

[0010] Traditional recommendation engines may recommend products within a marketplace, but they generally do not transform marketplace transaction records into Al-generated peer groups, product discussion threads, group shopping prompts, collaborative purchase feeds, or graph-linked merchant analytics. Such engines areAttorney Ref. No. 0252-11758-5

[0011] - 2-typically optimized for individual product recommendations rather than the conversion of a marketplace into a collaborative social commerce network.

[0012] Merchants also lack visibility into group-level demand signals, peer influence, purchase clusters, social conversion behavior, and community-level product adoption. Marketplace dashboards may provide sales reports, but they generally do not produce predictive group trend analytics based on combined transaction history, social graph relationships, group engagement, and recommendation activity.

[0013] Combining marketplace, social, and financial data further requires privacypreserving synchronization, encryption, anonymization, user consent, and optional edge preprocessing. Conventional systems do not provide a unified conversion architecture that turns marketplace infrastructure into a privacy-aware collaborative social commerce network.

[0014] Accordingly, there remains a need for a technical architecture that authenticates marketplace accounts, synchronizes marketplace transaction histories, links such histories to social graph relationships, constructs commerce graphs, forms Al-generated peer groups, generates collaborative commerce objects, produces recommendations, updates reward states, supports conversational shopping assistance, and generates merchant-facing analytics while preserving privacy and consent controls.

[0015] Summary of the Invention

[0016] In one aspect, the disclosure provides a computer-implemented marketplace-to-social-commerce conversion system comprising a marketplace account authentication layer, a marketplace transaction synchronization layer, a social graph linkage layer, a commerce graph construction layer, an Al group-formation engine, a collaborative commerce object generator, a recommendation engine, a reward-state engine, a conversational Al assistant layer, and a merchant analytics layer.

[0017] The marketplace account authentication layer may authenticate users with one or more marketplace accounts using OAuth, token-based authorization, delegated access, or other marketplace authorization mechanisms. The marketplace transactionAttorney Ref. No. 0252-11758-5

[0018] - 3 -synchronization layer may retrieve or access transaction history, order history, cart history, wish list history, review data, return history, subscription history, seller interaction data, or marketplace browsing activity associated with authenticated users.

[0019] The social graph linkage layer may associate marketplace users, marketplace transaction records, products, merchants, sellers, or categories with one or more social graph relationships, including friend relationships, follower relationships, contact-list relationships, messaging relationships, community memberships, group relationships, or platform identities. The commerce graph construction layer may generate graph nodes and edges representing marketplace users, products, merchants, sellers, categories, groups, social relationships, transaction-derived relationships, product-affinity relationships, trust relationships, engagement relationships, recommendation relationships, or conversion relationships.

[0020] The Al group-formation engine may generate peer groups, shopping groups, discussion groups, product-affinity groups, merchant-affinity groups, category groups, or temporary purchase-objective groups based on marketplace transaction data and social graph data. The engine may apply collaborative filtering, clustering, k-means clustering, graph neural network processing, embedding similarity, nearest-neighbor matching, reinforcement learning, or hybrid models.

[0021] The collaborative commerce object generator may generate purchase feed items, group shopping prompts, product discussion threads, peer recommendation cards, product comparison objects, merchant discussion objects, group deal objects, or social shopping sessions from the commerce graph. The recommendation engine may generate product, group, discussion, merchant, offer, influencer, or shopping-assistant recommendations using transaction data, graph proximity, group engagement, sentiment analysis, or reward eligibility.

[0022] The reward-state engine may update reward, incentive, discount, credit, loyalty, cashback, badge, access, or group-benefit states based on engagement within the collaborative commerce network. In some embodiments, a smart contract records, calculates, distributes, or audits reward events.Attorney Ref. No. 0252-11758-5

[0023] - 4- The conversational Al assistant may use a large language model or natural language processing model to answer user questions using marketplace transaction data, social graph data, group data, recommendation data, product data, merchant data, or sentiment data. The merchant analytics layer may generate analytics concerning group trends, purchase spikes, peer influence, discussion activity, group-level demand signals, reward redemption, social conversion, cohort behavior, or predictive commerce insights. Privacy, consent, encryption, anonymization, aggregation, and optional edge preprocessing may be applied to protect user data.

[0024] The more important features of the assembly have thus been outlined in order that the more detailed description that follows may be better understood and to ensure that the present contribution to the art is appreciated. Additional features of the system will be described hereinafter and will form the subject matter of the claims that follow.

[0025] Many objects of the present assembly will appear from the following description and appended claims, reference being made to the accompanying drawings forming a part of this specification wherein like reference characters designate corresponding parts in the several views.

[0026] Before explaining at least one embodiment of the system in detail, it is to be understood that the assembly is not limited in its application to the details of construction and the arrangements of the components set forth in the following description or illustrated in the drawings. The assembly is capable of other embodiments and of being practiced and carried out in various ways. Also it is to be understood that the phraseology and terminology employed herein are for the purpose of description and should not be regarded as limiting.

[0027] As such, those skilled in the art will appreciate that the conception, upon which this disclosure is based, may readily be utilized as a basis for the designing of other structures, methods and systems for carrying out the various purposes of the present assembly. It is important, therefore, that the claims be regarded as including such equivalent constructions insofar as they do not depart from the spirit and scope of the present assembly.Attorney Ref. No. 0252-11758-5

[0028] - 5 - Brief

[0029]

[0030] of the

[0031]

[0032] The novel features believed characteristic of the application are set forth in the appended claims. However, the application itself, as well as a preferred mode of use, and further objectives and advantages thereof, will best be understood by reference to the following detailed description when read in conjunction with the accompanying drawings, wherein:

[0033] FIG. 1 is a chart of a computer-implemented marketplace to social commerce conversion system according to the present application.

[0034] FIG. 2 illustrates marketplace account authentication and transaction synchronization workflow in the system of Figure 1.

[0035] FIG. 3 illustrates social graph linkage workflow for the system of Figure 1.

[0036] FIG. 4 illustrates commerce graph construction diagram for use with the system of Figure 1.

[0037] FIG. 5 illustrates an Al group-formation engine workflow for use with the system of Figure 1.

[0038] FIG. 6 illustrates collaborative commerce object generation for use with the system of Figure 1.

[0039] FIG. 7 illustrates recommendation engine workflow for use with the system of Figure 1.

[0040] FIG. 8 illustrates reward-state and smart-contract incentive workflow for use with the system of Figure 1.

[0041] FIG. 9 illustrates conversational Al shopping assistant workflow for use with the system of Figure 1.Attorney Ref. No. 0252-11758-5

[0042] - 6 - FIG. 10 illustrates merchant analytics dashboard workflow for use with the system of Figure 1.

[0043] FIG. 11 illustrates privacy and consent control workflow for use with the system of Figure 1.

[0044] FIG. 12 illustrates dynamic commerce graph update lifecycle for use with the system of Figure 1.

[0045] FIG. 13 illustrates an exemplary schematic of the system of Figure 1.

[0046] While the assembly of the present application is susceptible to various modifications and alternative forms, specific embodiments thereof have been shown by way of example in the drawings and are herein described in detail. It should be understood, however, that the description herein of specific embodiments is not intended to limit the application to the particular embodiment disclosed, but on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the process of the present application as defined by the appended claims.

[0047] Description of the Preferred Embodiment

[0048] Illustrative embodiments of the preferred embodiment are described below. In the interest of clarity, not all features of an actual implementation are described in this specification. It will of course be appreciated that in the development of any such actual embodiment, numerous implementation-specific decisions must be made to achieve the developer’s specific goals, such as compliance with system-related and business-related constraints, which will vary from one implementation to another. Moreover, it will be appreciated that such a development effort might be complex and time-consuming but would nevertheless be a routine undertaking for those of ordinary skill in the art having the benefit of this disclosure.

[0049] In the specification, reference may be made to the spatial relationships between various components and steps as depicted in the attached drawings. However, as will be recognized by those skilled in the art after a complete reading of the presentAttorney Ref. No. 0252-11758-5

[0050] - 7 -application, the devices, steps, apparatuses, etc. described herein may be positioned in any desired orientation. Thus, the use of terms to describe a relationship between various components or to describe the steps should be understood to describe a relative relationship between them, as the system described herein may be configured in any desired manner.

[0051] The system and method will be understood, both as to its structure and operation, from the accompanying drawings, taken in conjunction with the accompanying description. Several embodiments of the system and method may be presented herein. It should be understood that various components, steps, and features of the different embodiments may be combined together and / or interchanged with one another, all of which are within the scope of the present application, even though not all variations and particular embodiments are shown in the drawings. It should also be understood that the mixing and matching of features, elements, and / or functions between various embodiments is expressly contemplated herein so that one of ordinary skill in the art would appreciate from this disclosure that the features, elements, and / or functions of one embodiment may be incorporated into another embodiment as appropriate, unless otherwise described.

[0052] For purposes of clarity in describing the various elements, functions, and features of system 101 , the following definitions are useful:

[0053] Marketplace transaction history - order history, purchase history, cart history, wish list history, product review data, seller interaction data, return history, subscription history, browsing behavior, or other marketplace-originated transaction-adjacent data associated with one or more users.

[0054] Marketplace account authentication - a process by which a user authorizes access to a marketplace account using credentials, delegated authorization, OAuth, token-based authentication, or an API authorization flow.

[0055] Social graph identifier - an identifier associated with a user, contact, friend, follower, group, community, message account, or social platform identity.

[0056] Commerce graph - a graph data structure representing marketplace users, products, merchants, sellers, categories, groups, transaction edges, social edges,Attorney Ref. No. 0252-11758-5

[0057] - 8 -similarity edges, engagement edges, trust edges, recommendation edges, or conversion edges.

[0058] Commerce graph node - a graph entity representing a user, product, merchant, seller, category, group, community, discussion, offer, campaign, or other commerce-related entity.

[0059] Commerce graph edge - a relationship between graph nodes, including a purchase relationship, social relationship, similarity relationship, engagement relationship, recommendation relationship, trust relationship, conversion relationship, or reward relationship.

[0060] Al-generated peer group - a group of users generated by a model using marketplace transaction data, social graph data, purchase similarity, social proximity, product affinity, merchant affinity, or engagement behavior.

[0061] Collaborative commerce object - a generated digital object derived from the commerce graph, including a purchase feed item, group shopping prompt, product discussion thread, peer recommendation card, product comparison object, merchant discussion object, group deal object, or social shopping session.

[0062] Reward state - a data state identifying an incentive, discount, loyalty point, credit, cashback, badge, access privilege, merchant benefit, group benefit, smart-contract state, or platform reward state.

[0063] Merchant analytics signal - an anonymized, aggregated, or permissioned signal describing group trends, purchase spikes, peer influence, social conversion, product demand, reward performance, or predicted merchant outcomes.

[0064] Conversational shopping assistant - a large language model or natural-language processing assistant configured to respond to user questions using marketplace transaction data, social graph data, group data, recommendation data, product data, merchant data, or sentiment data.

[0065] Consent rule - a data-access rule defining a data source, access duration, permitted recipient, permitted processing purpose, revocation condition, display rule, or analytics permission.Attorney Ref. No. 0252-11758-5

[0066] - 9 - Financial support data - financial, card, bank, email receipt, or transaction-adjacent data used to validate, supplement, or enrich marketplace transaction history under user consent.

[0067] Referring now to the Figures wherein like reference characters identify corresponding or similar elements in form and function throughout the several views. The following Figures describe the assembly of the present application and its associated features. With reference now to the Figures, an embodiment of the valve assembly and method of use are herein described. It should be noted that the articles “a”, “an”, and “the”, as used in this specification, include plural referents unless the content clearly dictates otherwise.

[0068] Referring to FIG. 1 , a system and method for converting marketplace transaction infrastructure into Al driven collaborative social commerce networks is illustrated. The system 101 is a computer-implemented marketplace-to-social-commerce conversion system and is configured to include one or more client devices, marketplace account interfaces, authorization services, marketplace transaction synchronization services, social graph connectors, commerce graph databases, Al group-formation engines, collaborative commerce object generators, recommendation engines, reward-state engines, conversational Al assistant services, merchant analytics services, and privacy / consent management modules. The system may operate as a standalone service or as a marketplace-integrated module, a social commerce layer, an API service, or a federated service spanning multiple marketplaces and social environments.

[0069] The system is configured to convert marketplace transaction infrastructure into a collaborative social commerce network. This conversion occurs by authenticating marketplace accounts 102, retrieving or accessing marketplace transaction history in a marketplace transaction synchronization layer 103, linking transaction data to social graph relationships 104, Layer 105 receives financial support data 106. Inputs 102, 103, 104, and 106 are inserted into commerce graph construction layer 105. Layer 105 is configured to construct commerce graph nodes and edges. Layer 105 sends data to an Al group formation engine 107 to form Al-generated groups. A collaborative commerce object generator 108 is configured to produce collaborative commerce objects. GeneratorAttorney Ref. No. 0252-11758-5

[0070] - 10 - 108 can be used to interact with a conversational Al shopping assistant 111. A recommendation engine 109 is configured for generating recommendations. Engine 109 is used for generating merchant analytics in a merchant analytics dashboard layer 112. Layer 105 further sends data to a reward state engine 110 for regulating and updating reward states and interacting with interfaces 113.

[0071] Referring to FIG. 2, a workflow 201 for marketplace account authentication layer 102 is provided. Marketplace account authentication layer 102 may permit a user to authorize access to one or more marketplace accounts 203 via one or more user devices 202. Authentication 204 may occur through OAuth, token-based authorization, delegated permission, marketplace credentials, API authorization, passwordless authentication, device authorization, or another account authorization mechanism. The authentication layer may validate marketplace identity 205. Layer 102 confirms that the user controls the account, and establishes an authorization token or data-access session.

[0072] The authentication layer 102 may maintain different access scopes 206 for different marketplaces. For example, a first marketplace may permit order history access but not review history access, while a second marketplace may permit access to order history, wish list data, seller messages, and subscription data. The system may store scope metadata so downstream modules know which transaction categories may be used for graph construction, group formation, recommendations, or merchant analytics. History may be accessed 207 wherein selected transaction records may be retrieved 208 and sent through standardized commerce graph inputs 209. The data may be sent to a commerce graph engine 210.

[0073] Referring back to FIG. 1, the marketplace transaction synchronization layer 103 may retrieve order history, purchase history, cart history, wish list history, product review history, seller interaction history, return history, subscription history, marketplace browsing behavior, delivery status, price data, timestamps, product identifiers, seller identifiers, merchant identifiers, category labels, and user annotations. The retrieved records may be normalized into a shared marketplace transaction schema before commerce graph construction.Attorney Ref. No. 0252-11758-5

[0074] - 11 - Where a user connects multiple marketplaces, the system may map equivalent product records, reconcile product identifiers, standardize merchant or seller identifiers, deduplicate overlapping records, and generate a normalized transaction set. The normalization process may produce graph-ready transaction records used to create userproduct, user-merchant, user-seller, user-category, and user-group relationships.

[0075] In some embodiments, financial support data layer 106 may supplement marketplace transaction data. The system may receive or access bank, card, financial, email receipt, or transaction-adjacent data under user consent. Financial support data may validate, enrich, or confirm marketplace transaction history. For example, a bank transaction may confirm a marketplace purchase amount, or an email receipt may supply missing item-level metadata.

[0076] The financial support data layer 106 may apply encryption, anonymization, pseudonymization, user-controlled consent, local processing, or edge preprocessing before synchronization. Consent rules may define data source, access duration, permitted recipient, permitted processing purpose, revocation rules, and analytics eligibility. Financial support data is not the core invention center of this filing; it operates as supporting input for converting marketplace transaction infrastructure into a collaborative social commerce network.

[0077] Referring now also to FIG. 3 in the drawings, a social graph linkage workflow 301 for input layer 104 is provided. A social graph linkage layer 104 may link marketplace user identifiers 302 to social network identifiers 303. Purchase records 304 may also be considered. A further input can be had from identifier 303 by comparing them with user relations 306. Layer 104 links inputs 302, 303, 304, and 306 within an identity and relationship linker 305.

[0078] These inputs may be used to link with relationship identifiers, such as, contact-list identifiers, messaging identifiers, follower relationships, friend relationships, community memberships, or group relationships. The linkage may be based on user authorization, identity matching, contact matching, username matching, account linking, platform identity resolution, or user confirmation.Attorney Ref. No. 0252-11758-5

[0079] - 12 - The social graph linkage layer 104 may generate any number of outputs, such as outputs 307, 308, 309. Examples of these outputs are commerce relationship edges between buyer nodes, seller nodes, merchant nodes, product nodes, category nodes, group nodes, friend nodes, and community nodes. An example would be commerce relationship edges include purchase-similarity edges, social-proximity edges, trust edges, product-affinity edges, engagement edges, recommendation edges, conversion edges, and merchant-affinity edges.

[0080] Commerce relationships may be ranked or weighted based on purchase similarity, social proximity, communication frequency, shared products, shared merchants, category affinity, group membership, review similarity, or engagement response. The system may update the social graph linkage and related commerce graph edges when new marketplace transactions, social interactions, recommendations, comments, purchases, merchant campaigns, or reward events occur. A commerce graph update 310 may be generated.

[0081] Referring now also to FIG. 4 in the drawings, a commerce graph construction diagram 401 for use with layer 105 is provided. A commerce graph construction layer 105 may generate graph nodes and edges representing users 401 and 408, products 403, merchants 404, sellers 405, categories 410, groups 409, transaction records, social relationships, discussion I feeds 406, product affinities, group memberships, engagement behaviors, recommendation events, reward events, and conversion events 407. The graph may be stored in a graph database, relational database, key-value store, vector database, or distributed data store.

[0082] A user node may be connected to a product node by a purchase edge. The same user node may be connected to another user node by a social-proximity edge. A product node may be connected to a category node, a merchant node, a seller node, and one or more discussion or group nodes. These graph relationships enable downstream Al group formation, collaborative commerce object generation, recommendation ranking, reward evaluation, and merchant analytics.

[0083] Referring now also to FIG. 5 in the drawings, an Al group formation engine workflow 501 is illustrated for use in engine 107. Al group-formation engine 107 receivesAttorney Ref. No. 0252-11758-5

[0084] - 13 - inputs from layer 105 and is configured to process input signals 502, such as marketplace transaction data, social graph data, engagement data, product category data, merchant data, seller data, and group activity data. The engine 107 extracts some features 503 and is configured to use a model layer 504 to apply collaborative filtering, k-means clustering, other clustering algorithms, graph neural network processing, embedding similarity, nearest-neighbor matching, reinforcement learning, or hybrid models.

[0085] The Al group-formation engine 107 may form group outputs 505, such as, peer groups, shopping groups, product-affinity groups, merchant-affinity groups, category groups, local commerce groups, event-based groups, promotion-based groups, temporary product groups, warranty-issue groups, service-marketplace groups, or shared purchase-objective groups. Group formation may be based on purchase similarity, social proximity, product category affinity, merchant affinity, spending range, review similarity, shopping frequency, lifestyle pattern, location, or engagement behavior.

[0086] The Al group-formation engine may dynamically update 506 group membership when new marketplace transactions, social interactions, comments, reviews, group discussions, reward events, or merchant campaigns occur. The engine may also detect influencers, category experts, trusted buyers, high-engagement users, or users with product-specific authority within generated groups.

[0087] Referring now also to FIG. 6 in the drawings, a collaborative commerce object generation workflow 601 for use with generator 108 is provided. The collaborative commerce object generator 108 may generate digital objects from commerce graph events 602. Such objects may include purchase feed items 605, group shopping prompts 608, product discussion threads 606, peer recommendation cards, merchant discussion objects 609, product comparison cards 607, social shopping sessions, group deal objects 610, campaign objects, or group demand objects.

[0088] Collaborative commerce objects may be generated from marketplace transaction history and social graph relationship data rather than from manually submitted posts alone. Various events may trigger the generation of a collaborative commerce object. Examples of events that may do this are a purchase spike, group interest signal, merchant campaign, product review cluster, peer question, or detected product category trend. TheAttorney Ref. No. 0252-11758-5

[0089] - 14 - object may include product title, merchant identity, seller identity, category, redacted transaction signal, group relevance score, trust indicator, engagement prompt, or reward opportunity.

[0090] Different users may receive different collaborative commerce objects based on group membership, privacy permissions, marketplace transaction relevance, social graph proximity, merchant eligibility rules, or consent settings. In some embodiments, product discussion threads are automatically generated in response to a detected purchase spike, group interest, merchant campaign, or peer question. The objects are shared with interfaces 611 for users, groups, and merchants as governed by visibility and privacy rules 604.

[0091] Referring now also to FIG. 7 in the drawings, a recommendation engine workflow 701 is provided for use with engine 109. Recommendation engine 109 may generate product recommendations 705, group recommendations 706, discussion recommendations 707, and other recommendations 708 such as, merchant recommendations, offer recommendations, influencer recommendations, or shopping assistant responses. The recommendation engine 109 may use processing tools 703 like reinforcement learning, collaborative filtering, and graph-based ranking. Recommendation inputs 702 are provided to tools 703. Inputs can be engagement metrics, sentiment analysis, purchase similarity, group behavior, social graph distance, reward eligibility, merchant campaign data, or user preferences.

[0092] Recommendations may be personalized based on both marketplace transaction records and social relationships. For example, a recommendation may be ranked higher when the product is purchased by socially proximate users, discussed within a generated peer group, associated with high group engagement, or aligned with a merchant campaign. Recommendations may update when commerce graph nodes, edges, group memberships, reward states, or engagement metrics are updated. User feedback 704 is also utilized to enhance and refine outputs.

[0093] Referring now also to FIG. 8 in the drawings, an incentive workflow 801 for use with engine 110 is provided. The reward-state engine 110 may update reward, incentive, or engagement states based on user activity within the collaborative commerce network.Attorney Ref. No. 0252-11758-5

[0094] - 15 - Reward-triggering activities 802 may include sharing, commenting, purchasing, joining a group, responding to a discussion, providing feedback, referring another user, generating group engagement, or influencing a downstream purchase. Engine 110 monitors engagement for detection 803 and assesses reward eligibility 804. These inputs 802, 803, 804 are processed and evaluated according to reward rules 805.

[0095] Rewards 808 may include discounts, credits, loyalty points, cashback, badges, merchant benefits, access privileges, group benefits, smart-contract-distributed rewards, early access, or other commercial benefits. Reward eligibility may be based on group participation, verified engagement, marketplace transaction behavior, peer influence, product discussion activity, merchant campaign thresholds, or social conversion outcomes.

[0096] In some embodiments, a smart contract records engine 806, calculates, distributes, or audits reward events. In other embodiments, a platform reward engine 807 performs the same functions using database logic, campaign rules, merchant instructions, or reward policies. Reward states may be written back to the commerce graph 809 so that they can influence future recommendations, group membership, merchant analytics, or user ranking.

[0097] Referring now also to FIG. 9 in the drawings, a conversational Al shopping assistant workflow 901 for use with assistant 111 is provided. System 101 may include a conversational Al assistant 111 configured to respond to user questions 902 using a context assembler 903. Assembler 903 receives the inquiry or input from the user and analyzes it to contextualize it into categories, such as, marketplace transaction data, social graph data, group data, recommendation data, merchant data, product data, discussion data, or sentiment data. The assistant 111 may use a processing model like a large language model, natural language processing model, retrieval-augmented generation, graph-based context retrieval, or other Al technique to analyze the outputs of the assembler 903 prior to sending to response generator 905.

[0098] The conversational Al assistant 111 uses a response generator 905 to generate outputs, such as, product recommendations, group recommendations, product comparison explanations, peer trend explanations, merchant suggestions, shoppingAttorney Ref. No. 0252-11758-5

[0099] - 16 - decision guidance, discussion summaries, sentiment-aware responses, or group discussion prompts. Assistant 111 can send data to a user interface 906. Assistant 111 can initiate or recommend a group discussion based on a user question, detected purchase spike, emerging trend, merchant campaign, or group-level product interest.

[0100] Referring now also to FIG. 10 in the drawings, a merchant analytics dashboard workflow 1001 for use with layer 112 is provided. The merchant analytics layer 112 may generate analytics within an analytics engine 1004 for group trends, product spikes, purchase clusters, peer influence, discussion activity, recommendation engagement, reward redemption, social conversion, group-level demand, merchant campaign performance, or more. The analytics layer 112 may produce analytic outputs 1005 and apply time-series forecasting, cohort analysis, graph analytics, trend detection, predictive modeling, or causal attribution logic.

[0101] Merchant analytics layer 112 may be presented through dashboards 1006 showing potential actions 1007, such as, group-level demand signals, product interest acceleration, recommendation-to-purchase behavior, reward performance, social conversion rates, purchase clusters, group affinity, or suggested merchant actions 1007. Suggested merchant actions 1007 may include offer creation, campaign adjustment, product targeting, group targeting, inventory planning, reward threshold adjustment, or discussion sponsorship.

[0102] Merchant-facing analytics layer 112 may be generated from aggregated or anonymized commerce graph data 1002 unless user permissions authorize greater detail. Data 1002 is anonymized or aggregated 1003 prior to being provided to engine 1004. A merchant may receive a group-level demand signal based on marketplace transaction history and social engagement without receiving raw personal transaction data.

[0103] Referring now also to FIG. 11 in the drawings, a privacy and consent control workflow 1101 is provided. System 101 may provide a user privacy dashboard 1102 for marketplace data permissions, financial data permissions, social graph permissions, group participation permissions, merchant analytics permissions, and recommendation visibility. A consent rule engine 1104 may apply controlled processing 1103 encryption,Attorney Ref. No. 0252-11758-5

[0104] - 17 -anonymization, pseudonymization, aggregation, edge preprocessing, purpose limitation, access-duration limits, and revocation rules.

[0105] System 101 may restrict raw transaction data, raw financial data, personally identifying information, or sensitive social graph details from being exposed to merchants via a controlled data output 1105. Privacy rules may prevent collaborative commerce objects from exposing raw financial data. Consent may be configured at the data-source level, group level, merchant level, recommendation level, or analytics level.

[0106] Referring now also to FIG. 12 in the drawings, a dynamic commerce graph update lifecycle 1201 is provided. The commerce graph 1203 may be continuously updated with event inputs 1202 when new marketplace transactions, social interactions, group activities, reward events, merchant campaign events, comments, recommendations, conversions, or consent changes occur. Updating the commerce graph 1203 may cause group membership updates 1204, recommendation updates 1206, reward-state updates, merchant analytics updates 1205, notifications for user and / or merchants 1207, or merchant dashboard updates.

[0107] For example, when a new marketplace transaction occurs, the transaction synchronization layer 103 may normalize the transaction, the commerce graph construction layer 105 may create or revise user-product and user-merchant edges, the Al group-formation engine may update group memberships, the recommendation engine may adjust outputs, and the merchant analytics layer may update trend signals.

[0108] Referring now also to Figure 13 of the drawings, an exemplary schematic of system 101 configured to convert marketplace transaction infrastructure into a collaborative social commerce network is illustrated. System 101 includes program software executed on one or more computerized devices for the purpose of performing the tasks and methods herein.

[0109] Figure 13 illustrates exemplary computerized devices configured to execute and access the programs associated with system 101. The system 101 includes an input / output (I / O) interface 12, a control processor 14, a database 16, and a maintenance interface 18. Alternative embodiments can combine or distribute the input / output (I / O) interface 12, control processor 14, database 16, and maintenance interface 18 as desired.Attorney Ref. No. 0252-11758-5

[0110] - 18 - Embodiments of system 101 can include one or more computers that include one or more processors and memories configured for performing tasks described herein below. This can include, for example, a computer having a central processing unit (CPU) and nonvolatile memory that stores software instructions for instructing the CPU to perform at least some of the tasks described herein. This can also include, for example, two or more computers that are in communication via a computer network, where one or more of the computers includes a CPU and non-volatile memory, and one or more of the computer’s non-volatile memory stores software instructions for instructing any of the CPU(s) to perform any of the tasks described herein. Thus, while the exemplary embodiment is described in terms of a discrete machine, it should be appreciated that this description is non-limiting, and that the present description applies equally to numerous other arrangements involving one or more machines performing tasks distributed in any way among the one or more machines. It should also be appreciated that such machines need not be dedicated to performing tasks described herein, but instead can be multipurpose machines, for example computer workstations, that are suitable for also performing other tasks. Furthermore, the computers may use transitory and non-transitory forms of computer-readable media. Non-transitory computer-readable media is to be interpreted to comprise all computer-readable media, with the sole exception of being a transitory, propagating signal.

[0111] The I / O interface 12 provides a communication link between external users, systems, and data sources and components of system 101. The I / O interface 12 is in communication with control processor 14 and database 16 and is configured to provide an interactive link between the user and other external parties. The I / O interface 12 can be configured for allowing one or more users to input information to the system 101 via any known input device. Examples can include a keyboard, mouse, touch screen, microphone, and / or any other desired input device. The I / O interface 12 provides a display portal defining a plurality of visually perceptible elements corresponding to the prediction data. The I / O interface 12 can be configured for allowing one or more users to receive information output from the system 101 via any known output device. Examples can include a display monitor, a printer, a speaker, and / or any other desired output device.Attorney Ref. No. 0252-11758-5

[0112] - 19 - The I / O interface 12 can be configured for allowing other systems to communicate with the system 101. For example, the I / O interface 12 can allow one or more remote computer(s) to access information, input information, and / or remotely instruct system 101 to perform one or more of the tasks described herein. The I / O interface 12 can be configured to allow communication with one or more remote data sources. For example, the I / O interface 12 can allow one or more remote data source(s) to access information, input information, and / or remotely instruct the system 101 to perform one or more of the tasks described herein.

[0113] The database 16 provides persistent data storage (computer readable storage media, i.e. hardware) for system 101. Database 16 is in communication with control processor 14 and I / O interface 12. While the term "database" is primarily used, a memory or other suitable data storage arrangement may provide the functionality of the database 16. In alternative embodiments, the database 16 can be integral to or separate from the system 101 and can operate on one or more computers. The database 16 preferably provides non-volatile data storage for any information suitable to support the operation of system 101, including various types of data necessary to perform the functions and feature discussed below.

[0114] The maintenance interface 18 is configured to allow users to maintain desired operation of the system 101. In some embodiments, the maintenance interface 18 can be configured to allow for reviewing and / or revising the data stored in the database 16 and / or performing any suitable administrative tasks commonly associated with database management. This can include, for example, updating database management software, revising security settings, and / or performing data backup operations. In some embodiments, the maintenance interface 18 can be configured to allow for maintenance of the control processor 14 and / or the I / O interface 12. This can include, for example, software updates and / or administrative tasks such as security management and / or adjustment of certain tolerance settings.

[0115] Control processor 14 can be configured to perform a process or a plurality of processes such as the processes described below in connection with the associated Figures. Additionally, control processor 14 includes software programmed to compileAttorney Ref. No. 0252-11758-5

[0116] - 20 - properly communicate with the interested parties. Processor 14 includes a non-transitory computer-readable medium with instructions stored thereon to execute predetermined steps. Various functions of the control processor 14 may be realized, as set forth herein.

[0117] A plurality of use cases are provided for clarity and simplification of system 101 in use. A first use case involves converting marketplace purchase history into social groups. A user connects their marketplace account. System 101 retrieves the user’s purchase history and links it to their social graph, including friends, contacts, or community memberships. The Al group-formation engine identifies other users with similar purchase behavior and social proximity and automatically places the user into one or more shopping groups focused on shared product categories. The purpose is to show marketplace transaction sync, social graph linkage, and Al group formation.

[0118] A second use case involves generating collaborative commerce discussion from purchases. Multiple users within a group purchase similar products from a marketplace. System 101 detects a purchase spike within a product category and automatically generates a collaborative discussion thread. Group members can see product-related insights, reviews, and recommendations derived from real purchase behavior rather than manual posts. A purpose is to show automated collaborative commerce object generation from marketplace data.

[0119] A third use case involves Al-driven product and group recommendations. A user’s marketplace transaction history and social relationships are processed by the recommendation engine. The system identifies relevant products, groups, and discussions based on purchase similarity, group activity, and engagement patterns. The user receives personalized recommendations that combine marketplace data and social context. A purpose is to show recommendation engines using marketplace data, social graph data, and Al.

[0120] A fourth use case involves rewarding engagement in social comer groups. A user participates in group discussions, shares purchase insights, and influences other users’ purchasing decisions. The system detects engagement events and downstream purchases. Based on this activity, the reward-state engine updates the user’s rewardAttorney Ref. No. 0252-11758-5

[0121] - 21 -status and distributes incentives such as discounts, credits, or badges. A purpose is to show reward-state engine, engagement tracking, and incentive distribution.

[0122] A fifth use case involves merchant insight from group-level commerce activity. A merchant accesses the analytics dashboard and observes that a specific product is trending within a defined group. The system provides anonymized insights about group-level demand, engagement, and purchasing behavior. Based on these insights, the merchant launches a targeted campaign for that group. A purpose is to show merchant analytics, group-level trend detection, and actionable insights.

[0123] Other examples may include a big online store where people buy things. System 101 turns that store into a place where people who bought similar things can find each other and share ideas. Additionally, if you buy a lot of sports equipment, the system finds other people who also like sports and puts you in a group where you can talk about what to buy next. Furthermore, stores can see what groups of people like and want to buy, without seeing private details, so they can offer better products to those groups.

[0124] The particular embodiments disclosed above are illustrative only, as the application may be modified and practiced in different but equivalent manners apparent to those skilled in the art having the benefit of the teachings herein. It is therefore evident that the particular embodiments disclosed above may be altered or modified, and all such variations are considered within the scope and spirit of the application. Accordingly, the protection sought herein is as set forth in the description. It is apparent that an application with significant advantages has been described and illustrated. Although the present application is shown in a limited number of forms, it is not limited to just these forms, but is amenable to various changes and modifications without departing from the spirit thereof.

Claims

Attorney Ref. No. 0252-11758-5CLAIMSWhat is claimed is:

1. A computer-implemented marketplace-to-social-commerce conversion system comprising:a marketplace account authentication layer configured to authenticate users with one or more marketplace accounts;a marketplace transaction synchronization layer configured to retrieve or access marketplace transaction history associated with authenticated users;a social graph linkage layer configured to associate marketplace users, marketplace transaction records, products, merchants, or sellers with one or more social graph relationships;a commerce graph construction layer configured to generate graph nodes and edges representing marketplace users, products, merchants, sellers, social relationships, and transaction-derived relationships;an Al group-formation engine configured to generate peer groups, shopping groups, discussion groups, or product-affinity groups based on marketplace transaction data and social graph data;a collaborative commerce object generator configured to generate purchase feeds, product discussions, group recommendations, merchant recommendations, or social shopping objects from the commerce graph;a recommendation engine configured to generate product, group, discussion, merchant, or offer recommendations using at least marketplace transaction history, social graph relationships, group engagement, or user interaction history;a reward-state engine configured to update reward, incentive, or engagement states based on user activity within the collaborative commerce network; anda merchant analytics layer configured to generate merchant-facing analytics based on group-level, graph-level, transaction-level, or engagement-level marketplace activity.Attorney Ref. No. 0252-11758-5- 23 - 2. The system of claim 1 , wherein the marketplace account authentication layer uses OAuth, token-based authentication, API authorization, marketplace account credentials, or delegated permission.

3. The system of claim 1 , wherein the marketplace transaction synchronization layer accesses at least one of order history, purchase history, cart history, wish list history, product reviews, seller interactions, return history, subscription history, or marketplace browsing behavior.

4. The system of claim 1, wherein transaction history is retrieved from an online marketplace, merchant platform, e-commerce storefront, delivery platform, digital goods marketplace, app marketplace, travel marketplace, service marketplace, or localcommerce marketplace.

5. The system of claim 1 , wherein the transaction synchronization layer standardizes marketplace transaction records into commerce graph inputs.

6. The system of claim 1, wherein marketplace transaction records are linked to product identifiers, seller identifiers, merchant identifiers, timestamps, category labels, prices, delivery status, review data, or user annotations.

7. The system of claim 1 , wherein marketplace transaction records are ingested from multiple marketplaces and normalized into a shared marketplace transaction schema.

8. The system of claim 1 , further comprising a financial data support layer configured to receive or access financial, card, bank, email receipt, or transaction-adjacent data under user consent.Attorney Ref. No. 0252-11758-5- 24 - 9. The system of claim 8, wherein the financial data support layer uses encryption, anonymization, user-controlled consent, or local / edge preprocessing before synchronization.

10. The system of claim 8, wherein financial data is used to validate, supplement, or enrich marketplace transaction history.

11. The system of claim 8, wherein consent rules define at least one of data source, access duration, permitted recipient, permitted processing purpose, or revocation rule.

12. The system of claim 8, wherein user-controlled financial data is used only as supporting input to the commerce graph and not as a standalone financial-memory vault.

13. The system of claim 1, wherein the social graph linkage layer links marketplace user identifiers to social network identifiers, contact-list identifiers, messaging identifiers, follower relationships, friend relationships, community memberships, or group relationships.

14. The system of claim 1 , wherein the social graph linkage layer generates commerce relationship edges between at least two of buyer nodes, seller nodes, merchant nodes, product nodes, group nodes, friend nodes, category nodes, or community nodes.

15. The system of claim 1, wherein commerce relationship edges include purchasesimilarity edges, social-proximity edges, trust edges, product-affinity edges, engagement edges, recommendation edges, or conversion edges.

16. The system of claim 1 , wherein the social graph linkage layer ranks relationships based on purchase similarity, social proximity, communication frequency, shared products, shared merchants, category affinity, group membership, or engagement response.Attorney Ref. No. 0252-11758-5- 25 - 17. The system of claim 1 , wherein the commerce graph is updated when new marketplace transactions, social interactions, recommendations, purchases, comments, or reward events occur.

18. The system of claim 1 , wherein the Al group-formation engine applies collaborative filtering, clustering, k-means clustering, graph neural network processing, embedding similarity, nearest-neighbor matching, reinforcement learning, or hybrid recommendation models.

19. The system of claim 1 , wherein the Al group-formation engine forms groups based on at least one of purchase similarity, product category affinity, merchant affinity, social proximity, spending range, review similarity, shopping frequency, lifestyle pattern, location, or engagement behavior.

20. The system of claim 1 , wherein the Al group-formation engine dynamically updates group membership based on new marketplace transactions or social engagement activity.

21. The system of claim 1 , wherein the Al group-formation engine recommends a user to join a group based on a computed similarity between the user’s marketplace transaction history and group-level transaction patterns.

22. The system of claim 1 , wherein the Al group-formation engine forms a temporary group around a product, merchant, category, event, promotion, warranty issue, local service, or shared purchase objective.

23. The system of claim 1 , wherein the Al group-formation engine detects influencers, category experts, or trusted buyers within generated groups.

24. The system of claim 1 , wherein the collaborative commerce object generator generates at least one of a purchase feed item, group shopping prompt, productAttorney Ref. No. 0252-11758-5- 26 - discussion thread, peer recommendation card, merchant discussion object, product comparison object, social shopping session, or group deal object.

25. The system of claim 24, wherein the collaborative commerce object is generated from a combination of marketplace transaction history and social graph relationship data.

26. The system of claim 24, wherein the collaborative commerce object includes product title, merchant identity, seller identity, category, redacted transaction signal, group relevance score, trust indicator, engagement prompt, or reward opportunity.

27. The system of claim 24, wherein different users receive different collaborative commerce objects based on group membership, privacy permissions, marketplace transaction relevance, or social graph proximity.

28. The system of claim 1 , wherein purchase feeds are generated from marketplace transaction history rather than manually submitted social posts.

29. The system of claim 1, wherein product discussion threads are generated automatically in response to a detected purchase spike, group interest, merchant campaign, or peer question.

30. The system of claim 1, wherein the recommendation engine uses reinforcement learning, collaborative filtering, graph-based ranking, engagement metrics, sentiment analysis, purchase similarity, or group behavior.

31. The system of claim 1 , wherein recommendations include at least one of product recommendation, merchant recommendation, group recommendation, discussion recommendation, offer recommendation, influencer recommendation, or shopping assistant response.Attorney Ref. No. 0252-11758-5- 27 - 32. The system of claim 1 , wherein the recommendation engine ranks recommendations based on a combination of marketplace purchase history, social graph distance, group affinity, engagement velocity, reward eligibility, or merchant campaign data.

33. The system of claim 1 , wherein recommendations are personalized based on both marketplace transaction records and social relationships.

34. The system of claim 1 , wherein the recommendation engine updates recommendations when commerce graph nodes or edges are updated.

35. The system of claim 1 , wherein recommendations are filtered by consent settings, privacy rules, user preferences, ethical shopping preferences, sustainability preferences, or merchant eligibility rules.

36. The system of claim 1, wherein the reward-state engine updates reward states based on sharing, commenting, purchasing, joining a group, responding to a discussion, providing feedback, referring another user, or generating engagement within the collaborative commerce network.

37. The system of claim 1 , wherein rewards comprise discounts, credits, loyalty points, cashback, badges, merchant benefits, access privileges, group benefits, or smartcontract-distributed rewards.

38. The system of claim 1 , wherein a smart contract records, calculates, distributes, or audits reward events.

39. The system of claim 1 , wherein reward eligibility is based on at least one of group participation, verified engagement, marketplace transaction behavior, peer influence, product discussion activity, or merchant campaign thresholds.Attorney Ref. No. 0252-11758-5- 28 - 40. The system of claim 1 , wherein reward states are updated in response to machine-detected commerce engagement events.

41. The system of claim 1 , further comprising a conversational Al assistant configured to respond to user questions using marketplace transaction data, social graph data, group data, recommendation data, or merchant data.

42. The system of claim 41, wherein the conversational Al assistant uses a large language model or natural language processing model.

43. The system of claim 41 , wherein the conversational Al assistant generates product recommendations, group recommendations, product comparison explanations, peer trend explanations, merchant suggestions, or shopping decision guidance.

44. The system of claim 41 , wherein the conversational Al assistant uses sentiment analysis to modify responses based on user tone, group sentiment, review sentiment, or discussion sentiment.

45. The system of claim 41 , wherein the conversational Al assistant initiates or recommends a group discussion based on a user question or detected marketplace trend.

46. The system of claim 1 , wherein the merchant analytics layer generates analytics for group trends, product spikes, purchase clusters, peer influence, discussion activity, recommendation engagement, reward redemption, or social conversion.

47. The system of claim 46, wherein the merchant analytics layer uses time-series forecasting, cohort analysis, graph analytics, trend detection, or predictive modeling.

48. The system of claim 46, wherein merchant analytics are presented through a dashboard.Attorney Ref. No. 0252-11758-5- 29 - 49. The system of claim 46, wherein merchant analytics are generated from aggregated or anonymized commerce graph data.

50. The system of claim 46, wherein the merchant analytics layer identifies a group-level demand signal based on marketplace transaction history and social engagement.

51. The system of claim 46, wherein the merchant analytics layer recommends merchant actions including offer creation, campaign adjustment, product targeting, group targeting, inventory planning, or reward threshold adjustment.

52. The system of claim 1, wherein transaction, social graph, financial, or recommendation data is encrypted in transit or at rest.

53. The system of claim 1, wherein user data is anonymized, pseudonymized, or aggregated before being exposed to merchants.

54. The system of claim 1 , wherein a user interface permits a user to manage privacy controls for marketplace transaction sharing, financial data syncing, group membership, recommendation visibility, or merchant analytics participation.

55. The system of claim 1 , wherein the system applies GDPR, CCPA, HIPAA-adjacent, or jurisdiction-specific privacy rules through configurable consent workflows.

56. The system of claim 1 , wherein edge device preprocessing is performed before cloud synchronization.

57. The system of claim 1 , wherein a privacy rule prevents a collaborative commerce object from exposing raw financial data.Attorney Ref. No. 0252-11758-5- 30 - 58. A computer-implemented method for converting marketplace infrastructure into a collaborative social commerce network, comprising:authenticating a user with a marketplace account; retrieving marketplace transaction history associated with the user;linking the marketplace transaction history to one or more social graph relationships;generating commerce graph nodes and edges representing users, products, merchants, sellers, marketplace transactions, and social relationships;forming one or more Al-generated peer groups using marketplace transaction data and social graph data;generating collaborative commerce objects from the commerce graph; generating product, group, discussion, merchant, or offer recommendations; updating reward or incentive states based on engagement within the collaborative commerce network; andgenerating merchant analytics based on group-level, graph-level, transactionlevel, or engagement-level activity.

59. The method of claim 58, further comprising synchronizing financial, bank, card, email receipt, or transaction-adjacent data under user consent.

60. The method of claim 58, wherein forming one or more Al-generated peer groups comprises applying collaborative filtering, clustering, graph neural network processing, or purchase similarity analysis.

61. The method of claim 58, further comprising generating a purchase feed from marketplace transaction history.

62. The method of claim 58, further comprising generating a product discussion thread from a detected group-level marketplace transaction pattern.Attorney Ref. No. 0252-11758-5- 31 - 63. The method of claim 58, further comprising ranking recommendations using marketplace transaction data and social graph proximity.

64. The method of claim 58, further comprising distributing rewards through a smart contract or platform reward engine.

65. The method of claim 58, further comprising generating a conversational Al shopping response using marketplace transaction data and group data.

66. The method of claim 58, further comprising generating a merchant dashboard displaying group trends, purchase spikes, predictive insights, or reward performance.

67. The method of claim 58, further comprising anonymizing or aggregating commerce graph data before exposing merchant analytics.

68. The method of claim 58, further comprising updating the commerce graph based on a new marketplace transaction, social interaction, group activity, reward event, or merchant campaign event.

69. A non-transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to:authenticate a user with a marketplace account; retrieve marketplace transaction history;link marketplace transaction data with social graph data; generate commerce graph nodes and edges;form Al-generated groups using marketplace and social graph data; generate collaborative commerce objects; generate recommendations; update reward states based on engagement; andgenerate merchant analytics.