Computer-network-based referral service functions and user interfaces

Abstract

A method of improving a network-based marketplace system with referral-service functionality is disclosed. One or more notifications are received from a client device of a first user of a plurality of users. The one or more notifications include an authorization from the first user to make a payment to complete a purchase of an item included in a listing posted on the network-based publication system. The one or more notifications also include a referral code associated with the authorization. The payment is received from the first user into a holding account. Based on the referral code, a second user of the plurality of users is identified as a referrer of the purchase. The payment is divided into a plurality of payments to be made to a seller of the item as a purchase fee and to be made to the referrer of the purchase as a referral fee.

What is claimed is: 
     
         1 . A system comprising:
 one or more computer processors;   one or more computer memories;   a set of instructions incorporated into the one or more computer memories, the set of instructions configuring the one or more computer processors to perform operations comprising:   determining that a user of a network-based publication system has specified general information about an item for listing on the network-based publication system;   seeding a machine-learning algorithm with one or more parameters associated with transaction data for previous items listed on the network-based publication system, the previous items identified based on a matching of one or more attributes of the previous items to the specified general information;   training the machine-learning model in real-time as additional transaction data is collected;   determining a suggested referral fee for the item based on an application of the machine-learning algorithm to the general information; and   causing a user interface element to be presented in a user interface of the network-based publication system, the user interface element being activatable for associating the suggested referral fee with the item.   
     
     
         2 . The system of  claim 1 , wherein the training of the machine-learning model in real-time includes discarding portions of the transaction data or the additional transaction data that are outside of a specified window of time. 
     
     
         3 . The system of  claim 1 , wherein the one or more parameters relate to at least one of a sales price or a speed of sale of each of the previous items. 
     
     
         4 . The system of  claim 1 , wherein the one or more parameters relate to at least one of social actions of potential buyers or other behaviors of respective buyers. 
     
     
         5 . The system of  claim 1 , wherein the one or more parameters are selected by the user via an additional user interface of the network-based publication system. 
     
     
         6 . The system of  claim 1 , wherein the application of the machine-learning model to the general information includes determining an optimal referral fee for the item based on the one or more parameters. 
     
     
         7 . The system of  claim 1 , further comprising, based on a completion of a transaction pertaining to the item, causing the referral fee to be transferred to a referrer. 
     
     
         8 . The system of  claim 6 , wherein the referrer is identified based on a receiving of a notification that includes a unique code identifying the referrer. 
     
     
         9 . A method comprising:
 determining that a user of a network-based publication system has specified general information about an item for listing on the network-based publication system;   seeding a machine-learning algorithm with one or more parameters associated with transaction data for previous items listed on the network-based publication system, the previous items identified based on a matching of one or more attributes of the previous items to the specified general information;   training the machine-learning model in real-time as additional transaction data is collected;   determining a suggested referral fee for the item based on an application of the machine-learning algorithm to the general information; and   causing a user interface element to be presented in a user interface of the network-based publication system, the user interface element being activatable for associating the suggested referral fee with the item   
     
     
         10 . The method of  claim 9 , wherein the training of the machine-learning model in real-time includes discarding portions of the transaction data or the additional transaction data that are outside of a specified window of time. 
     
     
         11 . The method of  claim 9 , wherein the one or more parameters relate to at least one of a sales price or a speed of sale of each of the previous items. 
     
     
         12 . The method of  claim 9 , wherein the one or more parameters relate to at least one of social actions of potential buyers or other behaviors of respective buyers. 
     
     
         13 . The method of  claim 9 , wherein the one or more parameters are selected by the user via an additional user interface of the network-based publication system. 
     
     
         14 . The method of  claim 9 , wherein the application of the machine-learning model to the general information includes determining an optimal referral fee for the item based on the one or more parameters. 
     
     
         15 . The method of  claim 9 , further comprising, based on a completion of a transaction pertaining to the item, causing the referral fee to be transferred to a referrer. 
     
     
         16 . The method of  claim 15 , wherein the referrer is identified based on a receiving of a notification that includes a unique code identifying the referrer. 
     
     
         17 . A non-transitory computer-readable storage medium storing a set of instructions that, when executed by one or more computer processors, causes the one or more computer processors to perform operations, the operations comprising:
 determining that a user of a network-based publication system has specified general information about an item for listing on the network-based publication system;   seeding a machine-learning algorithm with one or more parameters associated with transaction data for previous items listed on the network-based publication system, the previous items identified based on a matching of one or more attributes of the previous items to the specified general information;   training the machine-learning model in real-time as additional transaction data is collected;   determining a suggested referral fee for the item based on an application of the machine-learning algorithm to the general information; and   causing a user interface element to be presented in a user interface of the network-based publication system, the user interface element being activatable for associating the suggested referral fee with the item   
     
     
         18 . The non-transitory computer-readable storage medium of  claim 17 , wherein the training of the machine-learning model in real-time includes discarding portions of the transaction data or the additional transaction data that are outside of a specified window of time. 
     
     
         19 . The non-transitory computer-readable storage medium of  claim 17 , wherein the one or more parameters relate to at least one of a sales price or a speed of sale of each of the previous items. 
     
     
         20 . The non-transitory computer-readable storage medium of  claim 17 , wherein the one or more parameters relate to at least one of social actions of potential buyers or other behaviors of respective buyers.