Method, System, and Computer Program Product for Wait Time Estimation Using Predictive Modeling

Abstract

Described are a system, method, and computer program product for wait time estimation using predictive modeling. The method includes receiving a request for a predictive wait time estimate from a user including a designated time and a selection of a merchant. The method also includes determining an initial queue length and determining a service rate for each subinterval of a plurality of subintervals from the current time to the designated time. The method further includes producing a plurality of arrival rates using a trained predictive model, and determining a difference between an arrival rate and a service rate for each subinterval, to produce a plurality of changes in queue length. The method further includes determining a queue length based on the plurality of changes in queue length, generating the predictive wait time estimate based on the queue length, and transmitting the predictive wait time estimate to the user.

What is claimed is: 
     
         1 . A computer-implemented method comprising:
 receiving, with at least one processor, a request for a predictive wait time estimate from a communication device of a user, wherein the request comprises a designated time and a selection of a merchant;   determining, with at least one processor, an initial queue length associated with the merchant at a current time preceding the designated time;   determining, with at least one processor, a service rate for each subinterval of a plurality of subintervals from the current time to the designated time based on previously processed transactions to produce a plurality of service rates;   determining, with at least one processor, an arrival rate for each subinterval of the plurality of subintervals from the current time to the designated time using a trained predictive model to produce a plurality of arrival rates, wherein the trained predictive model is trained on transaction data representative of a plurality of transactions between a plurality of transaction accounts and at least one merchant completed during a sample time period preceding the current time, and wherein the trained predictive model is trained to output a predicted arrival rate given an input of a time associated with a subinterval of the plurality of subintervals;   determining, with at least one processor, a difference between an arrival rate of the plurality of arrival rates and a service rate of the plurality of services rates for each subinterval of the plurality of subintervals, to produce a plurality of changes in queue length for each subinterval of the plurality of subintervals;   determining, with at least one processor, a queue length at the designated time based on the initial queue length and the plurality of changes in queue length;   generating, with at least one processor, the predictive wait time estimate based on the queue length at the designated time and a service rate at the designated time; and   transmitting, with at least one processor, a response to the communication device of the user, wherein the response comprises the predictive wait time estimate.   
     
     
         2 . The method of  claim 1 , wherein the designated time is based on the current time plus a travel time for the user to travel from a current location of the user to a location of the merchant. 
     
     
         3 . The method of  claim 2 , further comprising transmitting to the communication device of the user, with at least one processor, a list comprising a plurality of merchants, wherein the selection of the merchant is based on the list comprising the plurality of merchants. 
     
     
         4 . The method of  claim 3 , further comprising generating, with at least one processor, the list comprising the plurality of merchants based at least partly on a proximity of the location of the user to a location of each merchant of the plurality of merchants. 
     
     
         5 . The method of  claim 1 , further comprising, in response to determining that the predictive wait time estimate is greater than or equal to a predetermined threshold wait time for the merchant, generating and transmitting, with at least one processor, a communication to the communication device of the user comprising an offer for a reduced service or product price for the merchant. 
     
     
         6 . The method of  claim 1 , further comprising, in response to determining that the predictive wait time estimate is greater than or equal to a predetermined threshold wait time for the merchant, generating and transmitting, with at least one processor, a communication to a communication device of the merchant comprising an alert configured to cause the merchant to take action to increase a current service rate of the merchant. 
     
     
         7 . The method of  claim 1 , further comprising, in response to determining that the predictive wait time estimate is less than or equal to a predetermined minimum wait time for the merchant, generating and transmitting, with at least one processor, a communication to the communication device of the user comprising an advertisement for the merchant. 
     
     
         8 . A system comprising at least one processor, wherein the at least one processor is programmed and/or configured to:
 receive a request for a predictive wait time estimate from a communication device of a user, wherein the request comprises a designated time and a selection of a merchant;   determine an initial queue length associated with the merchant at a current time preceding the designated time;   determine a service rate for each subinterval of a plurality of subintervals from the current time to the designated time based on previously processed transactions to produce a plurality of service rates;   determine an arrival rate for each subinterval of the plurality of subintervals from the current time to the designated time using a trained predictive model to produce a plurality of arrival rates, wherein the trained predictive model is trained on transaction data representative of a plurality of transactions between a plurality of transaction accounts and at least one merchant completed during a sample time period preceding the current time, and wherein the trained predictive model is trained to output a predicted arrival rate given an input of a time associated with a subinterval of the plurality of subintervals;   determine a difference between an arrival rate of the plurality of arrival rates and a service rate of the plurality of services rates for each subinterval of the plurality of subintervals, to produce a plurality of changes in queue length for each subinterval of the plurality of subintervals;   determine a queue length at the designated time based on the initial queue length and the plurality of changes in queue length;   generate the predictive wait time estimate based on the queue length at the designated time and a service rate at the designated time; and   transmit a response to the communication device of the user, wherein the response comprises the predictive wait time estimate.   
     
     
         9 . The system of  claim 8 , wherein the designated time is based on the current time plus a travel time for the user to travel from a current location of the user to a location of the merchant. 
     
     
         10 . The system of  claim 9 , wherein the at least one processor is further programmed and/or configured to transmit to the communication device of the user a list comprising a plurality of merchants, wherein the selection of the merchant is based on the list comprising the plurality of merchants. 
     
     
         11 . The system of  claim 10 , wherein the at least one processor is further programmed and/or configured to generate the list comprising the plurality of merchants based at least partly on a proximity of the location of the user to a location of each merchant of the plurality of merchants. 
     
     
         12 . The system of  claim 8 , wherein the at least one processor is further programmed and/or configured to, in response to determining that the predictive wait time estimate is greater than or equal to a predetermined threshold wait time for the merchant, generate and transmit a communication to the communication device of the user comprising an offer for a reduced service or product price for the merchant. 
     
     
         13 . The system of  claim 8 , wherein the at least one processor is further programmed and/or configured to, in response to determining that the predictive wait time estimate is greater than or equal to a predetermined threshold wait time for the merchant, generate and transmit a communication to a communication device of the merchant comprising an alert configured to cause the merchant to take action to increase a current service rate of the merchant. 
     
     
         14 . The system of  claim 8 , wherein the at least one processor is further programmed and/or configured to, in response to determining that the predictive wait time estimate is less than or equal to a predetermined minimum wait time for the merchant, generate and transmit a communication to the communication device of the user comprising an advertisement for the merchant. 
     
     
         15 . A computer program product comprising at least one non-transitory computer-readable medium storing one or more instructions that, when executed by at least one processor, cause the at least one processor to:
 receive a request for a predictive wait time estimate from a communication device of a user, wherein the request comprises a designated time and a selection of a merchant;   determine an initial queue length associated with the merchant at a current time preceding the designated time;   determine a service rate for each subinterval of a plurality of subintervals from the current time to the designated time based on previously processed transactions to produce a plurality of service rates;   determine an arrival rate for each subinterval of the plurality of subintervals from the current time to the designated time using a trained predictive model to produce a plurality of arrival rates, wherein the trained predictive model is trained on transaction data representative of a plurality of transactions between a plurality of transaction accounts and at least one merchant completed during a sample time period preceding the current time, and wherein the trained predictive model is trained to output a predicted arrival rate given an input of a time associated with a subinterval of the plurality of subintervals;   determine a difference between an arrival rate of the plurality of arrival rates and a service rate of the plurality of services rates for each subinterval of the plurality of subintervals, to produce a plurality of changes in queue length for each subinterval of the plurality of subintervals;   determine a queue length at the designated time based on the initial queue length and the plurality of changes in queue length;   generate the predictive wait time estimate based on the queue length at the designated time and a service rate at the designated time; and   transmit a response to the communication device of the user, wherein the response comprises the predictive wait time estimate.   
     
     
         16 . The computer program product of  claim 15 , wherein the designated time is based on the current time plus a travel time for the user to travel from a current location of the user to a location of the merchant. 
     
     
         17 . The computer program product of  claim 16 , wherein the one or more instructions further cause the at least one processor to transmit to the communication device of the user a list comprising a plurality of merchants, wherein the selection of the merchant is based on the list comprising the plurality of merchants. 
     
     
         18 . The computer program product of  claim 17 , wherein the one or more instructions further cause the at least one processor to generate the list comprising the plurality of merchants based at least partly on a proximity of the location of the user to a location of each merchant of the plurality of merchants. 
     
     
         19 . The computer program product of  claim 15 , wherein the one or more instructions further cause the at least one processor to, in response to determining that the predictive wait time estimate is greater than or equal to a predetermined threshold wait time for the merchant, generate and transmit a communication to the communication device of the user comprising an offer for a reduced service or product price for the merchant. 
     
     
         20 . The computer program product of  claim 15 , wherein the one or more instructions further cause the at least one processor to, in response to determining that the predictive wait time estimate is less than or equal to a predetermined minimum wait time for the merchant, generate and transmit a communication to the communication device of the user comprising an advertisement for the merchant.