Method and system for intelligently settling bridged transactions
Methods and systems for intelligently settling bridged transactions are disclosed. The method performed by a server system includes receiving a payment authorization message associated with an ongoing payment transaction from an issuer server. Here, the ongoing payment transaction is a bridged transaction with the issuer server operating in a single message system and an acquirer server operating in a dual message system. Method includes extracting a transaction feature set from the ongoing payment transaction and accessing a historical trend feature set from a database. Method includes generating, by one or more clearing prediction models associated with the server system, a clearing score for the ongoing payment transaction based, at least in part, on the transaction feature set and the historical trend feature set. Method includes transmitting a hold transaction message to the issuer server based, at least in part, on the clearing score being lower than a predefined threshold.
1 . A computer-implemented method, comprising:
receiving, by a server system, a payment authorization message associated with an ongoing payment transaction from an issuer server operating in a single message system;
determining, using a machine learning model, a likelihood of an absence of a clearing message for the ongoing payment transaction from an acquirer server operating in a dual message system;
based on the likelihood of the absence of the clearing message, identifying the ongoing payment transaction as a bridged transaction that is unlikely to be cleared by the acquirer server operating in the dual message system with the issuer server operating in the single message system;
extracting, by the server system, a transaction feature set from the ongoing payment transaction;
accessing, by the server system, a historical trend feature set from a database associated with the server system, the historical trend feature set including metrics related to historical bridged transactions associated with the issuer server and the acquirer server;
generating, by one or more clearing prediction models associated with the server system, a clearing score for the ongoing payment transaction based, at least in part, on the transaction feature set and the historical trend feature set, the clearing score indicating a likelihood of the bridged transaction being delayed or failed by the acquirer server operating in the dual message system; and
transmitting, by the server system, a hold transaction message to the issuer server operating in the single message system based, at least in part, on the clearing score being lower than a predefined threshold.
2 . The computer-implemented method as claimed in claim 1 , wherein generating the clearing score comprises:
determining, by at least one model from the one or more clearing prediction models, a transaction clearance likelihood score based, at least in part, on the transaction feature set and a historical authentication feature set from the historical trend feature set;
determining, by at least another model from the one or more clearing prediction models, a transaction dispute likelihood score based, at least in part, on the transaction feature set and a historical dispute feature set from the historical trend feature set; and
computing, by the server system, the clearing score based, at least in part, on the transaction clearance likelihood score and the transaction dispute likelihood score.
3 . The computer-implemented method as claimed in claim 1 , further comprising:
receiving, by the server system, a transaction clearing message for the ongoing payment transaction from the acquirer server; and
transmitting, by the server system, a settlement initiation message to the issuer server in response to receiving the transaction clearing message.
4 . The computer-implemented method as claimed in claim 1 , further comprising:
accessing, by the server system, a historical transaction dataset from the database, the historical transaction dataset comprising transaction-related information associated with a plurality of transactions performed by a plurality of cardholders with a plurality of merchants;
generating, by the server system, the historical trend feature set based, at least in part, on the transaction-related information associated with the plurality of transactions; and
storing, by the server system, the historical trend feature set in the database.
5 . The computer-implemented method as claimed in claim 1 , further comprising:
transmitting, by the server system, a settlement initiation message to the issuer server based, at least in part, on the clearing score being at least equal to the predefined threshold.
6 . The computer-implemented method as claimed in claim 5 , wherein the hold transaction message and the settlement initiation message are Application Programming Interface (API) messages.
7 . The computer-implemented method as claimed in claim 1 , wherein the transaction feature set comprises at least one of merchant category, merchant industry, transaction amount, pre-authorization amount, Decision Intelligence (DI) score, card present/card not present indicator, and e-Commerce/recurring/POS transaction indicator.
8 . The computer-implemented method as claimed in claim 1 , wherein the historical trend feature set comprises a historical authentication feature set and a historical dispute feature set.
9 . The computer-implemented method as claimed in claim 1 , wherein each model of the one or more clearing prediction models is a decision tree-based Machine Learning model.
10 . The computer-implemented method as claimed in claim 1 , wherein the server system is a payment server associated with a payment network.
11 . A server system, comprising:
a communication interface;
a memory comprising executable instructions; and
a processor communicably coupled to the communication interface and the memory, the processor configured to cause the server system to at least:
receive a payment authorization message associated with an ongoing payment transaction from an issuer server operating in a single message system;
determine, using a machine learning model, a likelihood of an absence of a clearing message for the ongoing payment transaction from an acquirer server operating in a dual message system;
based on the likelihood of the absence of the clearing message, identify the ongoing payment transaction as a bridged transaction that is unlikely to be cleared by the acquirer server operating in the dual message system with the issuer server operating in the single message system;
extract a transaction feature set from the ongoing payment transaction;
access a historical trend feature set from a database associated with the server system, the historical trend feature set including metrics related to historical bridged transactions associated with the issuer server and the acquirer server;
generate, by one or more clearing prediction models associated with the server system, a clearing score for the ongoing payment transaction based, at least in part, on the transaction feature set and the historical trend feature set, the clearing score indicating a likelihood of the bridged transaction being delayed or failed by the acquirer server operating in the dual message system; and
transmit a hold transaction message to the issuer server operating in the single message system based, at least in part, on the clearing score being lower than a predefined threshold.
12 . The server system as claimed in claim 11 , wherein to generate the clearing score, the server system is further caused at least to:
determine, by at least one model from the one or more clearing prediction models, a transaction clearance likelihood score based, at least in part, on the transaction feature set and a historical authentication feature set from the historical trend feature set;
determine, by at least another model from the one or more clearing prediction models, a transaction dispute likelihood score based, at least in part, on the transaction feature set and a historical dispute feature set from the historical trend feature set; and
compute the clearing score based, at least in part, on the transaction clearance likelihood score and the transaction dispute likelihood score.
13 . The server system as claimed in claim 11 , wherein the server system is further caused at least to:
access a historical transaction dataset from the database, the historical transaction dataset comprising transaction-related information associated with a plurality of transactions performed by a plurality of cardholders with a plurality of merchants;
generate the historical trend feature set based, at least in part, on the transaction-related information associated with the plurality of transactions; and
store the historical trend feature set in the database.
14 . The server system as claimed in claim 12 , wherein the server system is further caused at least to:
transmit a settlement initiation message to the issuer server based, at least in part, on the clearing score being at least equal to the predefined threshold.
15 . The server system as claimed in claim 14 , wherein the hold transaction message and the settlement initiation message are Application Programming Interface (API) messages.
16 . The server system as claimed in claim 11 , wherein the transaction feature set comprises a merchant category, a merchant industry, a transaction amount, a pre-authorization amount, and a Decision Intelligence (DI) score.
17 . The server system as claimed in claim 11 , wherein the historical trend feature set comprises a historical authentication feature set and a historical dispute feature set.
18 . The server system as claimed in claim 11 , wherein each model of the one or more clearing prediction models is a decision tree-based Machine Learning model.
19 . A non-transitory computer-readable storage medium comprising computer-executable instructions that, when executed by at least a processor of a server system, cause the server system to perform a method comprising:
receiving a payment authorization message associated with an ongoing payment transaction from an issuer server operating in a single message system;
determining, using a machine learning model, a likelihood of an absence of a clearing message for the ongoing payment transaction from an acquirer server operating in a dual message system;
based on the likelihood of the absence of the clearing message, identifying the ongoing payment transaction as a bridged transaction that is unlikely to be cleared by the acquirer server operating in the dual message system with the issuer server operating in the single message system;
extracting a transaction feature set from the ongoing payment transaction;
accessing a historical trend feature set from a database associated with the server system, the historical trend feature set including metrics related to historical bridged transactions associated with the issuer server and the acquirer server;
generating, by one or more clearing prediction models associated with the server system, a clearing score for the ongoing payment transaction based, at least in part, on the transaction feature set and the historical trend feature set, the clearing score indicating a likelihood of the bridged transaction being delayed or failed by the acquirer server operating in the dual message system; and
transmitting a hold transaction message to the issuer server operating in the single message system based, at least in part, on the clearing score being lower than a predefined threshold.
20 . The non-transitory computer-readable storage medium as claimed in claim 19 , wherein the method further comprises:
transmitting a settlement initiation message to the issuer server based, at least in part, on the clearing score being at least equal to the predefined threshold.