Systems and methods for automating pricing desk operation

A computer-implemented method for automating pricing desk operations, comprising:

• receiving, by at least one processor, an initial offer requested by a client, wherein the initial offer comprises offer parameters in relation to a financial product;
• receiving, by the at least one processor, input context information associated with the initial offer;
• processing, via the at least one processor, the initial offer and the input context information using a machine learning model to generate a proposed counteroffer, the first machine learning model being trained, using historical offer data and corresponding historical counteroffers provided by analysts, to generate proposed counteroffers based on offer parameters associated with the initial offers and context information associated with the initial offers;
• processing, via the at least one processor, the proposed counteroffer and the input context information using a second machine learning model to determine an acceptance probability corresponding to a probability that the proposed counteroffer will result in a positive client decision, second machine learning model being trained, using historical offer data and corresponding historical client decisions, to classify offers according to positive or negative client decisions based on historical offer parameters associated with the offers and historical context information associated with the historical offers;
• when the acceptance probability of the proposed counteroffer is above a predetermined threshold, transmitting the proposed counteroffer for communication to the client;
• and
• when the acceptance probability of the proposed counteroffer is below the predetermined threshold, optimizing the proposed counteroffer by:
• generating, via the at least one processor, a modified offer by altering the offer parameters of the proposed counteroffer;
• processing, via the at least one processor, the modified offer and the input context information using the second machine learning model to determine a modified acceptance probability corresponding to a probability that the modified offer will result in a positive client decision;
• and
• repeating the generating of the modified offer and the processing of the modified offer using the machine learning module to obtain an optimized offer having optimized offer parameters and an until the modified acceptance probability of the modified offer is above the predetermined threshold;
• and
• transmitting the modified offer for communication to the client.

A non-transitory computer-readable medium having instructions stored thereon which, when executed by at least one processor, cause the at least one processor to:

• receive an initial offer requested by a client, wherein the initial offer comprises offer parameters in relation to a financial product;
• receive input context information associated with the initial offer;
• process the initial offer and the input context information using a first machine learning model to generate a proposed counteroffer, the first machine learning model being trained, using historical offer data and corresponding historical counteroffers provided by analysts, to generate proposed counteroffers based on offer parameters associated with the historical initial offers and context information associated with the historical initial offers;
• process the proposed counteroffer and the input context information using a second machine learning model to determine an acceptance probability corresponding to a probability that the proposed counteroffer will result in a positive client decision, the second machine learning module model being trained, using the historical offer data and corresponding historical client decisions, to classify offers according to positive or negative client decisions based on historical offer parameters associated with the offers and historical context information associated with the offers,
• when the acceptance probability of the proposed counteroffer is above a predetermined threshold, transmit the proposed counteroffer for communication to the client;
• and
• when the acceptance probability of the proposed counteroffer is below a predetermined threshold, optimize the proposed counteroffer by:
• generating a modified offer by altering the offer parameters of the proposed counteroffer;
• processing the modified offer and the input context information using the second machine learning model to determine a modified acceptance probability corresponding to a probability that the modified offer will result in a positive client decision;
• and
• repeating the generating of the modified offer and the processing of the modified offer until the modified acceptance probability of the modified offer is above the predetermined threshold;
• and
• transmit the modified offer for communication to the client.