# US 2026/0260269 A1 · Optimizing bids for media content in a demand-side platform

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0260269 A1
- Document ID: US20260260269A1
- Status: Published application
- Kind: A1
- Application number: 19/555,672
- Filed: 2026-03-03
- Published: 2026-09-03
- Earliest claimed: 2025-03-03
- Assignees: Viant Technology LLC
- Applicants: Viant Technology LLC
- Inventors: Xin Chen; Fabrizio Blanco
- Web page: https://patentgrep.com/patent/US20260260269A1

## CPC

- G06Q 30/0275: {Auctions}
- G06Q 30/0249: {based upon budgets or funds}
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

A system and method provide the ability to optimize a bid in a real time bid (RTB) auction. A metadata producer (MDP) application includes an online adaptive learning component that autonomously produces campaign metadata including budget pacing, retrieves historical RTB auction data, and generates a price adjustment variable. Mediator application(s) handle RTB auctions, receive a predicted offer price and predicted key performance index (KPI) performance metrics from a machine learning (ML) model, and choose the bid offer price based on the price adjustment variable, the predicted offer price and predicted KPI performance metric. The ML model predicts a win-price prediction and KPI performance metrics for the mediator. A feedback loop provides bids and impression delivery information from the mediator application to the MDP application.

## Claims

### Claim 1

A computer-implemented system for optimizing a bid in a real time bid (RTB) auction comprising:
(a) a computer having a memory;
(b) a processor executing on the computer;
(c) the memory storing a set of instructions, wherein the set of instructions, when executed by the processor cause the processor to perform operations;
(d) a metadata producer (MDP) application, executed via the operations on the processor, wherein the MDP application comprises an online adaptive learning component configured to autonomously, at predefined time interval cycles:
(i) produce campaign metadata including budget pacing;
(ii) retrieve historical RTB auction data including a snapshot of any prior interval cycles;
(iii) generate a price adjustment variable for adjusting a bid offer price based on the historical RTB auction data and the campaign metadata; and
(iv) provides the price adjustment variable to one or more mediator applications;
(e) the one or more mediator applications, executed via the operations on the processor, wherein the one or more mediator applications:
(i) handle RTB auctions including submitting a bid within the RTB auction;
(ii) receive RTB requests from a supply side platform (SSP);
(iii) make bid/no-bid decisions;
(iv) receive a predicted offer price and predicted key performance index (KPI) performance metrics from a machine learning (ML) model;
(v) choose the bid offer price based on the price adjustment variable generated by the MDP, and the predicted offer price and predicted KPI performance metrics received from the ML model; and
(vi) log bids and impression delivery information;
(f) the machine learning (ML) model, executed via the operations on the processor, wherein the ML model:
(i) includes a win-price prediction model that predicts the predicted offer price to win an RTB auction;
(ii) includes a KPI prediction model that predicts the KPI performance metrics; and
(iii) provides the predicted offer price and predicted KPI performance metrics to the mediator application; and
(g) a feedback loop, executed via the operations on the processor, wherein the feedback loop provides the bids and impression delivery information from the mediator application to the online adaptive learning component of the MDP application.

### Claim 2 (depends on 1)

The computer-implemented system of claim 1, wherein the win-price prediction model comprises:
a deep learning based predictive model that determines the predicted offer price in both first-price and second price RTB auctions by capturing feature patterns and data variations present in the RTB bid requests.

### Claim 3 (depends on 1)

The computer-implemented system of claim 1, wherein:
a training dataset for the win-price prediction model comprises historical winning prices;
the win-price prediction model applies a heuristic label adjustment to the training dataset;
the heuristic label adjustment considers factors such that the predicted offer price falls between a bid floor and the historical winning prices.

### Claim 4 (depends on 3)

The computer-implemented system of claim 3, further comprising:
the ML model refining the heuristic label adjustment using a statistical method that identifies a pattern across website categories.

### Claim 5 (depends on 1)

The computer-implemented system of claim 1, wherein:
the MDP dynamically adjusts the price adjustment variable to meet demands of different advertising campaigns; and
the mediator dynamically adjusts the bid offer price based on the dynamically adjusted price adjustment variable.

### Claim 6 (depends on 1)

The computer-implemented system of claim 1, wherein:
the bids and impression delivery information in the feedback loop comprise a time-slot evaluation metric that is utilized to quantify an effectiveness of the mediator application and the ML model;
the online adaptive learning component utilizes the time-slot evaluation metric to adjust the price adjustment variable.

### Claim 7 (depends on 1)

The computer-implemented system of claim 1, wherein the online adaptive learning component:
dynamically optimizes the price adjustment variable for individual orders within advertising campaigns.

### Claim 8 (depends on 1)

The computer-implemented system of claim 1, wherein:
budget delivery is the only goal considered by the MDP;
in generating the price adjustment variable, the online adaptive learning component optimizes an adjustment ratio.

### Claim 9 (depends on 1)

The computer-implemented system of claim 1, wherein:
both budget pacing and KPI optimization are goals considered by the MDP;
in generating the price adjustment variable, the online adaptive learning component optimizes both an adjustment ratio and a KPI slope.

### Claim 10 (depends on 1)

The computer-implemented system of claim 1, wherein:
an objective of the online adaptive learning component is to learn the price adjustment variable using gradient descent;
the online adaptive learning component formulates a process for optimizing the price adjustment variable as a constrained optimization problem that minimizes a hybrid loss function;
the hybrid loss function comprises a quadratic regression loss, a hinge loss, and an equality constraint;
the hybrid loss function is minimized resulting in an updated price adjustment variable in real time by the online adaptive learning component.

### Claim 11

A computer-implemented method for optimizing a bid in a real time bid (RTB) auction comprising, comprising:
(a) a metadata producer (MDP) application, executed on a computer, wherein the MDP application comprises an online adaptive learning component configured to autonomously, at predefined time interval cycles:
(i) produce campaign metadata including budget pacing;
(ii) retrieve historical RTB auction data including a snapshot of any prior interval cycles;
(iii) generate a price adjustment variable for adjusting a bid offer price based on the historical RTB auction data and the campaign metadata; and
(iv) provides the price adjustment variable to one or more mediator applications;
(b) the one or more mediator applications, executed on the computer, wherein the one or more mediator applications:
(i) handle RTB auctions including submitting a bid within the RTB auction;
(ii) receive RTB requests from a supply side platform (SSP);
(iii) make bid/no-bid decisions;
(iv) receive a predicted offer price and predicted key performance index (KPI) performance metrics from a machine learning (ML) model;
(v) choose the bid offer price based on the price adjustment variable generated by the MDP, and the predicted offer price and predicted KPI performance metrics received from the ML model; and
(vi) log bids and impression delivery information;
(f) the machine learning (ML) model, executed on the computer, wherein the ML model:
(i) includes a win-price prediction model that predicts the predicted offer price to win an RTB auction;
(ii) includes a KPI prediction model that predicts the KPI performance metrics; and
(iii) provides the predicted offer price and predicted KPI performance metrics to the mediator application; and
(g) a feedback loop, executed via the computer, wherein the feedback loop provides the bids and impression delivery information from the mediator application to the online adaptive learning component of the MDP application.

### Claim 12 (depends on 11)

The computer-implemented method of claim 11, wherein the win-price prediction model comprises:
a deep learning based predictive model that determines the predicted offer price in both first-price and second price RTB auctions by capturing feature patterns and data variations present in the RTB bid requests.

### Claim 13 (depends on 11)

The computer-implemented method of claim 11, wherein:
a training dataset for the win-price prediction model comprises historical winning prices;
the win-price prediction model applies a heuristic label adjustment to the training dataset;
the heuristic label adjustment considers factors such that the predicted offer price falls between a bid floor and the historical winning prices.

### Claim 14 (depends on 13)

The computer-implemented method of claim 13, further comprising:
the ML model refining the heuristic label adjustment using a statistical method that identifies a pattern across website categories.

### Claim 15 (depends on 11)

The computer-implemented method of claim 11, wherein:
the MDP dynamically adjusts the price adjustment variable to meet demands of different advertising campaigns; and
the mediator dynamically adjusts the bid offer price based on the dynamically adjusted price adjustment variable.

### Claim 16 (depends on 11)

The computer-implemented method of claim 11, wherein:
the bids and impression delivery information in the feedback loop comprise a time-slot evaluation metric that is utilized to quantify an effectiveness of the mediator application and the ML model;
the online adaptive learning component utilizes the time-slot evaluation metric to adjust the price adjustment variable.

### Claim 17 (depends on 11)

The computer-implemented method of claim 11, wherein the online adaptive learning component:
dynamically optimizes the price adjustment variable for individual orders within advertising campaigns.

### Claim 18 (depends on 11)

The computer-implemented method of claim 11, wherein:
budget delivery is the only goal considered by the MDP;
in generating the price adjustment variable, the online adaptive learning component optimizes an adjustment ratio.

### Claim 19 (depends on 11)

The computer-implemented method of claim 11, wherein:
both budget pacing and KPI optimization are goals considered by the MDP;
in generating the price adjustment variable, the online adaptive learning component optimizes both an adjustment ratio and a KPI slope.

### Claim 20 (depends on 11)

The computer-implemented method of claim 11, wherein:
an objective of the online adaptive learning component is to learn the price adjustment variable using gradient descent;
the online adaptive learning component formulates a process for optimizing the price adjustment variable as a constrained optimization problem that minimizes a hybrid loss function;
the hybrid loss function comprises a quadratic regression loss, a hinge loss, and an equality constraint;
the hybrid loss function is minimized resulting in an updated price adjustment variable in real time by the online adaptive learning component.
