# US 2022/0027959 A1 · Real-Time Bidding

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

- Number: US 2022/0027959 A1
- Document ID: US20220027959A1
- Status: Published application
- Kind: A1
- Application number: 17/296,195
- Filed: 2019-11-21
- Published: 2022-01-27
- Earliest claimed: 2018-11-21
- Assignees: LoopMe, Ltd.
- Applicants: LoopMe, Ltd.
- Inventors: Piyush Paliwal; Oleksii Renov; Leonard Newham
- Web page: https://patentgrep.com/patent/US20220027959A1

## CPC

- G06Q 30/0275: {Auctions}
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/00: Machine learning
- G06N 20/20: Ensemble learning
- G06Q 10/06315: {Needs-based resource requirements planning or analysis}
- 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
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

The demand-side platform (DSP) is a technological ingredient that fits into the larger real-time-bidding (RTB) ecosystem. DSPs enable advertisers to purchase ad impressions from a wide range of ad slots, generally via a second-price auction mechanism. In this aspect, predicting the auction winning price notably enhances the decision for placing the right bid value to win the auction and helps with the advertiser's campaign planning and traffic reallocation between campaigns. This is a difficult task because the observed winning price distribution is biased due to censorship; the DSP only observes the win price in the case of winning the auction. For losing bids, the win price remains censored. In this invention, we generalize the winning price model to incorporate a gradient boosting framework adapted to learn from both observed and censored data. This yields a boost in predictive performance in comparison to classic linear censored regression.

## Claims

### Claim 1

A data processing apparatus for minimising usage of computer hardware resource in an automated real-time auction, comprising a machine learning estimator arranged to receive historical data on the winning bids of previous auctions and also the losing bids of previous auctions and arranged to estimate the likely win price for a future auction, and
a bid determinator configured to receive data on a maximum bid for winning a future auction and the estimated win price from the estimator, and arranged to cause the hardware resource to be employed in entering the future auction only when the budget is not less than the estimated win price.

### Claim 2 (depends on 1)

The data processing apparatus of claim 1, wherein the bid determinator receives a profit margin goal which is used to adjust the estimated win price to ensure that auctions are only won with a sufficient profit margin

### Claim 3 (depends on 1)

The data processing apparatus of claim 1, wherein the estimator is configured to create a set of training data from the historical data on the winning bids and the losing bids, to calculate an overall loss function based on the set, and to calculate first and second order derivatives of the overall loss function to generate a win price model.

### Claim 4 (depends on 3)

The data processing apparatus of claim 3, wherein the estimator is configured to calculate a likelihood function of historical wins and a likelihood function of historical losses and to combine these functions to create the overall loss function.

### Claim 5 (depends on 2)

The data processing apparatus of claim 2, wherein the estimator is configured to create a set of training data from the historical data on the winning bids and the losing bids, to calculate an overall loss function based on the set, and to calculate first and second order derivatives of the overall loss function to generate a win price model.

### Claim 6 (depends on 5)

The data processing apparatus of claim 5, wherein the estimator is configured to calculate a likelihood function of historical wins and a likelihood function of historical losses and to combine these functions to create the overall loss function.

### Claim 7 (depends on 3)

The data processing apparatus of claim 3, wherein the estimator is configured to generalise the win price model using gradient boosting.

### Claim 8 (depends on 4)

The data processing apparatus of claim 4, wherein the estimator is configured to generalise the win price model using gradient boosting.

### Claim 9

A method of minimising usage of computer hardware resource in an automated real-time auction, comprising the steps of:
(a) receiving historical data on the winning bids of previous auctions and also the losing bids of previous auctions and estimating the likely win price for a future auction, and
(b) receiving data on a maximum bid for winning a future auction and the estimated win price from the estimator, and causing the hardware resource to be employed in entering the future auction only when the budget is not less than the estimated win price.

### Claim 10 (depends on 9)

The method of claim 9, further including an additional step of:
receiving a profit margin goal which is used to adjust the estimated win price to ensure that auctions are only won with a sufficient profit margin.

### Claim 11 (depends on 9)

The method of claim 9, further including an additional step, performed after the step of receiving historical data, of:
creating a set of training data from the historical data on the winning bids and the losing bids, calculating an overall loss function based on the set, and calculating first and second order derivatives of the overall loss function to generate a win price model.

### Claim 12 (depends on 10)

The method of claim 10, further including an additional step, performed after the step of receiving historical data, of:
creating a set of training data from the historical data on the winning bids and the losing bids, calculating an overall loss function based on the set, and calculating first and second order derivatives of the overall loss function to generate a win price model.

### Claim 13 (depends on 11)

The method of claim 11, further including additional steps of:
calculating one or more of a likelihood function of historical wins and a likelihood function of historical losses; and
combining the likelihood function of historical wins and the likelihood function of historical losses to create the overall loss function.

### Claim 14 (depends on 11)

The method of claim 11, including an additional step, performed after the creating step, of:
generalising the win price model using gradient boosting.

### Claim 15 (depends on 13)

The method of claim 13, including an additional step, performed after the creating step, of:
generalising the win price model using gradient boosting.

### Claim 16

A computer program product comprising instructions which, when the program is executed by a computer, cause the computer to carry out steps of:
(a) receiving historical data on the winning bids of previous auctions and also the losing bids of previous auctions and estimating the likely win price for a future auction, and
(b) receiving data on a maximum bid for winning a future auction and the estimated win price from the estimator, and causing the hardware resource to be employed in entering the future auction only when the budget is not less than the estimated win price.

### Claim 17 (depends on 16)

The computer program product of claim 16, wherein the computer carries out a further step of receiving a profit margin goal which is used to adjust the estimated win price to ensure that auctions are only won with a sufficient profit margin.

### Claim 18 (depends on 16)

The computer program product of claim 16, wherein the computer carries out a further step, performed after the step of receiving the historical data, of creating a set of training data from the historical data on the winning bids and the losing bids, calculating an overall loss function based on the set, and calculating first and second order derivatives of the overall loss function to generate a win price model.

### Claim 19 (depends on 17)

The computer program product of claim 17, wherein the computer carries out a further step, performed after the step of receiving the historical data, of creating a set of training data from the historical data on the winning bids and the losing bids, calculating an overall loss function based on the set, and calculating first and second order derivatives of the overall loss function to generate a win price model.

### Claim 20 (depends on 18)

The computer program product of claim 18, wherein the computer carries out a further step of calculating a likelihood function of historical wins and a likelihood function of historical losses and combining these functions to create the overall loss function.
