# US 2021/0174381 A1 · Methods and apparatus to project ratings for future broadcasts of media

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

- Number: US 2021/0174381 A1
- Document ID: US20210174381A1
- Status: Published application
- Kind: A1
- Application number: 17/121,323
- Filed: 2020-12-14
- Published: 2021-06-10
- Earliest claimed: 2014-11-24
- Assignees: The Nielsen Company (US), LLC
- Applicants: The Nielsen Company (US), LLC
- Inventors: Jingsong Cui; Peter Campbell Doe; Scott Sereday
- Web page: https://patentgrep.com/patent/US20210174381A1

## CPC

- G06Q 30/0202: Market predictions or forecasting for commercial activities
- G06Q 10/40: Business processes related to social networking or social networking services
- G06Q 30/0201: Market modelling; Market analysis; Collecting market data
- H04N 21/251: {Learning process for intelligent management, e.g. learning user preferences for recommending movies (details of learning user preferences for the retrieval of video data in a video database G06F16/739; computer systems using learning methods G06N3/08)}
- H04N 21/252: {Processing of multiple end-users' preferences to derive collaborative data}
- H04N 21/25891: {being end-user preferences (retrieval of video data in a video database based on user preferences G06F16/739; arrangements for recognizing users' preferences H04H60/46; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18)}
- H04N 21/44226: {on social networks}
- H04N 21/4532: {involving end-user characteristics, e.g. viewer profile, preferences (monitoring of user activities for profile generation for accessing a video database G06F16/739; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18)}
- H04N 21/4665: {involving classification methods, e.g. Decision trees}
- H04N 21/6582: {Data stored in the client, e.g. viewing habits, hardware capabilities, credit card number (arrangements where receivers interact with the broadcast H04H20/38)}
- 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
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

Methods, apparatus, systems and articles of manufacture are disclosed to project ratings for future broadcasts of media. Disclosed example methods include normalizing, with a processor, audience measurement data corresponding to media exposure data, social media exposure data and programming information associated with a future quarter to determine normalized audience measurement data. Disclosed example methods also include classifying a media asset based on the programming information to determine a media asset classification. Disclosed example methods also include building, with the processor, a projection model based on a first subset of the normalized audience measurement data, the first subset of the normalized audience measurement data associated with a first time frame relative to the future quarter, the first subset of the normalized audience measurement data based on the media asset classification, and applying, with the processor, the programming information to the projection model to project ratings for the media asset.

## Claims

### Claim 1

(canceled)

### Claim 2

An apparatus comprising:
a data transformer to transform audience measurement data to determine normalized training data;
a model builder to:
build respective demographic segment machine learning models associated with corresponding demographic segments of interest;
select a subset of predictive features from the normalized training data according to a predictive feature schema and a first one of the demographic segments, the predictive feature schema selected from a plurality of predictive feature schemas based on a classification of a media asset, the subset of predictive features including historical ratings data for the media asset;
train a first one of the respective demographic segment machine learning models based on at least a portion of the subset of predictive features to reduce error between the historical ratings data and predicted ratings data output by the first one of the respective demographic segment machine learning models, the first one of the respective demographic segment machine learning models associated with the first one of the demographic segments; and
a ratings projector to apply the respective demographic segment machine learning models to predict ratings for the media asset for a future quarter.

### Claim 3 (depends on 2)

The apparatus of claim 2, wherein the data transformer is to transform media exposure data, social media exposure data, programming information, and demographic information included in the audience measurement data to determine the normalized training data.

### Claim 4 (depends on 2)

The apparatus of claim 2, wherein the model builder is to exclude a portion of the historical ratings data from training data used to train the first one of the respective demographic segment machine learning models, the portion of the historical ratings data corresponding to a gap between a current quarter and the future quarter.

### Claim 5 (depends on 4)

The apparatus of claim 4, wherein the gap includes at least a first number of quarters between the current quarter and the future quarter.

### Claim 6 (depends on 5)

The apparatus of claim 5, wherein the first number of quarters is three quarters.

### Claim 7 (depends on 2)

The apparatus of claim 2, wherein the model builder is to classify the media asset as a television series when a characteristic of the media asset is indicative of at least one of a premier episode, a repeat episode, or a new episode.

### Claim 8 (depends on 2)

The apparatus of claim 2, wherein the ratings projector is to apply the first one of the respective demographic segment machine learning models to predict first ratings for the media asset for the future quarter, the first ratings corresponding to the first one of the demographic segments.

### Claim 9

At least one non-transitory computer readable storage medium comprising instructions that, when executed, cause one or more processors to at least:
transform audience measurement data to determine normalized training data;
build respective demographic segment machine learning models associated with corresponding demographic segments of interest;
select a subset of predictive features from the normalized training data according to a predictive feature schema and a first one of the demographic segments, the predictive feature schema selected from a plurality of predictive feature schemas based on a classification of a media asset, the subset of predictive features including historical ratings data for the media asset;
train a first one of the respective demographic segment machine learning models based on at least a portion of the subset of predictive features to reduce error between historical ratings data and predicted ratings data output by the first one of the respective demographic segment machine learning models, the first one of the respective demographic segment machine learning models associated with the first one of the demographic segments; and
apply the respective demographic segment machine learning models to predict ratings for the media asset for a future quarter.

### Claim 10 (depends on 9)

The at least one non-transitory computer readable storage medium of claim 9, wherein the instructions cause the one or more processors to transform media exposure data, social media exposure data, programming information, and demographic information included in the audience measurement data to determine the normalized training data.

### Claim 11 (depends on 9)

The at least one non-transitory computer readable storage medium of claim 9, wherein the instructions cause the one or more processors to exclude a portion of the historical ratings data from training data used to train the first one of the respective demographic segment machine learning models, the portion of the historical ratings data corresponding to a gap between a current quarter and the future quarter.

### Claim 12 (depends on 11)

The at least one non-transitory computer readable storage medium of claim 11, wherein the gap includes at least a first number of quarters between the current quarter and the future quarter.

### Claim 13 (depends on 12)

The at least one non-transitory computer readable storage medium of claim 12, wherein the first number of quarters is three quarters.

### Claim 14 (depends on 9)

The at least one non-transitory computer readable storage medium of claim 9, wherein the instructions cause the one or more processors to classify the media asset as a television series when a characteristic of the media asset is indicative of at least one of a premier episode, a repeat episode, or a new episode.

### Claim 15 (depends on 9)

The at least one non-transitory computer readable storage medium of claim 9, wherein the instructions cause the one or more processors to apply the first one of the respective demographic segment machine learning models to predict first ratings for the media asset for the future quarter, the first ratings corresponding to the first one of the demographic segments.

### Claim 16

A method comprising:
transforming audience measurement data to determine normalized training data;
building respective demographic segment machine learning models associated with corresponding demographic segments of interest;
selecting a subset of predictive features from the normalized training data according to a predictive feature schema and a first one of the demographic segments, the predictive feature schema selected from a plurality of predictive feature schemas based on a classification of a media asset, the subset of predictive features including historical ratings data for the media asset;
training, by executing an instruction with at least one processor, a first one of the respective demographic segment machine learning models based on at least a portion of the subset of predictive features to reduce error between historical ratings data and predicted ratings data output by the first one of the respective demographic segment machine learning models, the first one of the respective demographic segment machine learning models associated with the first one of the demographic segments; and
applying, by executing an instruction with the at least one processor, the respective demographic segment machine learning models to predict ratings for the media asset for a future quarter.

### Claim 17 (depends on 16)

The method of claim 16, wherein the transforming of the audience measurement data includes transforming media exposure data, social media exposure data, programming information, and demographic information included in the audience measurement data to determine the normalized training data.

### Claim 18 (depends on 16)

The method of claim 16, further including excluding a portion of the historical ratings data from training data used to train the first one of the respective demographic segment machine learning models, the portion of the historical ratings data corresponding to a gap between a current quarter and the future quarter.

### Claim 19 (depends on 18)

The method of claim 18, wherein the gap includes at least a first number of quarters between the current quarter and the future quarter.

### Claim 20 (depends on 16)

The method of claim 16, further including classifying the media asset as a television series when a characteristic of the media asset is indicative of at least one of a premier episode, a repeat episode, or a new episode.

### Claim 21 (depends on 16)

The method of claim 16, further including applying the first one of the respective demographic segment machine learning models to predict first ratings for the media asset for the future quarter, the first ratings corresponding to the first one of the demographic segments.
