# Core Concepts & Capabilities

### About this export

| Field | Value |
| --- | --- |
| **content_type** | course |
| **platform** | contentstack-academy |
| **source_url** | https://www.contentstack.com/academy/courses/data-insights-core-concepts-capabilities |
| **language** | en |
| **product_area** | Contentstack Academy |
| **learning_path** | data-and-insights-practitioner-certification |
| **course_id** | data-insights-core-concepts-capabilities |
| **slug** | data-insights-core-concepts-capabilities |
| **version** | 2026-03-01 |
| **last_updated** | 2026-05-04 |
| **status** | published |
| **keywords** | ["Contentstack Academy"] |
| **summary_one_line** | This course is a high-level introduction to the Data & Insights platform (Lytics), designed to give you a foundational understanding of how the product works. We'll cover the key concepts and capabilities you'll explore … |
| **total_duration_minutes** | 16 |
| **lessons_count** | 8 |
| **video_lessons_count** | 7 |
| **text_lessons_count** | 1 |
| **linked_learning_path** | data-and-insights-practitioner-certification |
| **linked_assessment_ref** | LMS_UNCONFIGURED_COURSE_ASSESSMENT |
| **markdown_file_url** | /academy/md/courses/data-insights-core-concepts-capabilities.md |
| **generated_at** | 2026-05-04T05:36:51.587Z |
| **intended_audience** | [] |
| **prerequisites** | [] |
| **related_courses** | [] |

> **Academy MD v3** — companion `.md` for Ask AI. Quizzes and graded assessments are **LMS-only**; this file never contains answer keys.

## Course Overview

| Metadata | Value |
| --- | --- |
| Catalog duration | 15m 40s |
| Released (if known) | 2026-03-01 |
| Product area | Contentstack Academy |

### Description

_This course is a high-level introduction to the Data & Insights platform (Lytics), designed to give you a foundational understanding of how the product works. We'll cover the key concepts and capabilities you'll explore in more depth throughout the certification program._

### Overview

### What You'll Learn

This introductory session provides essential background on customer data platforms and hands-on experience with basic Lytics functionality. You'll understand the strategic importance of data & insights platforms (CDPS) and see real-time profile building in action.

### What We'll Cover

We'll start with the fundamentals—introducing what a Data & Insights platform is, the role of the data activation layer, and the critical importance of defining clear use cases before implementation. You'll learn to install the JavaScript tag and watch real-time customer profiles take shape, explore identity resolution basics, and get introduced to data collection methods, schema management, and audience building. We'll also provide your first look at Flows for journey orchestration.

### Learning objectives

1. Follow each lesson in order.
2. Practice in a training stack using placeholders **YOUR_STACK_API_KEY** and **YOUR_DELIVERY_TOKEN** in local `.env` files only.
3. Validate API responses against the official documentation.

### Topics covered

Contentstack Academy

## Course structure

```text
data-insights-core-concepts-capabilities/
├── 01-data-insights-course-2--what-is-a-profile · video · 85s
├── 02-data-insights-course-2--what-is-a-common-schema · video · 137s
├── 03-data-insights-course-2--how-does-scoring-work · video · 117s
├── 04-data-insights-course-2--what-are-behavioral-scores · video · 160s
├── 05-data-insights-course-2--what-are-interest-scores · video · 113s
├── 06-data-insights-course-2--how-do-audiences-work · video · 190s
├── 07-data-insights-course-2--can-i-create-custom-models · video · 138s
├── 08-data-insights-course-2--quiz · quiz (LMS only) · 3 min
```

## Lessons

### Lesson 01 — What is a profile?

<!-- ai_metadata: {"lesson_id":"01","type":"video","duration_seconds":85,"video_url":"https://cdn.jwplayer.com/previews/mMtDUT4b","thumbnail_url":"https://cdn.jwplayer.com/v2/media/mMtDUT4b/poster.jpg?width=720","topics":["What","profile"]} -->

#### Video details

#### At a glance

- **Title:** data-insights__core_concepts__the-profile
- **Duration:** 1m 25s
- **Media link:** https://cdn.jwplayer.com/previews/mMtDUT4b
- **Publish date (unix):** 1752797003

#### Streaming renditions

- application/vnd.apple.mpegurl
- audio/mp4 · AAC Audio · 114457 kbps
- video/mp4 · 180p · 180p · 178062 kbps
- video/mp4 · 270p · 270p · 228817 kbps
- video/mp4 · 360p · 360p · 244198 kbps
- video/mp4 · 406p · 406p · 271551 kbps
- video/mp4 · 540p · 540p · 369053 kbps
- video/mp4 · 720p · 720p · 508859 kbps
- video/mp4 · 1080p · 1080p · 821662 kbps

#### Timed text tracks (delivery)

- **thumbnails:** `https://cdn.jwplayer.com/strips/mMtDUT4b-120.vtt`

#### Transcript

At the heart of Lytx is the customer profile. We help brands like yours build the most comprehensive custom data asset possible right out of the box. Because this occurs in real time, you never run the risk of missing the key engagement opportunity, even when the window for that engagement is small. This of course is often the case with anonymous site traffic. The real magic rests with our proprietary identity graph, allowing individual interactions across any number of channels to be associated with a single consumer and how we can effectively associate an individual's interactions from different channels such as clicking an email and making a purchase. This, along with our common schema, integrations, proprietary enrichments and profile management toolkit called Schema Studio result in tremendous opportunity with unbelievably low lift right out of the box. Over the next several videos, we'll examine every aspect of the Lytx profile, ensuring you have the knowledge and expertise necessary to maximize the impact.

#### Subtitles (WebVTT)

```webvtt
WEBVTT

1
00:00:00.000 --> 00:00:18.800
At the heart of Lytx is the customer profile.

2
00:00:18.800 --> 00:00:23.640
We help brands like yours build the most comprehensive custom data asset possible right out of the

3
00:00:23.640 --> 00:00:24.960
box.

4
00:00:24.960 --> 00:00:28.900
Because this occurs in real time, you never run the risk of missing the key engagement

5
00:00:28.900 --> 00:00:32.940
opportunity, even when the window for that engagement is small.

6
00:00:32.940 --> 00:00:37.060
This of course is often the case with anonymous site traffic.

7
00:00:37.060 --> 00:00:42.100
The real magic rests with our proprietary identity graph, allowing individual interactions

8
00:00:42.100 --> 00:00:47.140
across any number of channels to be associated with a single consumer and how we can effectively

9
00:00:47.140 --> 00:00:51.620
associate an individual's interactions from different channels such as clicking an email

10
00:00:51.620 --> 00:00:53.540
and making a purchase.

11
00:00:53.780 --> 00:00:59.860
This, along with our common schema, integrations, proprietary enrichments and profile management

12
00:00:59.860 --> 00:01:05.820
toolkit called Schema Studio result in tremendous opportunity with unbelievably low lift right

13
00:01:05.820 --> 00:01:08.340
out of the box.

14
00:01:08.340 --> 00:01:13.060
Over the next several videos, we'll examine every aspect of the Lytx profile, ensuring

15
00:01:13.060 --> 00:01:16.420
you have the knowledge and expertise necessary to maximize the impact.

```

```transcript
<!-- PLACEHOLDER: replace with real transcript before publish if cues were auto-derived from WebVTT -->
[00:00] At the heart of Lytx is the customer profile.
[00:18] We help brands like yours build the most comprehensive custom data asset possible right out of the
[00:23] box.
[00:24] Because this occurs in real time, you never run the risk of missing the key engagement
[00:28] opportunity, even when the window for that engagement is small.
[00:32] This of course is often the case with anonymous site traffic.
[00:37] The real magic rests with our proprietary identity graph, allowing individual interactions
[00:42] across any number of channels to be associated with a single consumer and how we can effectively
[00:47] associate an individual's interactions from different channels such as clicking an email
[00:51] and making a purchase.
[00:53] This, along with our common schema, integrations, proprietary enrichments and profile management
[00:59] toolkit called Schema Studio result in tremendous opportunity with unbelievably low lift right
[01:05] out of the box.
[01:08] Over the next several videos, we'll examine every aspect of the Lytx profile, ensuring
[01:13] you have the knowledge and expertise necessary to maximize the impact.
```

#### Key takeaways

- Connect **What is a profile?** back to your stack configuration before moving to the next module.
- Capture one concrete artifact (screenshot, Postman call, or code snippet) that proves the step works in your environment.
- Re-read the delivery versus management boundary for anything you changed in the entry model.

### Lesson 02 — What is a common schema?

<!-- ai_metadata: {"lesson_id":"02","type":"video","duration_seconds":137,"video_url":"https://cdn.jwplayer.com/previews/PLvM0JAb","thumbnail_url":"https://cdn.jwplayer.com/v2/media/PLvM0JAb/poster.jpg?width=720","topics":["What","common","schema"]} -->

#### Video details

#### At a glance

- **Title:** data-insights__core_concepts__common-schema
- **Duration:** 2m 17s
- **Media link:** https://cdn.jwplayer.com/previews/PLvM0JAb
- **Publish date (unix):** 1752796674

#### Streaming renditions

- application/vnd.apple.mpegurl
- audio/mp4 · AAC Audio · 114288 kbps
- video/mp4 · 180p · 180p · 197915 kbps
- video/mp4 · 270p · 270p · 259644 kbps
- video/mp4 · 360p · 360p · 244034 kbps
- video/mp4 · 406p · 406p · 269699 kbps
- video/mp4 · 540p · 540p · 351866 kbps
- video/mp4 · 720p · 720p · 488582 kbps
- video/mp4 · 1080p · 1080p · 919649 kbps

#### Timed text tracks (delivery)

- **thumbnails:** `https://cdn.jwplayer.com/strips/PLvM0JAb-120.vtt`

#### Transcript

The Lytx Schema Studio represents a set of tools and automated intelligence to aid the curation and enrichment of your customer profiles effortlessly. It starts with our robust common schema, allowing you to quickly implement high-value use cases in just minutes. The predefined customer attributes streamline data mapping, letting you focus on results while fully supporting custom solutions as your needs evolve. Our common schema focuses on the following key categories. Identity. Predefined identifiers have been hand-curated to seamlessly aggregate data across all key engagement channels, ensuring native support and minimal maintenance. Associating a customer's email and web activity into a unified profile has never been easier. Consent and governance. Understanding and enforcing customer consent continues to be a critical investment. Lytx provides a means to gather consent preferences with little lift, also enabling adherence to those preferences through our automated segmentation and downstream syncs capabilities. Demographic and geographic. Of course, there is a dedicated home for general customer information such as name, address and location, along with customizable attributes to maintain first-party data such as account type or status. Activity. Build and maintain a comprehensive catalogue of user activity across channels, devices and campaigns. In addition, we'll automatically generate summary attributes, allowing you to easily access insights such as the first UTN collected or the last page visited. Intelligence. Lytx provides valuable out-of-the-box signals and insights related to customer interests and behaviours. These intelligence-based attributes are among the most powerful and actionable features of the platform. In the next video, we'll explore each of these attributes in more detail. Thank you for watching. Visit us at www.lytx.com

#### Subtitles (WebVTT)

```webvtt
WEBVTT

1
00:00:00.000 --> 00:00:20.420
The Lytx Schema Studio represents a set of tools and automated intelligence to aid the

2
00:00:20.420 --> 00:00:24.820
curation and enrichment of your customer profiles effortlessly.

3
00:00:24.820 --> 00:00:29.860
It starts with our robust common schema, allowing you to quickly implement high-value use cases

4
00:00:29.860 --> 00:00:31.360
in just minutes.

5
00:00:31.360 --> 00:00:36.120
The predefined customer attributes streamline data mapping, letting you focus on results

6
00:00:36.120 --> 00:00:40.720
while fully supporting custom solutions as your needs evolve.

7
00:00:40.720 --> 00:00:44.720
Our common schema focuses on the following key categories.

8
00:00:44.720 --> 00:00:46.400
Identity.

9
00:00:46.400 --> 00:00:50.640
Predefined identifiers have been hand-curated to seamlessly aggregate data across all key

10
00:00:50.640 --> 00:00:54.960
engagement channels, ensuring native support and minimal maintenance.

11
00:00:54.960 --> 00:01:02.320
Associating a customer's email and web activity into a unified profile has never been easier.

12
00:01:02.320 --> 00:01:04.440
Consent and governance.

13
00:01:04.440 --> 00:01:08.560
Understanding and enforcing customer consent continues to be a critical investment.

14
00:01:08.560 --> 00:01:13.360
Lytx provides a means to gather consent preferences with little lift, also enabling adherence

15
00:01:13.360 --> 00:01:20.000
to those preferences through our automated segmentation and downstream syncs capabilities.

16
00:01:20.000 --> 00:01:22.420
Demographic and geographic.

17
00:01:22.420 --> 00:01:26.660
Of course, there is a dedicated home for general customer information such as name,

18
00:01:26.660 --> 00:01:31.820
address and location, along with customizable attributes to maintain first-party data such

19
00:01:31.820 --> 00:01:35.340
as account type or status.

20
00:01:35.340 --> 00:01:36.340
Activity.

21
00:01:36.340 --> 00:01:41.380
Build and maintain a comprehensive catalogue of user activity across channels, devices

22
00:01:41.380 --> 00:01:42.820
and campaigns.

23
00:01:42.820 --> 00:01:46.940
In addition, we'll automatically generate summary attributes, allowing you to easily

24
00:01:46.940 --> 00:01:53.540
access insights such as the first UTN collected or the last page visited.

25
00:01:53.540 --> 00:01:54.540
Intelligence.

26
00:01:54.540 --> 00:01:59.180
Lytx provides valuable out-of-the-box signals and insights related to customer interests

27
00:01:59.180 --> 00:02:00.800
and behaviours.

28
00:02:00.800 --> 00:02:04.740
These intelligence-based attributes are among the most powerful and actionable features

29
00:02:04.740 --> 00:02:06.220
of the platform.

30
00:02:06.220 --> 00:02:09.460
In the next video, we'll explore each of these attributes in more detail.

31
00:02:16.940 --> 00:02:17.940
Thank you for watching.

32
00:02:17.940 --> 00:02:18.940
Visit us at www.lytx.com

```

```transcript
<!-- PLACEHOLDER: replace with real transcript before publish if cues were auto-derived from WebVTT -->
[00:00] The Lytx Schema Studio represents a set of tools and automated intelligence to aid the
[00:20] curation and enrichment of your customer profiles effortlessly.
[00:24] It starts with our robust common schema, allowing you to quickly implement high-value use cases
[00:29] in just minutes.
[00:31] The predefined customer attributes streamline data mapping, letting you focus on results
[00:36] while fully supporting custom solutions as your needs evolve.
[00:40] Our common schema focuses on the following key categories.
[00:44] Identity.
[00:46] Predefined identifiers have been hand-curated to seamlessly aggregate data across all key
[00:50] engagement channels, ensuring native support and minimal maintenance.
[00:54] Associating a customer's email and web activity into a unified profile has never been easier.
[01:02] Consent and governance.
[01:04] Understanding and enforcing customer consent continues to be a critical investment.
[01:08] Lytx provides a means to gather consent preferences with little lift, also enabling adherence
[01:13] to those preferences through our automated segmentation and downstream syncs capabilities.
[01:20] Demographic and geographic.
[01:22] Of course, there is a dedicated home for general customer information such as name,
[01:26] address and location, along with customizable attributes to maintain first-party data such
[01:31] as account type or status.
[01:35] Activity.
[01:36] Build and maintain a comprehensive catalogue of user activity across channels, devices
[01:41] and campaigns.
[01:42] In addition, we'll automatically generate summary attributes, allowing you to easily
[01:46] access insights such as the first UTN collected or the last page visited.
[01:53] Intelligence.
[01:54] Lytx provides valuable out-of-the-box signals and insights related to customer interests
[01:59] and behaviours.
[02:00] These intelligence-based attributes are among the most powerful and actionable features
[02:04] of the platform.
[02:06] In the next video, we'll explore each of these attributes in more detail.
[02:16] Thank you for watching.
[02:17] Visit us at www.lytx.com
```

#### Key takeaways

- Connect **What is a common schema?** back to your stack configuration before moving to the next module.
- Capture one concrete artifact (screenshot, Postman call, or code snippet) that proves the step works in your environment.
- Re-read the delivery versus management boundary for anything you changed in the entry model.

### Lesson 03 — How does scoring work?

<!-- ai_metadata: {"lesson_id":"03","type":"video","duration_seconds":117,"video_url":"https://cdn.jwplayer.com/previews/BwZ9Bhrt","thumbnail_url":"https://cdn.jwplayer.com/v2/media/BwZ9Bhrt/poster.jpg?width=720","topics":["How","does","scoring","work"]} -->

#### Video details

#### At a glance

- **Title:** data-insights__core_concepts__scoring-intro
- **Duration:** 1m 57s
- **Media link:** https://cdn.jwplayer.com/previews/BwZ9Bhrt
- **Publish date (unix):** 1752796899

#### Streaming renditions

- application/vnd.apple.mpegurl
- audio/mp4 · AAC Audio · 114294 kbps
- video/mp4 · 180p · 180p · 239876 kbps
- video/mp4 · 270p · 270p · 339652 kbps
- video/mp4 · 360p · 360p · 347789 kbps
- video/mp4 · 406p · 406p · 390500 kbps
- video/mp4 · 540p · 540p · 522535 kbps
- video/mp4 · 720p · 720p · 730717 kbps
- video/mp4 · 1080p · 1080p · 1322534 kbps

#### Timed text tracks (delivery)

- **thumbnails:** `https://cdn.jwplayer.com/strips/BwZ9Bhrt-120.vtt`

#### Transcript

Understanding behavioral and interest patterns has always been challenging, especially when faced with the complexity of raw data. For marketers, applying one-size-fits-all rules across channels simply doesn't cut it. The key is recognizing individual patterns. How do you know if someone consumes more or less content than usual? Consider return visitors. Instead of arbitrarily assigning significance to a specific number of page views, like five, how can you determine if they're engaging more or less than expected? Will they return, and when? These are the essential signals marketers need to engage effectively and maximize their investments. This is where Lytx proprietary profile intelligence comes into play. Each time an event, such as a page view or button click, is collected, a series of calculations occur. In this processing pipeline, we determine what profile to associate the event with, how it impacts the profile definition itself, and what actions should be triggered, such as a sync to your ad campaign audience. Most importantly, Lytx enriches each profile during that process with tangible signals that make activation a breeze. We call these our intelligence-based attributes. Within this category, you'll find our proprietary behavioral scores, interest scores, audience membership, predictive attributes, and custom model-based attributes. In the following modules, we'll cover the basics of each of our intelligence-based attributes and introduce some examples of how brands like yours are completely revolutionizing their marketing approach.

#### Subtitles (WebVTT)

```webvtt
WEBVTT

1
00:00:00.000 --> 00:00:19.840
Understanding behavioral and interest patterns has always been challenging, especially when

2
00:00:19.840 --> 00:00:24.840
faced with the complexity of raw data. For marketers, applying one-size-fits-all rules

3
00:00:24.840 --> 00:00:31.120
across channels simply doesn't cut it. The key is recognizing individual patterns.

4
00:00:31.120 --> 00:00:35.440
How do you know if someone consumes more or less content than usual?

5
00:00:35.440 --> 00:00:40.200
Consider return visitors. Instead of arbitrarily assigning significance to a specific number

6
00:00:40.200 --> 00:00:46.360
of page views, like five, how can you determine if they're engaging more or less than expected?

7
00:00:46.360 --> 00:00:50.480
Will they return, and when? These are the essential signals marketers

8
00:00:50.480 --> 00:00:55.520
need to engage effectively and maximize their investments.

9
00:00:55.520 --> 00:01:00.560
This is where Lytx proprietary profile intelligence comes into play. Each time an event, such

10
00:01:00.560 --> 00:01:06.160
as a page view or button click, is collected, a series of calculations occur.

11
00:01:06.160 --> 00:01:11.200
In this processing pipeline, we determine what profile to associate the event with,

12
00:01:11.200 --> 00:01:15.560
how it impacts the profile definition itself, and what actions should be triggered, such

13
00:01:15.560 --> 00:01:20.600
as a sync to your ad campaign audience. Most importantly, Lytx enriches each profile

14
00:01:20.600 --> 00:01:25.320
during that process with tangible signals that make activation a breeze. We call these

15
00:01:25.320 --> 00:01:30.000
our intelligence-based attributes. Within this category, you'll find our proprietary

16
00:01:30.000 --> 00:01:36.700
behavioral scores, interest scores, audience membership, predictive attributes, and custom

17
00:01:36.700 --> 00:01:41.080
model-based attributes. In the following modules, we'll cover the

18
00:01:41.080 --> 00:01:45.440
basics of each of our intelligence-based attributes and introduce some examples of

19
00:01:45.440 --> 00:01:49.160
how brands like yours are completely revolutionizing their marketing approach.

```

```transcript
<!-- PLACEHOLDER: replace with real transcript before publish if cues were auto-derived from WebVTT -->
[00:00] Understanding behavioral and interest patterns has always been challenging, especially when
[00:19] faced with the complexity of raw data. For marketers, applying one-size-fits-all rules
[00:24] across channels simply doesn't cut it. The key is recognizing individual patterns.
[00:31] How do you know if someone consumes more or less content than usual?
[00:35] Consider return visitors. Instead of arbitrarily assigning significance to a specific number
[00:40] of page views, like five, how can you determine if they're engaging more or less than expected?
[00:46] Will they return, and when? These are the essential signals marketers
[00:50] need to engage effectively and maximize their investments.
[00:55] This is where Lytx proprietary profile intelligence comes into play. Each time an event, such
[01:00] as a page view or button click, is collected, a series of calculations occur.
[01:06] In this processing pipeline, we determine what profile to associate the event with,
[01:11] how it impacts the profile definition itself, and what actions should be triggered, such
[01:15] as a sync to your ad campaign audience. Most importantly, Lytx enriches each profile
[01:20] during that process with tangible signals that make activation a breeze. We call these
[01:25] our intelligence-based attributes. Within this category, you'll find our proprietary
[01:30] behavioral scores, interest scores, audience membership, predictive attributes, and custom
[01:36] model-based attributes. In the following modules, we'll cover the
[01:41] basics of each of our intelligence-based attributes and introduce some examples of
[01:45] how brands like yours are completely revolutionizing their marketing approach.
```

#### Key takeaways

- Connect **How does scoring work?** back to your stack configuration before moving to the next module.
- Capture one concrete artifact (screenshot, Postman call, or code snippet) that proves the step works in your environment.
- Re-read the delivery versus management boundary for anything you changed in the entry model.

### Lesson 04 — What are behavioral scores?

<!-- ai_metadata: {"lesson_id":"04","type":"video","duration_seconds":160,"video_url":"https://cdn.jwplayer.com/previews/8I7tQlvF","thumbnail_url":"https://cdn.jwplayer.com/v2/media/8I7tQlvF/poster.jpg?width=720","topics":["What","are","behavioral","scores"]} -->

#### Video details

#### At a glance

- **Title:** data-insights__core_concepts__behavioral-scores
- **Duration:** 2m 40s
- **Media link:** https://cdn.jwplayer.com/previews/8I7tQlvF
- **Publish date (unix):** 1752797058

#### Streaming renditions

- application/vnd.apple.mpegurl
- audio/mp4 · AAC Audio · 113622 kbps
- video/mp4 · 180p · 180p · 161033 kbps
- video/mp4 · 270p · 270p · 192964 kbps
- video/mp4 · 360p · 360p · 192398 kbps
- video/mp4 · 406p · 406p · 206608 kbps
- video/mp4 · 540p · 540p · 253002 kbps
- video/mp4 · 720p · 720p · 331136 kbps
- video/mp4 · 1080p · 1080p · 551882 kbps

#### Timed text tracks (delivery)

- **thumbnails:** `https://cdn.jwplayer.com/strips/8I7tQlvF-120.vtt`

#### Transcript

Each time an event, such as a page view or button click, gets collected, a series of calculations take place. This processing pipeline is where we determine what user to associate an event with, how it impacts a common schema or custom schema, and most importantly, all of that user's individual intelligence-based attributes. Lytx automatically surfaces nine dynamic scores on every profile, unique to each individual and reflective of their cross-channel engagement. These scores are updated in real-time for each individual user. Here's how these scores work. Frequency measures a visitor's cumulative activity with your brand. The more active the user is, the higher the score is comparing each user to the rest. Frequency tracks how consistently a visitor interacts with your brand. More frequent engagement results in a higher score, benchmarking users against all others. Recency – this measure focuses on how recently the user has engaged. More recent activity leads to a higher score, comparing the user's present engagement to past engagement. Intensity assesses the depth of interaction. The more intense or sustained the engagement, the higher the score measuring depth relative to other users. Momentum tracks the rate of engagement. Users increasing their activity with your brand will have a higher score comparing their recent and past behaviors. Propensity predicts the likelihood of a user returning. Positive patterns of interaction lead to higher scores, measured relative to all users. Consistency measures the regularity of user engagement. Consistent behaviors, such as interacting every 7 or 30 days, lead to higher scores while inconsistent behavior reduces the score. Maturity – this measure reflects how long a user has been engaged with your brand. Long-term users have higher scores while users with significant engagement gaps will have lower scores. Volatility measures how stable or sporadic the user's engagement is. This score reflects the stability of interaction patterns, offering a more nuanced version of intensity.

#### Subtitles (WebVTT)

```webvtt
WEBVTT

1
00:00:00.000 --> 00:00:21.040
Each time an event, such as a page view or button click, gets collected, a series of

2
00:00:21.040 --> 00:00:26.560
calculations take place. This processing pipeline is where we determine what user to associate

3
00:00:26.560 --> 00:00:32.440
an event with, how it impacts a common schema or custom schema, and most importantly, all

4
00:00:32.440 --> 00:00:36.440
of that user's individual intelligence-based attributes.

5
00:00:36.440 --> 00:00:41.620
Lytx automatically surfaces nine dynamic scores on every profile, unique to each individual

6
00:00:41.620 --> 00:00:47.040
and reflective of their cross-channel engagement. These scores are updated in real-time for

7
00:00:47.040 --> 00:00:53.920
each individual user. Here's how these scores work.

8
00:00:53.920 --> 00:00:58.480
Frequency measures a visitor's cumulative activity with your brand. The more active

9
00:00:58.480 --> 00:01:04.560
the user is, the higher the score is comparing each user to the rest.

10
00:01:04.560 --> 00:01:09.760
Frequency tracks how consistently a visitor interacts with your brand. More frequent engagement

11
00:01:09.760 --> 00:01:15.440
results in a higher score, benchmarking users against all others.

12
00:01:15.440 --> 00:01:20.800
Recency – this measure focuses on how recently the user has engaged. More recent activity

13
00:01:20.800 --> 00:01:27.320
leads to a higher score, comparing the user's present engagement to past engagement.

14
00:01:27.320 --> 00:01:32.800
Intensity assesses the depth of interaction. The more intense or sustained the engagement,

15
00:01:32.800 --> 00:01:37.200
the higher the score measuring depth relative to other users.

16
00:01:37.200 --> 00:01:41.960
Momentum tracks the rate of engagement. Users increasing their activity with your brand

17
00:01:41.960 --> 00:01:46.800
will have a higher score comparing their recent and past behaviors.

18
00:01:46.800 --> 00:01:51.800
Propensity predicts the likelihood of a user returning. Positive patterns of interaction

19
00:01:51.800 --> 00:01:56.760
lead to higher scores, measured relative to all users.

20
00:01:56.760 --> 00:02:01.400
Consistency measures the regularity of user engagement. Consistent behaviors, such as

21
00:02:01.400 --> 00:02:07.160
interacting every 7 or 30 days, lead to higher scores while inconsistent behavior reduces

22
00:02:07.160 --> 00:02:11.480
the score. Maturity – this measure reflects how long

23
00:02:11.480 --> 00:02:16.680
a user has been engaged with your brand. Long-term users have higher scores while users

24
00:02:16.680 --> 00:02:20.440
with significant engagement gaps will have lower scores.

25
00:02:20.440 --> 00:02:26.200
Volatility measures how stable or sporadic the user's engagement is. This score reflects

26
00:02:26.200 --> 00:02:30.600
the stability of interaction patterns, offering a more nuanced version of intensity.

```

```transcript
<!-- PLACEHOLDER: replace with real transcript before publish if cues were auto-derived from WebVTT -->
[00:00] Each time an event, such as a page view or button click, gets collected, a series of
[00:21] calculations take place. This processing pipeline is where we determine what user to associate
[00:26] an event with, how it impacts a common schema or custom schema, and most importantly, all
[00:32] of that user's individual intelligence-based attributes.
[00:36] Lytx automatically surfaces nine dynamic scores on every profile, unique to each individual
[00:41] and reflective of their cross-channel engagement. These scores are updated in real-time for
[00:47] each individual user. Here's how these scores work.
[00:53] Frequency measures a visitor's cumulative activity with your brand. The more active
[00:58] the user is, the higher the score is comparing each user to the rest.
[01:04] Frequency tracks how consistently a visitor interacts with your brand. More frequent engagement
[01:09] results in a higher score, benchmarking users against all others.
[01:15] Recency – this measure focuses on how recently the user has engaged. More recent activity
[01:20] leads to a higher score, comparing the user's present engagement to past engagement.
[01:27] Intensity assesses the depth of interaction. The more intense or sustained the engagement,
[01:32] the higher the score measuring depth relative to other users.
[01:37] Momentum tracks the rate of engagement. Users increasing their activity with your brand
[01:41] will have a higher score comparing their recent and past behaviors.
[01:46] Propensity predicts the likelihood of a user returning. Positive patterns of interaction
[01:51] lead to higher scores, measured relative to all users.
[01:56] Consistency measures the regularity of user engagement. Consistent behaviors, such as
[02:01] interacting every 7 or 30 days, lead to higher scores while inconsistent behavior reduces
[02:07] the score. Maturity – this measure reflects how long
[02:11] a user has been engaged with your brand. Long-term users have higher scores while users
[02:16] with significant engagement gaps will have lower scores.
[02:20] Volatility measures how stable or sporadic the user's engagement is. This score reflects
[02:26] the stability of interaction patterns, offering a more nuanced version of intensity.
```

#### Key takeaways

- Connect **What are behavioral scores?** back to your stack configuration before moving to the next module.
- Capture one concrete artifact (screenshot, Postman call, or code snippet) that proves the step works in your environment.
- Re-read the delivery versus management boundary for anything you changed in the entry model.

### Lesson 05 — What are interest scores?

<!-- ai_metadata: {"lesson_id":"05","type":"video","duration_seconds":113,"video_url":"https://cdn.jwplayer.com/previews/m12ekXvQ","thumbnail_url":"https://cdn.jwplayer.com/v2/media/m12ekXvQ/poster.jpg?width=720","topics":["What","are","interest","scores"]} -->

#### Video details

#### At a glance

- **Title:** data-insights__core_concepts__interest-scores
- **Duration:** 1m 53s
- **Media link:** https://cdn.jwplayer.com/previews/m12ekXvQ
- **Publish date (unix):** 1752796812

#### Streaming renditions

- application/vnd.apple.mpegurl
- audio/mp4 · AAC Audio · 113983 kbps
- video/mp4 · 180p · 180p · 177270 kbps
- video/mp4 · 270p · 270p · 225027 kbps
- video/mp4 · 360p · 360p · 225916 kbps
- video/mp4 · 406p · 406p · 248946 kbps
- video/mp4 · 540p · 540p · 325756 kbps
- video/mp4 · 720p · 720p · 441998 kbps
- video/mp4 · 1080p · 1080p · 764356 kbps

#### Timed text tracks (delivery)

- **thumbnails:** `https://cdn.jwplayer.com/strips/m12ekXvQ-120.vtt`

#### Transcript

If behavioral signals, as covered in the previous module, represent one side of the coin, understanding interest levels in content and products is the other. This is where Lytics interest scores come into play. The process begins automatically. Based on your account's configuration, Lytics' classification service proactively analyzes content and products across your site, using natural language processing and image analysis. As a result, we'll build a rich taxonomy for each piece of content, a set of topics that describe the content. Each topic within the taxonomy helps identify precisely what exactly is driving that customer's interest. As customers engage with your content, such as reading a product description, Lytics tracks their interactions and builds a set of scores representing their relative interest in the topics associated with that content. This means you'll gain immediate insights into what each customer is interested in and the extent of that interest, and those insights are represented by topic-level scores available on each customer profile. The best part – this process is fully automated. As customers interact with your site, their interest scores are continually updated to reflect their most recent behaviors, without any additional effort from you. These insights help drive content strategies, personalize ad creative for specific interest cohorts, and enhance engagement with intelligent content recommendations, delivering exactly what each user wants when they want it.

#### Subtitles (WebVTT)

```webvtt
WEBVTT

1
00:00:00.000 --> 00:00:22.540
If behavioral signals, as covered in the previous module, represent one side of the coin, understanding

2
00:00:22.540 --> 00:00:26.160
interest levels in content and products is the other.

3
00:00:26.160 --> 00:00:29.280
This is where Lytics interest scores come into play.

4
00:00:29.280 --> 00:00:31.960
The process begins automatically.

5
00:00:31.960 --> 00:00:36.520
Based on your account's configuration, Lytics' classification service proactively analyzes

6
00:00:36.520 --> 00:00:42.480
content and products across your site, using natural language processing and image analysis.

7
00:00:42.480 --> 00:00:47.080
As a result, we'll build a rich taxonomy for each piece of content, a set of topics

8
00:00:47.080 --> 00:00:49.200
that describe the content.

9
00:00:49.200 --> 00:00:54.320
Each topic within the taxonomy helps identify precisely what exactly is driving that customer's

10
00:00:54.320 --> 00:00:55.480
interest.

11
00:00:55.480 --> 00:01:00.220
As customers engage with your content, such as reading a product description, Lytics tracks

12
00:01:00.220 --> 00:01:04.440
their interactions and builds a set of scores representing their relative interest in the

13
00:01:04.440 --> 00:01:07.440
topics associated with that content.

14
00:01:07.440 --> 00:01:11.360
This means you'll gain immediate insights into what each customer is interested in and

15
00:01:11.360 --> 00:01:16.780
the extent of that interest, and those insights are represented by topic-level scores available

16
00:01:16.780 --> 00:01:19.200
on each customer profile.

17
00:01:19.200 --> 00:01:22.600
The best part – this process is fully automated.

18
00:01:22.600 --> 00:01:26.960
As customers interact with your site, their interest scores are continually updated to

19
00:01:26.960 --> 00:01:32.200
reflect their most recent behaviors, without any additional effort from you.

20
00:01:32.200 --> 00:01:37.120
These insights help drive content strategies, personalize ad creative for specific interest

21
00:01:37.120 --> 00:01:42.400
cohorts, and enhance engagement with intelligent content recommendations, delivering exactly

22
00:01:42.400 --> 00:01:44.240
what each user wants when they want it.

```

```transcript
<!-- PLACEHOLDER: replace with real transcript before publish if cues were auto-derived from WebVTT -->
[00:00] If behavioral signals, as covered in the previous module, represent one side of the coin, understanding
[00:22] interest levels in content and products is the other.
[00:26] This is where Lytics interest scores come into play.
[00:29] The process begins automatically.
[00:31] Based on your account's configuration, Lytics' classification service proactively analyzes
[00:36] content and products across your site, using natural language processing and image analysis.
[00:42] As a result, we'll build a rich taxonomy for each piece of content, a set of topics
[00:47] that describe the content.
[00:49] Each topic within the taxonomy helps identify precisely what exactly is driving that customer's
[00:54] interest.
[00:55] As customers engage with your content, such as reading a product description, Lytics tracks
[01:00] their interactions and builds a set of scores representing their relative interest in the
[01:04] topics associated with that content.
[01:07] This means you'll gain immediate insights into what each customer is interested in and
[01:11] the extent of that interest, and those insights are represented by topic-level scores available
[01:16] on each customer profile.
[01:19] The best part – this process is fully automated.
[01:22] As customers interact with your site, their interest scores are continually updated to
[01:26] reflect their most recent behaviors, without any additional effort from you.
[01:32] These insights help drive content strategies, personalize ad creative for specific interest
[01:37] cohorts, and enhance engagement with intelligent content recommendations, delivering exactly
[01:42] what each user wants when they want it.
```

#### Key takeaways

- Connect **What are interest scores?** back to your stack configuration before moving to the next module.
- Capture one concrete artifact (screenshot, Postman call, or code snippet) that proves the step works in your environment.
- Re-read the delivery versus management boundary for anything you changed in the entry model.

### Lesson 06 — How do audiences work?

<!-- ai_metadata: {"lesson_id":"06","type":"video","duration_seconds":190,"video_url":"https://cdn.jwplayer.com/previews/ExHf6d4z","thumbnail_url":"https://cdn.jwplayer.com/v2/media/ExHf6d4z/poster.jpg?width=720","topics":["How","audiences","work"]} -->

#### Video details

#### At a glance

- **Title:** data-insights__core_concepts__audience-membership
- **Duration:** 3m 10s
- **Media link:** https://cdn.jwplayer.com/previews/ExHf6d4z
- **Publish date (unix):** 1752796602

#### Streaming renditions

- application/vnd.apple.mpegurl
- audio/mp4 · AAC Audio · 113681 kbps
- video/mp4 · 180p · 180p · 165673 kbps
- video/mp4 · 270p · 270p · 203155 kbps
- video/mp4 · 360p · 360p · 206407 kbps
- video/mp4 · 406p · 406p · 224963 kbps
- video/mp4 · 540p · 540p · 285763 kbps
- video/mp4 · 720p · 720p · 379899 kbps
- video/mp4 · 1080p · 1080p · 672480 kbps

#### Timed text tracks (delivery)

- **thumbnails:** `https://cdn.jwplayer.com/strips/ExHf6d4z-120.vtt`

#### Transcript

Audiences within Lytx are unique. In many regards, you can think of a Lytx audience as more of a computed attribute, one that has customers entering and exiting in real time based on the defined set of rules. Much different than a traditional static marketing audience where the members do not change after the initial creation. This means that just like a behavioral score, audience membership becomes a key part of every single profile. The membership represents the audiences that that customer meets the criteria of at that very moment. For example, if a collected event contains a valid email address, that user will automatically exit the anonymous user's audience and enter the known user's audience. Later on, as we explore all of the aspects of building and using profiles in Lytx, we will dive much deeper into our powerful segmentation engine, learning how you can leverage membership triggers to sync data when a customer enters or exits a segment. For now, however, we want to cover the basics. How an audience can be built and ultimately how that will be surfaced on the profile to power personalization and decision making. It starts with our powerful segmentation engine. This rules builder allows you to create virtually any combination of rules, from specific attribute values to the level of interest in a specific topic, if they are currently a member of another audience, and more. As an example, maybe we want to easily know when a customer has a high momentum but a low frequency. This might signal that you have a short window of opportunity with a customer who is interested but is not likely to visit again. To build an audience we'll first access audiences from using profile section of the main navigation. Choose custom rule to leverage any of the available attributes. We'll search for score momentum and say the value should be above 50. Now, let's add another rule including anyone with a frequency score below 25. Last, we'll label and save our audience. Membership is calculated and updated in real time. As you can see, if we view a customer's profile that falls into this audience we'll see that membership directly as a native part of the profile, the same profile that can be synced and leveraged across your engagement tools and channels.

#### Subtitles (WebVTT)

```webvtt
WEBVTT

1
00:00:00.000 --> 00:00:20.580
Audiences within Lytx are unique. In many regards, you can think of a Lytx audience

2
00:00:20.580 --> 00:00:25.080
as more of a computed attribute, one that has customers entering and exiting in real

3
00:00:25.080 --> 00:00:30.180
time based on the defined set of rules. Much different than a traditional static marketing

4
00:00:30.180 --> 00:00:34.280
audience where the members do not change after the initial creation.

5
00:00:34.280 --> 00:00:38.560
This means that just like a behavioral score, audience membership becomes a key part of

6
00:00:38.560 --> 00:00:43.080
every single profile. The membership represents the audiences that that customer meets the

7
00:00:43.080 --> 00:00:48.400
criteria of at that very moment. For example, if a collected event contains a valid email

8
00:00:48.400 --> 00:00:53.040
address, that user will automatically exit the anonymous user's audience and enter

9
00:00:53.040 --> 00:00:57.180
the known user's audience. Later on, as we explore all of the aspects

10
00:00:57.180 --> 00:01:02.920
of building and using profiles in Lytx, we will dive much deeper into our powerful segmentation

11
00:01:02.920 --> 00:01:07.280
engine, learning how you can leverage membership triggers to sync data when a customer enters

12
00:01:07.280 --> 00:01:13.700
or exits a segment. For now, however, we want to cover the basics.

13
00:01:13.700 --> 00:01:17.880
How an audience can be built and ultimately how that will be surfaced on the profile to

14
00:01:17.880 --> 00:01:24.640
power personalization and decision making. It starts with our powerful segmentation engine.

15
00:01:24.640 --> 00:01:30.040
This rules builder allows you to create virtually any combination of rules, from specific attribute

16
00:01:30.040 --> 00:01:35.680
values to the level of interest in a specific topic, if they are currently a member of another

17
00:01:35.680 --> 00:01:39.800
audience, and more. As an example, maybe we want to easily know

18
00:01:39.800 --> 00:01:44.520
when a customer has a high momentum but a low frequency. This might signal that you

19
00:01:44.520 --> 00:01:48.520
have a short window of opportunity with a customer who is interested but is not likely

20
00:01:48.520 --> 00:01:53.120
to visit again. To build an audience we'll first access audiences

21
00:01:53.120 --> 00:02:05.800
from using profile section of the main navigation. Choose custom rule to leverage any of the

22
00:02:05.800 --> 00:02:11.240
available attributes. We'll search for score momentum and say the

23
00:02:11.240 --> 00:02:19.400
value should be above 50. Now, let's add another rule including anyone

24
00:02:19.400 --> 00:02:34.360
with a frequency score below 25. Last, we'll label and save our audience.

25
00:02:34.360 --> 00:02:40.280
Membership is calculated and updated in real time.

26
00:02:40.280 --> 00:02:44.400
As you can see, if we view a customer's profile that falls into this audience we'll see that

27
00:02:44.400 --> 00:02:49.040
membership directly as a native part of the profile, the same profile that can be synced

28
00:02:49.040 --> 00:03:04.480
and leveraged across your engagement tools and channels.

```

```transcript
<!-- PLACEHOLDER: replace with real transcript before publish if cues were auto-derived from WebVTT -->
[00:00] Audiences within Lytx are unique. In many regards, you can think of a Lytx audience
[00:20] as more of a computed attribute, one that has customers entering and exiting in real
[00:25] time based on the defined set of rules. Much different than a traditional static marketing
[00:30] audience where the members do not change after the initial creation.
[00:34] This means that just like a behavioral score, audience membership becomes a key part of
[00:38] every single profile. The membership represents the audiences that that customer meets the
[00:43] criteria of at that very moment. For example, if a collected event contains a valid email
[00:48] address, that user will automatically exit the anonymous user's audience and enter
[00:53] the known user's audience. Later on, as we explore all of the aspects
[00:57] of building and using profiles in Lytx, we will dive much deeper into our powerful segmentation
[01:02] engine, learning how you can leverage membership triggers to sync data when a customer enters
[01:07] or exits a segment. For now, however, we want to cover the basics.
[01:13] How an audience can be built and ultimately how that will be surfaced on the profile to
[01:17] power personalization and decision making. It starts with our powerful segmentation engine.
[01:24] This rules builder allows you to create virtually any combination of rules, from specific attribute
[01:30] values to the level of interest in a specific topic, if they are currently a member of another
[01:35] audience, and more. As an example, maybe we want to easily know
[01:39] when a customer has a high momentum but a low frequency. This might signal that you
[01:44] have a short window of opportunity with a customer who is interested but is not likely
[01:48] to visit again. To build an audience we'll first access audiences
[01:53] from using profile section of the main navigation. Choose custom rule to leverage any of the
[02:05] available attributes. We'll search for score momentum and say the
[02:11] value should be above 50. Now, let's add another rule including anyone
[02:19] with a frequency score below 25. Last, we'll label and save our audience.
[02:34] Membership is calculated and updated in real time.
[02:40] As you can see, if we view a customer's profile that falls into this audience we'll see that
[02:44] membership directly as a native part of the profile, the same profile that can be synced
[02:49] and leveraged across your engagement tools and channels.
```

#### Key takeaways

- Connect **How do audiences work?** back to your stack configuration before moving to the next module.
- Capture one concrete artifact (screenshot, Postman call, or code snippet) that proves the step works in your environment.
- Re-read the delivery versus management boundary for anything you changed in the entry model.

### Lesson 07 — Can I create custom models?

<!-- ai_metadata: {"lesson_id":"07","type":"video","duration_seconds":138,"video_url":"https://cdn.jwplayer.com/previews/6y9bQMgx","thumbnail_url":"https://cdn.jwplayer.com/v2/media/6y9bQMgx/poster.jpg?width=720","topics":["Can","create","custom","models"]} -->

#### Video details

#### At a glance

- **Title:** data-insights__core_concepts__modeling
- **Duration:** 2m 18s
- **Media link:** https://cdn.jwplayer.com/previews/6y9bQMgx
- **Publish date (unix):** 1752796731

#### Streaming renditions

- application/vnd.apple.mpegurl
- audio/mp4 · AAC Audio · 113956 kbps
- video/mp4 · 180p · 180p · 181976 kbps
- video/mp4 · 270p · 270p · 227686 kbps
- video/mp4 · 360p · 360p · 225351 kbps
- video/mp4 · 406p · 406p · 245598 kbps
- video/mp4 · 540p · 540p · 311732 kbps
- video/mp4 · 720p · 720p · 421621 kbps
- video/mp4 · 1080p · 1080p · 736855 kbps

#### Timed text tracks (delivery)

- **thumbnails:** `https://cdn.jwplayer.com/strips/6y9bQMgx-120.vtt`

#### Transcript

As marketers, we know that data isn't always readily available. For example, using an account-based marketing tool like Sixth Sense gives us insights into only a small portion of our audience. And while we can be confident that the matched customers fit our ideal customer profile, what about the other 90% of visitors who aren't matched? Lytx makes it easy to leverage the data you do have to uncover customers who behave similarly. Building on our previous example, we can take the 10% of our audience we know and find customers who resemble the ideal profile from that group. We do this using Lytx Lookalike Modeling, a fully automated and highly configurable engine that surfaces the insights you need to engage your audience. To get started, navigate to Lookalike Models under the Using Profiles section in the main menu and choose Create New Model. From there, select the audience you want to analyze, in this case, customers without Sixth Sense data. Next, choose the audience you'd like to compare them to. Finally, Lytx will analyze all available data, including behavioral and interest signals, to determine how closely the customers in your source audience resemble those in your target audience. Next, we'll activate our model at the top of the screen. This will start the analysis process. Finally, we can choose to create a new audience using this model. It will take you directly to the audience builder with an initial definition in place. Customize it to your liking and sync the resulting audience. It's that easy. Under the hood, the result is a score between 0 and 1, 0 being a very low level of similarity, while 1 represents a high level of similarity. These scores exist independently on every user profile.

#### Subtitles (WebVTT)

```webvtt
WEBVTT

1
00:00:00.000 --> 00:00:19.700
As marketers, we know that data isn't always readily available.

2
00:00:19.700 --> 00:00:24.040
For example, using an account-based marketing tool like Sixth Sense gives us insights into

3
00:00:24.040 --> 00:00:26.740
only a small portion of our audience.

4
00:00:26.740 --> 00:00:31.220
And while we can be confident that the matched customers fit our ideal customer profile,

5
00:00:31.220 --> 00:00:35.900
what about the other 90% of visitors who aren't matched?

6
00:00:35.900 --> 00:00:41.500
Lytx makes it easy to leverage the data you do have to uncover customers who behave similarly.

7
00:00:41.500 --> 00:00:46.220
Building on our previous example, we can take the 10% of our audience we know and find customers

8
00:00:46.220 --> 00:00:49.300
who resemble the ideal profile from that group.

9
00:00:49.300 --> 00:00:53.840
We do this using Lytx Lookalike Modeling, a fully automated and highly configurable

10
00:00:53.840 --> 00:00:58.080
engine that surfaces the insights you need to engage your audience.

11
00:00:58.080 --> 00:01:02.520
To get started, navigate to Lookalike Models under the Using Profiles section in the main

12
00:01:02.520 --> 00:01:11.560
menu and choose Create New Model.

13
00:01:11.560 --> 00:01:16.200
From there, select the audience you want to analyze, in this case, customers without Sixth

14
00:01:16.200 --> 00:01:19.200
Sense data.

15
00:01:19.200 --> 00:01:26.240
Next, choose the audience you'd like to compare them to.

16
00:01:26.240 --> 00:01:33.520
Finally, Lytx will analyze all available data, including behavioral and interest signals,

17
00:01:33.520 --> 00:01:37.240
to determine how closely the customers in your source audience resemble those in your

18
00:01:37.240 --> 00:01:38.480
target audience.

19
00:01:38.480 --> 00:01:42.040
Next, we'll activate our model at the top of the screen.

20
00:01:42.040 --> 00:01:44.120
This will start the analysis process.

21
00:01:44.120 --> 00:01:47.800
Finally, we can choose to create a new audience using this model.

22
00:01:47.800 --> 00:01:52.560
It will take you directly to the audience builder with an initial definition in place.

23
00:01:52.560 --> 00:01:55.480
Customize it to your liking and sync the resulting audience.

24
00:01:55.480 --> 00:01:57.520
It's that easy.

25
00:01:57.520 --> 00:02:03.680
Under the hood, the result is a score between 0 and 1, 0 being a very low level of similarity,

26
00:02:03.680 --> 00:02:06.680
while 1 represents a high level of similarity.

27
00:02:06.680 --> 00:02:09.800
These scores exist independently on every user profile.

```

```transcript
<!-- PLACEHOLDER: replace with real transcript before publish if cues were auto-derived from WebVTT -->
[00:00] As marketers, we know that data isn't always readily available.
[00:19] For example, using an account-based marketing tool like Sixth Sense gives us insights into
[00:24] only a small portion of our audience.
[00:26] And while we can be confident that the matched customers fit our ideal customer profile,
[00:31] what about the other 90% of visitors who aren't matched?
[00:35] Lytx makes it easy to leverage the data you do have to uncover customers who behave similarly.
[00:41] Building on our previous example, we can take the 10% of our audience we know and find customers
[00:46] who resemble the ideal profile from that group.
[00:49] We do this using Lytx Lookalike Modeling, a fully automated and highly configurable
[00:53] engine that surfaces the insights you need to engage your audience.
[00:58] To get started, navigate to Lookalike Models under the Using Profiles section in the main
[01:02] menu and choose Create New Model.
[01:11] From there, select the audience you want to analyze, in this case, customers without Sixth
[01:16] Sense data.
[01:19] Next, choose the audience you'd like to compare them to.
[01:26] Finally, Lytx will analyze all available data, including behavioral and interest signals,
[01:33] to determine how closely the customers in your source audience resemble those in your
[01:37] target audience.
[01:38] Next, we'll activate our model at the top of the screen.
[01:42] This will start the analysis process.
[01:44] Finally, we can choose to create a new audience using this model.
[01:47] It will take you directly to the audience builder with an initial definition in place.
[01:52] Customize it to your liking and sync the resulting audience.
[01:55] It's that easy.
[01:57] Under the hood, the result is a score between 0 and 1, 0 being a very low level of similarity,
[02:03] while 1 represents a high level of similarity.
[02:06] These scores exist independently on every user profile.
```

#### Key takeaways

- Connect **Can I create custom models?** back to your stack configuration before moving to the next module.
- Capture one concrete artifact (screenshot, Postman call, or code snippet) that proves the step works in your environment.
- Re-read the delivery versus management boundary for anything you changed in the entry model.

### Lesson 08 — Data Insights: Core Quiz

<!-- ai_metadata: {"lesson_id":"08","type":"text","duration_minutes":1,"topics":["LMS","Knowledge check"]} -->

#### Lesson text

**This lesson is a knowledge check hosted in the Academy LMS.** This companion Markdown contains **no quiz questions, answers, scoring rules, or explanations**.

#### Key takeaways

- Connect **Data Insights: Core Quiz** back to your stack configuration before moving to the next module.
- Capture one concrete artifact (screenshot, Postman call, or code snippet) that proves the step works in your environment.
- Re-read the delivery versus management boundary for anything you changed in the entry model.

## Resources & references

| Page | Companion Markdown |
| --- | --- |
| /courses/data-insights-core-concepts-capabilities/data-insights-course-2--what-is-a-profile | /academy/md/courses/data-insights-core-concepts-capabilities/data-insights-course-2--what-is-a-profile.md |
| /courses/data-insights-core-concepts-capabilities/data-insights-course-2--what-is-a-common-schema | /academy/md/courses/data-insights-core-concepts-capabilities/data-insights-course-2--what-is-a-common-schema.md |
| /courses/data-insights-core-concepts-capabilities/data-insights-course-2--how-does-scoring-work | /academy/md/courses/data-insights-core-concepts-capabilities/data-insights-course-2--how-does-scoring-work.md |
| /courses/data-insights-core-concepts-capabilities/data-insights-course-2--what-are-behavioral-scores | /academy/md/courses/data-insights-core-concepts-capabilities/data-insights-course-2--what-are-behavioral-scores.md |
| /courses/data-insights-core-concepts-capabilities/data-insights-course-2--what-are-interest-scores | /academy/md/courses/data-insights-core-concepts-capabilities/data-insights-course-2--what-are-interest-scores.md |
| /courses/data-insights-core-concepts-capabilities/data-insights-course-2--how-do-audiences-work | /academy/md/courses/data-insights-core-concepts-capabilities/data-insights-course-2--how-do-audiences-work.md |
| /courses/data-insights-core-concepts-capabilities/data-insights-course-2--can-i-create-custom-models | /academy/md/courses/data-insights-core-concepts-capabilities/data-insights-course-2--can-i-create-custom-models.md |
| /courses/data-insights-core-concepts-capabilities/data-insights-course-2--quiz | /academy/md/courses/data-insights-core-concepts-capabilities/data-insights-course-2--quiz.md |

## Supplement for indexing

### Content summary

This course is a high-level introduction to the Data & Insights platform (Lytics), designed to give you a foundational understanding of how the product works. We'll cover the key concepts and capabilities you'll explore … This course is a high-level introduction to the Data & Insights platform (Lytics), designed to give you a foundational understanding of how the product works. We'll cover the key concepts and capabilities you'll explore in more depth throughout the certification program. What You'll Learn This introductory session provides essential background on customer data platforms and hands-on experience with basic Lytics functionality. You'll understand the strategic importance of data & insights platforms (CDPS) and see real-time profile building in action. What We'll Cover We'll start with the fundamentals—introducing what a Data & Insights platform is, the role of the data activation layer, and the critical importance of defining clear use cases before implementation. You'll learn to install the JavaScript tag and watch real-time customer profiles take shape, explore

### Retrieval tags

- Contentstack Academy
- data-insights-core-concepts-capabilities
- What
- profile
- common
- schema
- How
- does
- scoring
- work
- are
- behavioral
- scores
- interest

### Indexing notes

Chunk at each "### Lesson NN — Title" heading; copy lesson_id and topics from the preceding HTML comment into chunk metadata for RAG filters.
Course slug: data-insights-core-concepts-capabilities. Union of lesson topic tokens: What, profile, common, schema, How, does, scoring, work, are, behavioral, scores, interest, audiences, Can, create, custom, models, Data, Insights, Core, Quiz.
Do not embed or retrieve LMS-only quiz items or mastery exam answer keys from this export.

### Asset references

| Label | URL |
| --- | --- |
| Video thumbnail: What is a profile? | `https://cdn.jwplayer.com/v2/media/mMtDUT4b/poster.jpg?width=720` |
| Video thumbnail: What is a common schema? | `https://cdn.jwplayer.com/v2/media/PLvM0JAb/poster.jpg?width=720` |
| Video thumbnail: How does scoring work? | `https://cdn.jwplayer.com/v2/media/BwZ9Bhrt/poster.jpg?width=720` |
| Video thumbnail: What are behavioral scores? | `https://cdn.jwplayer.com/v2/media/8I7tQlvF/poster.jpg?width=720` |
| Video thumbnail: What are interest scores? | `https://cdn.jwplayer.com/v2/media/m12ekXvQ/poster.jpg?width=720` |
| Video thumbnail: How do audiences work? | `https://cdn.jwplayer.com/v2/media/ExHf6d4z/poster.jpg?width=720` |
| Video thumbnail: Can I create custom models? | `https://cdn.jwplayer.com/v2/media/6y9bQMgx/poster.jpg?width=720` |

### External links

| Label | URL |
| --- | --- |
| Contentstack Academy home | `https://www.contentstack.com/academy/` |
| Training instance setup | `https://www.contentstack.com/academy/training-instance` |
| Academy playground (GitHub) | `https://github.com/contentstack/contentstack-academy-playground` |
| Contentstack documentation | `https://www.contentstack.com/docs/` |