Behavioral Scores [Lesson]

Find out how Lytics behavioral scores enable you to better understand and target your customers.

Overview

What will I learn?

• What are behavioral scores?
• How are they calculated?
• What scores are available?
• How can I use them?

In this guide, we'll introduce you to the out-of-the-box behavioral scores Lytics provides to better understand and target your customers. Each score represent a distinct behavioral quality that can be composed to build rich audiences.

Taking the time to understand how these scores work will help you utilize them to the fullest and make them powerful tools in your marketing strategy.

How are scores calculated?

Lytics uses proprietary data science and machine learning to calculate behavioral scores.

Because of this, Lytics scores have distinct benefits over any segmentation rules a marketer could create manually:

• Scores are self-learning — they require no manual input and generate automatically
• Scores are self-maintaining - meaning that an audience created using a score will be as effective in six months as it is today.

Lytics behavioral scores are calculated on a scale between 0 and 100. This enables Lytics to continuously update user profiles without having to update audience definitions. It also gives the ability to see the complete distribution of all users. 

In the next section, we'll walk through examples of each score and how they are designed with marketing use cases in mind.

What scores are available?

The full set of behavioral scores

Here is a quick run down of the 9 out-of-the-box scores Lytics provides. Keep reading for deeper explanations of each score.

1. Quantity - Measures a user's cumulative activity over their lifetime of brand engagement.
2. Frequency - Measures how often a user is interacting with your brand over time.
3. Recency - Measures how recently the user's general interaction has been.
4. Intensity - Measures the depth of a user's typical interaction with your brand.
5. Momentum - Measures the rate at which users are interacting with your brand.
6. Propensity - Predicts how likely a user is to return with subsequent activity.
7. Consistency - Measures the regularity of a user's engagement pattern.
8. Maturity - Measures how long a user has registered interactions with your brand.
9. Volatility - Measures how sporadic a user's behavior is while interacting with your brand.

See the scores live in your account

You can check out how your customer data falls on the spectrum of behavioral scores in your account on the Scoring page in app.

Quantity

Quantity measures a user's cumulative activity over their lifetime of brand engagement. The more activity the user registers, the higher the score.

It is a common tactic to target a user based on the amount of times they have visited a website, or have performed some other behavior. This becomes increasingly difficult as marketers add more data sources to their stack, and users continue to engage over time.

Quantity takes into account a user's behavior on all data sources and measures that relative to how the most and least active users are engaging — so a user's score will always be between 0 and 100. You can think of this as a test score.

What is the point of scoring between 0 and 100? This is how we can ensure that any audience created with a score will always stay relevant. Perhaps 1,000 page views seems like a lot for a user now, but the number will only grow larger as your site grows older and the amount of content you have increases. Another benefit of having a bounded score range is the ability to see the complete distribution of all users.

This is an example of how scores look like across an entire audience. The x-axis is the score (ranging from 0 to 100; 5 to 95 in the example for clarity) and the y-axis is the number of people who have that value as their score.

Frequency

Frequency measures how consistent a user is overtime in interacting with your brand. More frequent interactions mean a higher score. This serves as a measurement of user regularity. Do they visit once a week? Once a day? Once a lifetime?

Since this score is relative to all your users, you can easily target your most frequent users, rather than something like "users who visited in the last week", which will vary wildly in size.

Again, this score has a fixed range of 0 to 100. All the scores are like this. It is how we can continuously update user profiles without having to update audience definitions.

Recency

Recency measures how recently the user's general interaction has been. More recent activity means a higher score.

Without scoring, this would be achieved by looking at the last time a user visited. Although better than nothing, that approach is kind of crude. Maybe an at-risk user opened your email by accident? It'd be an expensive oversight to assume that the user had recent activity and didn't need any nurturing.

Intensity

Intensity measures the depth of a user's typical interaction with your brand. More sustained intense/deep usage means a higher score.

The behavior a user exhibits during a single session is very telling of them as a consumer. If they have high interaction in a session (high intensity) they are more likely to be a deeper researcher or more curious. If they have low interaction in a session (low intensity) they are more likely to be casually browsing or engaged with a certain piece of content, but not your overall brand.

Momentum

Momentum measures the rate at which users are interacting with your brand. Users who are interacting more than usual with your brand will have a higher score.

It's easy to confuse how momentum and recency differ, but they are actually very different. Universally speaking, we've found them to have a 5% correlation. Recency measures absolute recency of activity, but just because a user has recent activity, doesn't mean they're not at risk of churning.

If a user maintains a constant rate of activity, their momentum score will be 50. If they are more active than they used to be, their momentum will be greater than 50 and might warrant a loyalty offer. If they are less active than they used to be, their momentum will be less than 50 and might warrant a win-back campaign.

Propensity

Propensity predicts how likely a user is to return with subsequent activity. Users exhibiting positive interaction patterns are more likely to return and have higher scores.

There are many reasons why users churn — changing interests, competition from competitors, bad experience, etc. — but from a data perspective, attrition of any kind starts to look similar.

Propensity employs an ensemble of statistical models to identify any patterns it can find for detecting how and when attrition starts to occur. With time, it's able to find more patterns in your data and become increasingly accurate in identifying when users start to exhibit those behaviors.

Consistency

Consistency measures the regularity of a user's engagement pattern. More regular behavior means a higher score.

Your most consistent users engage with your brand at a regular cadence. For example, a user that registers behavior every 7 days will have high consistency and would have the same consistency as a user who registers behavior every 30 days. As users' behavior starts to vary — sometimes every 7 days, sometimes every 30 — the users' consistency score will decrease.

Consistency can be an important factor in predicting churn, where more consistent users are less likely to churn than those who have lower consistency.

Volatility

Volatility measures how sporadic a user's behavior is while interacting with your brand. The more sporadic the activity, the higher the score.

It represents the stability of the volume of data that a user is generating, and serves as a slightly more nuanced version of the intensity score. Consider a user where 100% of their daily sessions are considered "intense". Their intensity score would be 100, but the score doesn't yield any information regarding the volatility of a typical session.

Maturity

Maturity measures how long a user has registered interactions with your brand.

A user who has registered behavior over 5 years will likely have high maturity. A user who registered behavior over 3 years, but hasn't registered any in 2 years will have less maturity. A user who registered behavior over the most recent 3 years will have the same maturity as the user previously mentioned.

As an example, you could target users with high maturity scores inviting them into a loyalty rewards program via ads, emails, and in-app notifications. Low maturity users could be served more onboarding or educational content to nurture them into high-value, long-term users.

All of this information and more can be found in our Behavioral Score documentation.

How can I use scores?

Use Behavioral Audiences based on Scores

Since Lytics scores are constantly updating in real time, audiences based on these scores are highly effective for targeting customers according to their engagement with your brand.

However, interfacing with these scores directly can be difficult. They are low-level building blocks that require some expertise to use to their fullest. For this reason, Lytics makes these scores more readily usable through our out-of-the-box Behavioral Audiences that use scoring under-the-hood.

After completing this module, check out the Behavioral Audiences one next to learn more.

Build Custom Audiences using Scores

You can also use behavioral scores in your own audiences. Each score is accessible as a Custom Rule in the Audience Builder. They can be added to any audience definition as an intelligent filter when the size of the audience is larger than desired.

For example, when creating an audience to be used to buy ads against, the size of the audience is critical. The size can be arbitrarily shrunk by taking 10% of the matching users, or it can be intelligently shrunk by creating a threshold with a Lytics score such as Propensity or Momentum. This way, the best fit users remain.

In the Lytics audience builder, simply type "score" in the Custom Rule tab and you'll see all 9 scores available.

Experimenting with the scores is encouraged. You don't have to be a data scientist to use them!

Use Scores in your Lookalike Models

Last but not least, behavioral scores can be used in your Lookalike Models. Scores are often one of the most important features when building models to predict which users are most likely to convert, which users are at risk of churning, etc. 

This topic is covered in much more detail in the Lookalike Models course in the Deep Dive section of the Lytics Academy.

Knowledge Check

Lytics behavioral scores are out-of-the-box. No configuration required on your part.

A. True

B. False

Answer: A

How often are Lytics behavioral scores are updated?

A. In real time

B. Daily

C. Weekly

Answer: A

All users will be scored on a range of _______?

A. 0 to 10

B. 0 to 100

C. 0 to 1,000

D. It varies based on the score

Answer: B

How can you leverage behavioral scores in your marketing efforts? Select all that apply.

A. Use scores in your audience definitions -- replacing demographic data or arbitrary rules

B. Use Lytics pre-built audiences based on scores -- no need for data science expertise

C. Use scores to improve your Lookalike Models -- improve conversions, reduce churn, etc.

D. Replace your data science team -- Lytics scores do the work for them!

Answer: A, B, C - Lytics provides a data science workbench for your marketing team, which can augment and support your data science team (if you have one), but not necessarily replace them. Adding Lytics to your stack can free up your data scientists to work on more custom use cases for your marketing organization.

Next Steps

Here are recommended resources to continue learning about how to leverage behavioral scores in your marketing use cases.

Academy Courses:

• Behavioral Audiences
• Lookalike Models

Documentation:

• Behavioral Analysis - What is it? Why is it useful for marketing?
• Behavioral Scores documentation
• Behavioral Audiences

Use Cases:

• Optimize Remarketing Spend - using recency and quantity scores
• Target High-Propensity Prospects with Higher Bids