> For the complete documentation index, see [llms.txt](https://docs.hackle.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.hackle.io/en/cohort/create/recommand.md).
# Cohort Recommendation
## Creating a Cohort of Users Who Abandoned Their Cart
If you want to extract users who dropped off at the cart stage as a Cohort and build marketing action items, you can extract the Cohort as follows! There are two ways to extract users who dropped off at a specific stage.
1. **Using the Funnel Chart**\
This method is useful when you want to create a Cohort of users who dropped off within a specific period.\
👉 Check it here! \[View how to create from the Funnel chart]\(../../핵클팀 추천 Use Case/bounced-users.md#1-퍼널-차트에서-만들기)
2. **Creating Manually**\
You can create a Dynamic Cohort by setting the desired conditions directly on the Cohort detail screen.\
👉 Check it here! \[View how to create manually]\(../../핵클팀 추천 Use Case/bounced-users.md#2-직접-만들기)
## Creating a Cohort of Users Who Viewed a Specific Page
1. Event Setup
1. Create \[view\_specific page] as an event!
2. Last N Days
1. Specify whether to include users who viewed within the last N days. The definition of 'last N days' may vary depending on how finely you manage active users (AU) within your organization.
3. Count Specification
1. Set the threshold for how many times the event set in step 1 must have been triggered to include a user in the Cohort.
## Creating a Cohort of Users Who Purchased During a Specific Period (e.g., Black Friday Sale)
{% hint style="info" %}
Analytics tip
You can analyze the average purchase frequency of users who purchased during a discount event vs. users who purchased during a regular period.
{% endhint %}
1. Specify the time period.
1. If there was a major promotion period, set that promotion period. (e.g., Black Friday)
2. Combine users who triggered the \[purchase event] during that period with (optional) users who viewed the \[promotion page] during that period using an `**AND**` condition.
## Creating a Cohort of Users Who Signed Up After Seeing a Specific Ad Campaign
{% hint style="info" %}
Usage tip
You can compare the **average purchase amount of users who signed up after a specific ad campaign**.
{% endhint %}
1. Specify the ad period.
2. Combine users who triggered the \[campaign page view event] during that period with users who triggered the \[sign-up event] during that period using an `**AND**` condition.
## Creating a Cohort of Users Who Used the Service in a Specific Month
{% hint style="info" %}
Usage tip
For example, you can save students who enrolled in the service in April as a Cohort, then compare the course completion rate between March and April in your analysis.
{% endhint %}
In this case, set the event to the service usage event and configure the period corresponding to the specific month (e.g., April).
1. Event: Select the event representing service usage, such as 'service\_use'.
2. Period: If you want to create a Cohort for April, set the period from April 1 to April 30 (all of April).
3. Count: ≥ 1 (users who used the service at least once)
**Usage tip**
With the above settings, you can extract users who used the service in April. Based on this, save the Cohort, then apply the same settings for March and compare the course completion rates for March and April in your analysis.
## Creating a Cohort of Users Who Repurchased Within 30 Days of a Purchase
1. Select the event corresponding to a purchase. (e.g., purchase\_payment)
2. Set the period to the last 30 days.
3. Set the Count condition to ≥ 2. This means the user **triggered the purchase\_payment event at least twice within the last 30 days**.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://docs.hackle.io/en/cohort/create/recommand.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.