> 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/ab-test/mab-test/mab-vs-ab-test.md).

# MAB Test vs A/B Test

### Overview

An A/B Test is an experiment method where a fixed amount of traffic is allocated to each group under a controlled environment over a period of time, and decisions are made by comparing performance between groups.\
In comparison, a MAB (Multi-Armed Bandit) Test is an experiment method that automatically adjusts traffic per group to maximize a success metric.

Because a MAB Test adjusts traffic distribution based on success metric results over a relatively shorter period than a typical A/B Test (approximately 1\~2 weeks recommended), you should account for the limitation that the sample may not be sufficient.\
Also, since traffic distribution is determined by a single success metric, decisions may differ from those that consider multiple metrics.

![](/files/1wdSbcJ4Y5u72w0slOca)

### How is MAB different from an A/B Test?

1. An A/B Test collects multiple goal metrics and their statistical values (p-value or Bayesian probability) over a period of time, and makes decisions through an analysis (interpretation) process. MAB, on the other hand, is only concerned with maximizing a single success metric (conversion rate, CTR, etc.) and automatically adjusts traffic to maximize it, so there is no analysis (interpretation) process. The main goal of MAB is to answer "Which test group shows the greatest reward (= success metric optimization)?"
2. MAB does not require a control group. Therefore, it does not provide statistical values like p-value or the probability of outperforming Group A.
3. MAB is suitable for maximizing conversions for short and temporary experiences where changes are not permanent (e.g., promotional offers, headline tests, webinar registration pages). It is also recommended when continuous optimization is needed, such as for algorithm tests like search and recommendation logic.

### How to use

It is recommended to use a MAB Test when you can set a single clear success metric and want to quickly identify the optimal option and expose it to more users within a short period.

Primarily, **experiments conducted in display areas within the service (e.g., home screen banners, recommended product carousels, etc.) can be run as MAB Tests.**\
This is because the target user behavior (such as banner clicks, product clicks) is clear, and it is generally unlikely that decision-making needs to consider trade-offs between the success metric and other metrics when deciding to release the change (e.g., success metric increases by 10% but metric Y drops by 9%).


---

# 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:

```
GET https://docs.hackle.io/en/ab-test/mab-test/mab-vs-ab-test.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.