---
## Introduction
---
Predictions are a codeless AI-powered tool built on top of Synerise analytics to predict any type of event or action in a customer’s journey.

**From this chapter you will learn:**  
<br><img src="/api/docs/image/54176ad07f146575310749eba44b7c2f42c1b327/icons/check-s.svg" alt="Arrow down icon" class="icon">how predictions work,  
<br><img src="/api/docs/image/54176ad07f146575310749eba44b7c2f42c1b327/icons/check-s.svg" alt="Arrow down icon" class="icon">where to find full predictions documentation.





- [Predictions](/docs/ai-hub/predictions) - learn more about Synerise predictions.


## Requirements
---
The following list explains basic requirements necessary to start working with predictions:

1. [Enable Predictions](/docs/ai-hub/predictions/enabling-predictions). Decide which of the predictions types you would like to enable:
    - [Lookalikes](/docs/ai-hub/predictions/lookalikes)
    - [Custom predictions](/docs/ai-hub/predictions/custom)
    - [Propensity predictions](/docs/ai-hub/predictions/propensity)  
    Further steps depend on whether your workspace contains the minimum required data. 
3. Once the set-up is ready, it usually takes a few hours to initialize predictions on your workspace. Once the initialization is done, you can make your first prediction. 


- [Quick start with predictions](/docs/ai-hub/predictions) - learn more about quick start with Synerise predictions.


## Types of predictions
---
Synerise offers 3 types of predictions, described below.

### Custom predictions 
---
You can use the Custom prediction type to predict any type of event or customer’s action that can be calculated in an expression and produce a numerical or 1/0 (true/false) value. Here are a few examples of what you can predict:

- Churn likelihood
- Conversion
- Open rate (OR)
- Click-through rate (CTR)
- Click-to-Open rate (CTOR)
- Who will visit
- Purchases from abandoned basket


- [Custom predictions](/docs/ai-hub/predictions/predictions-introduction#regression-and-classification-predictions) - check the requirements for custom predictions.



### Lookalikes predictions 
---
You can use Lookalikes for discovering new segments of customers, extending reach, picking the most promising new comers with regards to their similarity to your best customers. The list contains a few examples of what you can discover:
- Segment of customers likely to convert to your yearly repeating marketing campaign
- The best offline, fresh customers
- Best customers in a specific location
- And many more



- [Lookalikes predictions](/docs/ai-hub/predictions/predictions-introduction#lookalikes) - check the requirements for lookalikes predictions.


### Propensity predictions 
---
Propensity predictions let you evaluate how likely customers are to buy products with specific features, such as:
- Brand
- Category
- Color
- And many more


- [Propensity predictions](/docs/ai-hub/predictions/predictions-introduction#propensity-predictions) - check the requirements for propensity predictions.