# Optimal Marketing Channel
Optimal Channel Selection helps you automatically choose the best communication channel for each customer — significantly improving message engagement and marketing ROI. Instead of manually deciding whether to send a message via Email, SMS, WhatsApp, Push Notification, or RCS, our prediction model analyzes real-time behavior and historical engagement to make the most effective choice.
Use this feature to:
* Improve open, click-through, and conversion rates
* Reduce channel fatigue and unnecessary spend
* Deliver personalized experiences at scale
**Prerequisites:**
* Active installed channels you want to include (Email, SMS, WhatsApp, Push, RCS)
* Sufficient historical engagement data (typically 30 days minimum)
### How It Works
The system analyzes historical engagement data across all available channels to build predictive model for each contact. These models consider factors such as open rates, click-through rates, and channel-specific behaviors to determine the optimal channel for future communications.
#### **Understand Customer Preferences**
The model evaluates each contact's
* **Channel engagement history** (opens, clicks, reads, replies)
* **Delivery success rates**
#### **Segment Smartly**
You can create audience segments based on **Predictions for Contact**:
To create segment using Predictions, you can follow these steps:
* Create a segment and select condition as **Predictions for Contact**
* Select **Optimal Marketing Platform** as attribute
* Enter or select options like **Email, SMS, WhatsApp, Push, Google RCS**
#### **Continuous Optimization**
The system continuously learns from Real-time engagement signals. Models automatically re-train to reflect changing contact behavior.
The model considers **cost vs. expected engagement** when selecting a channel.
### **Fallback Strategy**
If the first choice fails (e.g., SMS is suppressed), the AI will automatically **fallback** to the next best channel based on:
1. Cost
2. Predicted engagement
---
# Agent Instructions: 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.bird.com/applications/audience/contacts/concepts/optimal-marketing-channel.md?ask=
```
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.