Skip to main content
Trackly SMS uses machine learning to select the optimal creative for each contact, maximizing clicks and revenue.

​
How It Works

Instead of manually choosing which message to send, the ML system:
  1. Analyzes contact history (clicks, revenue, engagement patterns)
  2. Predicts performance for each available creative
  3. Selects the winner for that specific contact
  4. Learns from results to improve over time

​
Enabling Automated Selection

​
Campaign Setup

  1. Create a campaign in Automated Mode
  2. Configure the automated percentage:
Automated selection: 80%
Manual fallback: 20%
  • 80% of contacts get ML-selected creatives
  • 20% get the default creative (control group)

​
Available Creatives

The ML system chooses from creatives marked as Automated type:
  1. Go to Creatives
  2. Mark creatives as “Automated” type
  3. These become candidates for ML selection

​
The Selection Model

​
Features Used

The model considers:
FeatureDescription
Send countHow many messages they’ve received
Click countHistorical click behavior
Last click recencyDays since last click
Revenue historyPast purchase behavior
Time of dayWhen they typically engage
Creative historyWhich creatives they’ve clicked before

​
Model Training

Models are trained on your account’s historical data:
  1. Click model: Predicts probability of clicking
  2. Revenue model: Predicts expected revenue
Training runs automatically:
  • Periodic retraining (weekly)
  • Incorporates recent performance data

​
Predictions

For each contact, the model predicts: 
Creative A: 12% click probability, $0.45 expected revenue
Creative B: 8% click probability, $0.52 expected revenue
Creative C: 15% click probability, $0.38 expected revenue
Selection can optimize for clicks OR revenue.

​
Configuration

​
Optimization Goal

Choose what to optimize for:
GoalBest For
ClicksEngagement, list warming
RevenueDirect response, sales

​
Cooldown Settings

Prevent the same creative from being sent repeatedly: 
Creative cooldown: 3 days
If a contact received Creative A yesterday, it won’t be selected again for 3 days.

​
Exploration vs Exploitation

Balance between:
  • Exploitation: Use the predicted best performer
  • Exploration: Try other creatives to gather more data
Exploration rate: 10%
10% of sends randomly select creatives to gather performance data.

​
Performance Tracking

​
Model Metrics

View model performance in Reports > ML Metrics:
MetricDescriptionGood Value
Click AUCClick prediction accuracy> 0.65
Revenue RMSERevenue prediction errorLower is better
Feature importanceWhat drives predictions-

​
A/B vs Automated

Compare automated selection against manual: 
Automated (80%): 14% click rate, $0.52 revenue/send
Control (20%): 11% click rate, $0.41 revenue/send

Lift: +27% clicks, +27% revenue

​
When to Use ML Selection

  • Large contact list (5,000+)
  • Multiple creatives to choose from (3+)
  • Enough historical data (10,000+ sends)
  • Measurable conversion goals

​
Cold Start

For new accounts or new creatives:

​
New Accounts

Without historical data, the model needs training data:
  1. Start with blast campaigns to gather clicks
  2. After 5,000-10,000 sends, ML becomes effective
  3. Switch to automated mode

​
New Creatives

New creatives need exposure:
  • Exploration rate ensures new creatives are tested
  • Performance data accumulates over time
  • Strong performers rise to the top

​
Monitoring

​
Dashboard Indicators

Watch for:
  • Model health: Is the model performing well?
  • Creative diversity: Are all creatives getting selected?
  • Performance trends: Is click rate improving?

​
Alerts

Set up alerts for:
  • Model degradation
  • Single creative dominating (may indicate overfitting)
  • Performance drops

​
Best Practices

Keep 5-10 active automated creatives. Too few limits ML effectiveness.
Add new creatives periodically. Stale content loses effectiveness.
Always maintain some manual sends to measure ML lift.
Understanding what drives predictions helps create better creatives.

​
Next Steps

Campaigns

Set up automated campaigns

Reporting

Analyze ML performance