Skip to main content

Best Practices & Troubleshooting

Best Practices

  • Provide Sufficient Historical Data: Set a Training Start Date covering at least 90–180 days of transaction data to ensure high-accuracy model predictions.

  • Filter Restricted SKUs: Set Exclusion Filters for out-of-stock items, internal store charges, or seasonal clearance goods that should not be automatically recommended.

  • Utilize Fallbacks: Always define a valid Fallback Lookback Days period to avoid empty recommendation slots for brand-new customers without prior purchase history.

 

Troubleshooting Guide

Problem: Recommendations are not appearing in campaign preview or test sends.

  • Cause 1: Model is still actively training.

    • Fix: Check Audience → Tools → Recommendations. Ensure 24 hours have elapsed since triggering initial training.

  • Cause 2: Fallback lookback period is too restrictive.

    • Fix: Expand Lookback Days (e.g., from 30 to 90 days) in Fallback Settings so the engine can aggregate adequate sales data for fallback recommendations.

Problem: Campaign scheduling is blocked by the editor.

  • Cause: The email template contains more than 6 recommended product merge tag slots.

  • Fix: Remove excess recommendation blocks until total product slots per email are 6 or fewer.

Problem: WhatsApp carousel toggle option is disabled or throwing errors.

Back to top