Overview
Seed Signals are custom audiences sent to TikTok Ads Manager. They contain visitors ranked by predicted incremental lift based on your selected objective. TikTok uses these audiences as a basis for Lookalike Audiences in ad groups. This guide covers the setup of Seed Audiences on TikTok, including audience structure, testing, and scaling.Prerequisites
Technical Requirements:- An active connection to your TikTok Ads account
- A TikTok Pixel connected in Innkeepr
- Sufficient data history for signal generation (minimum 30 days recommended)
Audience Types
On TikTok, Innkeepr provides seed audiences as Custom Audiences — visitor lists ranked by predicted incremental lift based on your selected objective. The objective determines what the ranking optimizes for — for example conversion probability, customer lifetime value, or average order value. These audiences are used as source audiences for TikTok Lookalike Audiences. Just like on Meta, Innkeepr builds these audiences from pixel events. Innkeepr scores visitors on the anonymous level — no login, no email, and no CRM match required.Setup Instructions
Step 1: Create Audience Buckets There are different ways to use seed audiences on TikTok, and not every setup works equally well across all accounts. The optimal configuration depends on factors like traffic volume, product portfolio, and spend budgets. As of July 2026, we recommend the following setup as a starting point: Recommended bucket structure:
The logic: more selective source audiences (smaller percentile) are paired with smaller lookalikes to maintain signal quality. Broader source audiences can support larger lookalikes because the expansion is less sensitive to individual user variation.
TikTok requires a source audience of at least 1,000 users before a Lookalike Audience can be created. If a percentile bucket contains fewer users than that, widen the percentile range.
Step 2: Send Audiences to TikTok
- Create an Audience Signal in Innkeepr for each bucket
- Select “TikTok Ads” as your destination and set the Audience Type to
Seed - Send — Innkeepr sends
innkeepr_targetingevents to your connected TikTok Pixel and builds the Custom Audience from these events - Wait 24–48 hours for TikTok to populate the Custom Audience
- Create Lookalike Audiences in TikTok Ads Manager based on each bucket, using the recommended size option (Narrow, Balanced, Broad) from the table above. Set Contain Source to Omit, so the lookalike reaches new users and the source audience itself is not targeted
Important: Keep all other variables identical across ad groups:
- Same creatives (videos, copy) in every ad group
- Same optimization event (e.g. Complete Payment, Add to Cart)
- Same bid strategy
- Same placements
Monitor & Optimize
Weeks 1–2: Observation Phase- Do not adjust budgets, bids, or creatives during the initial learning phase
- Monitor that all ad groups are spending their allocated budget and exiting the learning phase
- Verify that conversions are being tracked correctly across all ad groups
- Compare ROAS, new customer share, and AOV across ad groups
- Identify which buckets outperform broad targeting and by how much
- If a bucket underperforms broad consistently, it can be paused
- Increase budget on the best-performing Innkeepr ad groups incrementally (20–30% per increase, not more)
- Measure how much additional spend the Innkeepr audiences can absorb while maintaining comparable performance to broad
- The goal is to determine what share of total campaign spend Innkeepr audiences can cover at equal or better performance than broad targeting
- Continue monitoring after each budget increase — allow 3–5 days for TikTok’s algorithm to stabilize before evaluating
Scaling question to answer: How much additional spend can Innkeepr audiences absorb compared to broad targeting, at the same or better CPA/ROAS? This determines the incremental budget capacity that Innkeepr unlocks for your TikTok campaigns.
Best Practices
Creative Isolation The test is only valid if creatives are identical across all ad groups. If you want to test new creatives or add additional creatives during the test, add them to all ad groups at the same time. Never add creatives to only some ad groups — this makes performance differences between ad groups unattributable. Lookalike Size Selection The recommended lookalike sizes (Narrow, Balanced, Broad) are starting points. Depending on your market size and target geography, you may need to adjust:- Smaller markets (e.g. single country, DACH): if the Narrow lookalike does not spend its budget, switch Seed 1 to Balanced
- Larger markets (e.g. EU-wide, US): Narrow, Balanced, Broad works well
Troubleshooting
Audiences Not Populating
All Buckets Underperform Broad
Performance Drops After Sales Phases
Performance drops can coincide with sales events (e.g. Black Friday, seasonal promotions). During and after these phases, audience composition and conversion patterns shift temporarily. Innkeepr typically detects these phases automatically and adjusts the underlying models accordingly.
If a performance drop persists for more than 1–2 weeks after a sales event has ended, reach out to the Innkeepr team to verify that the model has recalibrated correctly.