Seatext library / BotRefund evidence
How to Use BotRefund to Detect Unusual Timing in Ad Traffic
BotRefund detects unusual timing by analyzing 110+ behavioral signals including superhuman input speed under 1ms, unnatural session durations, and burst lead arrivals. Install the tracking script, let it collect session data, then review the...
✓ Built for advertisers who need clear, refund-ready traffic evidence.
BotRefund identifies unusual timing patterns by measuring input speed, session duration, and lead arrival intervals across every paid click. The platform flags interactions faster than humanly possible — such as form submissions in under 1 millisecond — and sessions that are too short, too long, or too uniform to be human. These timing signals feed into an AI model that cross-checks 110+ independent browser, network, device, and behavioral checks to reach 99% confidence before generating a refund-ready report with click IDs, timestamps, and session recordings formatted for Google and Meta review teams.
What unusual timing means in paid traffic
Unusual timing covers any temporal pattern that real users rarely produce. On Meta campaigns this includes several leads arriving in short bursts, forms submitted immediately after landing, or conversions concentrated at unusual hours. On Google Ads it appears as rapid clicking — multiple clicks from the same IP in a short window — or duplicate click signatures suggesting automated repetition. Both platforms treat these as invalid activity when they deviate significantly from typical user behavior at the server or browser level.
BotRefund separates these patterns from normal variation. A weak campaign can attract real people who are not ready to buy, but bot traffic and form spam leave repeatable technical and behavioral patterns: unusually fast form completion, identical field structures, sudden placement-level spikes, or conversion events with no meaningful page engagement.
How BotRefund captures timing signals
BotRefund runs client-side checks in the visitor's browser after the paid click lands. The script measures pointer behavior (robotic linear mouse movements, absence of humanlike mouse tremor), speed behavior (superhuman input speed under 1ms), path behavior (grid-aligned movement patterns), engagement behavior (absence of clicks or scrolling), and session behavior (unnatural session durations that are too short, too long, or too uniform). Each check produces independent evidence rather than a verdict.
The platform combines 110+ behavioral, browser, hardware, network, and attribution signals. Timing signals are weighed alongside scrollbar width leaks, clean context iframe mismatches, and evasion/debugger/anti-stealth traps. The AI prediction model evaluates the complete pattern instead of trusting a raw rule, which is how BotRefund reaches 99% confidence when the session evidence supports it.
Key timing signals BotRefund monitors
- Superhuman input speed: Interactions faster than 1 millisecond that a person could not realistically perform.
- Unnatural session durations: Visits that are too short, too long, or too uniform across multiple sessions.
- Burst lead arrivals: Several conversions arriving in tight time clusters inconsistent with organic traffic flow.
- Immediate form submission: Forms completed instantly after page load without reading or scrolling.
- Unusual hour concentration: Conversions clustered at atypical times for the target audience.
- Rapid clicking patterns: Multiple clicks from the same IP or click ID within implausible intervals.
Step-by-step process to detect unusual timing with BotRefund
- Install the BotRefund tracking script on your landing pages. The script begins collecting browser, network, device, and behavioral data for every paid click immediately.
- Preserve attribution before changing campaigns. Keep campaign, ad set, creative, placement, and click identifier data intact so each flagged session ties back to the exact paid interaction.
- Allow data collection across a representative traffic volume. BotRefund needs enough sessions to distinguish anomalies from normal variation.
- Review the audit dashboard for timing-specific flags: speed behavior alerts, session duration anomalies, and burst-pattern clusters. Each finding includes a session-by-session explanation with signal-by-signal reasoning.
- Cross-check timing signals against CRM outcomes. A high reported lead count paired with no calls connected, demos booked, or qualified opportunities confirms the timing anomalies map to wasted spend.
- Generate the refund-ready report. BotRefund formats click IDs, campaign details, timestamps, session recordings, and signal-by-signal reasoning in the structure Google and Meta reviewers expect.
- Submit the claim through the platform's negotiation workflow or export the report for manual filing. BotRefund's team has worked through 2,500+ audits and knows how to present bot evidence to both platforms.
Interpreting timing data in context
Not every fast session is a bot. Privacy tools, travel, corporate networks, and unusual devices can produce unexpected behavior for genuine people. BotRefund keeps each timing signal as evidence — not a verdict — and cross-checks it against independent browser, network, device, and behavior data. The AI model weighs the complete pattern: a single anomaly rarely triggers a bot classification, but a consistent cluster of timing, pointer, scroll, and rendering anomalies does.
Campaign patterns matter too. A sharp lead-quality difference by placement, creative, audience expansion, device, or landing page helps isolate where unusual timing concentrates. This lets you suppress specific traffic sources rather than pausing entire campaigns.
Common mistakes and limitations
- Treating every unresponsive contact as fraud. This can make a team exclude a valuable audience. Start with a structured audit comparing ad-platform data, website sessions, and CRM outcomes before changing targeting.
- Relying on a single timing signal. BotRefund's 99% confidence comes from corroboration across 110+ checks, not one browser tell.
- Changing campaigns before preserving attribution. If you pause or edit campaigns before the audit captures click IDs and placement data, you lose the evidence chain needed for refunds.
- Expecting automatic platform credits. Google and Meta issue some invalid activity credits automatically, but their server-level detection catches far less than client-side behavioral evidence. Most refunds require a filed claim with structured evidence.
- Assuming timing detection works without the script installed. Server-side logs alone miss advanced botnets that mimic human IPs and headers. Client-side measurement is required for input-speed and session-duration signals.
Verification step: confirm timing anomalies map to wasted spend
Before filing a refund request, verify that flagged timing anomalies correlate with zero CRM progression. Pull the click IDs from BotRefund's report, match them to your CRM records, and confirm those sessions produced no calls connected, demos booked, qualified opportunities, or repeat engagement. This CRM-outcome check is the practical proof that unusual timing represents invalid traffic rather than fast but genuine users.
Key facts
| Metric | Detail | Source |
|---|---|---|
| Detection confidence | 99% when session evidence supports it | S2 |
| Behavioral signals analyzed | 110+ independent checks | S2 |
| Superhuman input speed threshold | Under 1 millisecond | S2 |
| Session duration anomalies | Too short, too long, or too uniform | S2 |
| Meta timing signals | Burst leads, immediate form submit, unusual hour concentration | S1 |
| Google timing signals | Rapid clicking, duplicate click signatures, abnormal click patterns | S6 |
| Client refund recovery rate | 83% across 2,500+ audits | S2 |
| Report format | Click IDs, campaign details, timestamps, session recordings, signal-by-signal reasoning | S2 |
Frequently asked questions
How fast is "superhuman" input speed?
BotRefund flags interactions under 1 millisecond. Real human input — clicks, keystrokes, form field transitions — cannot occur this fast. This threshold is measured client-side in the browser for each session.
Does BotRefund detect timing anomalies on both Google and Meta?
Yes. The same 110+ signal suite runs on traffic from both platforms. Meta-specific patterns include burst leads and immediate form submissions; Google-specific patterns include rapid clicking and duplicate click signatures. The refund-ready report is formatted for each platform's review process.
Can I use BotRefund timing data without filing a refund claim?
Yes. The dashboard shows timing anomalies in real time. You can suppress conversion events for flagged sessions so Google and Meta bidding algorithms train only on verified human traffic, improving ROAS without waiting for a platform refund.
What if my traffic has legitimate fast users?
BotRefund cross-checks timing signals against 100+ other browser, network, device, and behavioral checks. A single fast session without corroborating anomalies (robotic mouse paths, no scrolling, grid-aligned movement, etc.) will not be classified as a bot. The AI model weighs the complete pattern.
How long does data collection take before timing patterns are reliable?
There is no fixed minimum, but you need enough paid sessions to establish a baseline. Low-volume campaigns may require weeks; high-volume campaigns can produce actionable clusters in days. The dashboard indicates when statistical confidence is reached for each signal cluster.
Does BotRefund replace server-side fraud filters?
No. Server-side filters catch basic scraper bots via IP and header analysis. BotRefund adds the client-side behavioral layer that detects advanced botnets mimicking human IPs. Both layers can run together; BotRefund does not require infrastructure changes.
What happens after I submit a refund claim with BotRefund's report?
BotRefund's team supports the negotiation with Google and Meta reviewers using the structured evidence. Across 2,500+ audits, 83% of clients recover funds. The report format matches what platform teams use to review invalid traffic claims, reducing back-and-forth requests for additional data.
Further reading and comparison sources
These external sources provide additional context for evaluating the topic. Their inclusion is not an endorsement.
Learn more
Visit the website for more information.