For Admins
Call Spikes

Call Spikes

The portal continuously watches each company's call volume against its historical pattern. When something looks abnormal, you and the affected supervisor are notified.

Reviewing call spikes

Click Call Spikes (opens in a new tab) in the sidebar. You'll see a table of detected anomalies, with:

  • Affected company
  • When the spike occurred
  • The deviation magnitude (how far above or below normal)
  • Status (open, acknowledged, resolved)

Click into any row to see the underlying data — actual call volume vs. expected, recent calls during the spike window, and links into the calls themselves.

Investigating a spike

A typical investigation flow:

  1. Open the spike detail.
  2. Look at the calls during the spike window — are they legitimate (real customers) or noise (one persistent robocaller, accidental flood from a marketing test, etc.)?
  3. Check whether the affected company recently launched a new ad campaign or service.
  4. Cross-reference with operational events — was Five9 having issues at that time?
  5. If real → notify the supervisor responsible so they can adjust staffing.
  6. If noise → consider blocking the source (handled outside the portal in Five9) and document the cause.
  7. Mark the spike as acknowledged or resolved when investigation is complete.

Drops vs. spikes

The detector flags both spikes (volume sharply up) and drops (volume sharply down). Drops can indicate:

  • The customer's ad spend was paused
  • Their inbound number is broken or rerouted
  • Five9 is having an issue routing calls to that campaign

Drops are often more urgent than spikes — investigate them quickly. A silent phone is worse than a noisy one.

How forecasts and spikes relate

The forecasting feature predicts expected volume; the spike detection compares actual to expected. When you see a flagged spike, the forecast view shows you the gap visually.

If a customer's actual volume regularly diverges from forecast in a consistent direction, the model may need re-tuning for that customer's pattern. Note such cases for engineering review.

Spike severity rubric

A loose guide to triage urgency:

DeviationLikely meaningUrgency
Drop ≥50% during business hoursRouting/system issueHighest — investigate immediately
Spike ≥3× normal during business hoursReal campaign or PR momentHigh — confirm staffing
Spike outside business hoursSpam wave or robocallerMedium — investigate, may need to block
Drop ≥30% lasting many hoursAd pause or seasonalityMedium — confirm with customer
Single-hour deviationNoise or one-off eventLow — usually self-resolves

Coordinating with supervisors

Most spike alerts are best handled by the supervisor who owns the affected customer relationship. Your role as admin:

  • Investigate technical causes (Five9, S3, sync)
  • Tune the model when it consistently misfires
  • Escalate to engineering when it's not a customer-side issue

Next