34:21The Retention Roadshow
The Retention Roadshow · Los Angeles
Email and SMS Revenue Forecasting with Daniel Guerra
Daniel Guerra shares a repeatable process for building defensible retention forecasts with account data, business context, AI, and human judgment. Learn how to explain the gap between a projection and the result.
Watch it. Put it to work.
ABOUT THIS SESSION
Agree on the baseline before forecasting.
Daniel Guerra shares a repeatable process for building defensible retention forecasts with account data, business context, AI, and human judgment. Learn how to explain the gap between a projection and the result.
For ecommerce founders, marketers, and operators working on retention.
- Speaker
- Daniel Guerra
Head of Data, New Standard Co - Recorded at
- The Retention Roadshow ↗
Los Angeles · June 2026
Speaker roles and platform examples reflect the session’s original context. This is an archived conversation.
TAKE IT BACK TO YOUR DESK
Ideas to put to work.
- 01
Agree on the baseline before forecasting
Choose a measurement source, attribution settings, and growth goals before asking AI for a forecast.
Read this part · 08:14 ↓ - 02
Add the context your ESP cannot see
Combine email data with paid spend, promotions, and operational changes.
Read this part · 09:43 ↓ - 03
Use misses to improve the model
Explain differences between projected and actual revenue, then feed those explanations into the next forecast.
Read this part · 15:41 ↓
READ THE SESSION
The edited transcript.
A condensed, edited reading version based on the YouTube captions and session chapters. Repetition and unclear audience audio have been removed; the discussion is paraphrased for clarity, rather than presented as a verbatim transcript. Timestamps refer to the original video.
Original recording on YouTube ↗Agree on the baseline before forecasting
A forecast is only useful when everyone agrees on the number being measured. Daniel starts by documenting the measurement source, attribution settings, revenue mix, and goals in one reference. Otherwise, two people can evaluate the same month against different definitions and reach conflicting conclusions.
Add the context your ESP cannot see
Account data supplies part of the picture. Paid acquisition, promotional calendars, changes in offers, and other business decisions affect the outcome too. Daniel organizes inputs into accessible platform data, contextual information, and retrospective adjustments. Missing inputs can make a polished projection fundamentally unreliable.
Use misses to improve the model
Daniel treats forecasting as an ongoing feedback process. A change in paid spend or an increased discount can explain why actual performance diverged from the initial plan. Human review connects those changes to the numbers, challenges AI output, and improves the next projection rather than simply replacing a missed target.
KEEP THE IDEAS COMING
Stay in the conversation.
3 SESSIONSPLAY IT BACK. PUT IT TO WORK.
34:21
45:23The Retention Roadshow
BFCM Retention Testing with Fil Pejic
1:13:26The Retention Roadshow
The 2026 Email Flow Playbook
YOUR NEXT STEP: IN THE ROOM
Bring your questions.
Meet your people.
Join Commerce Roundtable in 2027 for focused learning and conversations with people working through the same challenges.