LiftSignals is live. Every plan starts with a 30-day free trial — no credit card required. Start free →

Platform · Sales forecasting

Ecommerce sales forecasting built from the customers you already have.

A trend line can’t tell you that your best cohort is slipping. LiftSignals builds its revenue forecast from customer-level predictions: who is likely to order again, how often and for how much, so the forecast changes when your customers do, and you can see why.

No credit card · Read-only access · Works with Shopify, WooCommerce, BigCommerce, Amazon, Square or a CSV

A row of gray clay bars rising gently, followed by two translucent orange glass bars continuing the rise

Definition

What is sales forecasting?

Sales forecasting estimates how much revenue a business will make over a coming period. Most ecommerce forecasts extend last year’s trend. A customer-based forecast adds up what each existing customer is predicted to spend, then adds expected new customers on top.

A CUSTOMER-BASED FORECAST

Forecast revenue = Σ predicted spend of existing customers + expected new-customer revenue

Returning revenue comes from each customer’s predicted orders and order value. New-customer revenue comes from your recent acquisition pace and seasonality.

Spreadsheet trendLiftSignals sales forecast
Built fromLast year’s monthly totalsEach customer’s predicted spend
Explains changesNoShows which customers moved the number
UncertaintyOne lineA likely range
UpdatesWhen someone rebuilds itEvery night

Why trend lines miss

Your forecast says growth while your best customers are quietly leaving.

01

Top-line trends hide cohort decay.

New-customer growth can mask returning-customer decline for months, until it doesn’t.

02

A single number invites false confidence.

Inventory and spend plans built on one line have no room for the range that actually exists.

03

Nobody can explain a miss.

When the month comes in low, a trend line can’t say whether it was fewer new buyers or lapsing old ones.

How LiftSignals does it

A revenue forecast you can trace back to customers.

Returning revenue

The sum of each existing customer’s predicted orders and spend, from the same models behind lifetime value and churn.

New customers

Expected first orders from your recent acquisition pace and seasonal patterns.

Range

A likely range around the forecast, not just a single line.

Drivers

A breakdown of what moved the forecast since last week: customers lapsing, customers rising, new-customer pace.

Refresh

Recalculated every night as orders arrive.

REVENUE FORECAST · NEXT 13 WEEKS

SOURCEFORECASTLIKELY RANGE
Returning customers$412,000$381K–$446K
New customers$168,000$139K–$199K
Total$580,000$531K–$632K

Down $9,400 since last week: 62 high-value customers moved to high churn risk.

Illustrative read-out. Your forecast is built from your own customers, and the range is shown in the app.

What to do with it

Four decisions a customer-based forecast improves.

01

Plan inventory around a range

Planning

Order to the likely range, not a single line, so a soft month doesn’t leave you overstocked.

02

Catch a revenue gap early

Klaviyo

When the forecast drops because valuable customers are lapsing, start the win-back before the month closes.

Churn prediction →

03

Set acquisition targets that close the gap

Planning

Compare returning revenue with your goal to see how much has to come from new customers.

LTV:CAC calculator (coming soon) →

04

Explain the number to your team

Reporting

Show which customers moved the forecast this week, so the conversation is about causes, not just totals.

Customer lifetime value →

Proof on every play

Then prove the plays moved the forecast.

Every audience you send carries an automatic holdout: a random slice of those customers who don’t get the message. 30 days later you see what the campaign caused, not what it claimed, in dollars, with the confidence interval printed next to it.

Two glass columns of gray sand at the same level; the right column carries an extra layer of orange sand on top

Is it right for you?

Who customer-based forecasting is for.

A good fit if you

  • Get a meaningful share of revenue from returning customers
  • Plan inventory or ad budgets weeks ahead
  • Have at least about 500 customers and 90 days of orders
  • Want to know why a forecast moved

Sounds like you? Start free

Not the right tool if you

  • Need financial forecasting for your whole P&L
  • Sell mostly one-time purchases to new customers
  • Have just launched with little order history
  • Need store-by-store retail forecasting

FAQ · sales forecasting

Sales forecasting questions, answered.

See the customer model underneath in how to calculate customer lifetime value.

How do you forecast ecommerce sales?

The simplest way extends past trends. A stronger way adds up what existing customers are predicted to spend and adds expected new-customer revenue, which is how LiftSignals does it.

How accurate is the forecast?

It comes with a likely range. The app shows how past forecasts compared with what actually happened in your store.

Can it explain why the forecast changed?

Yes. Each week shows what moved it: customers lapsing, customers rising in value and the pace of new customers.

Does it account for seasonality?

Yes. Seasonal patterns from your order history are part of both the returning and new-customer parts.

How much history do I need?

About 500 customers and 90 days of orders to start. Seasonal effects are clearer with a full year of history.

Can I export the forecast?

Yes, as a CSV, so it can go into your planning spreadsheet.