Predictive LTV Walkthrough

This guide will focus on how to access and understand your predictive LTV data in the Lifetime Value Report. For a full walkthrough of standard Lifetime Value Report features, please take a look at our LTV Report Walkthrough article.

How to access your predictive LTV data
How the predictive LTV model works
What your projections are telling you
How report settings work with predictive data
The "LTV Predictions" section
The "Predicted Revenue" section
Predictive vs Historical LTV

How to access your predictive LTV data

All predictive modeling is integrated directly into the Lifetime Value Report, which you can always access by clicking “Lifetime Value” and then "Cohorts" on the side banner of your screen.

Just below the report settings (but above the report matrix) is a switch labeled “Predictive data”. When you click this switch, your LTV report will fill out the rest of your matrix with predictive LTV data in one place for deeper insights into your customer base.

💡 Tip: The way to quickly denote predictive vs historical data is by color and by position on the report. Historical data is shown in different shades of a solid, navy blue and is always concentrated in the top-left half of your report. Your LTV projections are shown in striped shades of a brighter and lighter blue and are concentrated in the bottom-right half of your report.

Before getting deeper into the report, let’s take a quick look at how these projections are generated.

Predictive vs Historical data

Lifetimely offers two key ways to measure Customer Lifetime Value (LTV): Predictive LTV and Historical LTV.

Predictive LTV: This estimates the future value of a customer based on their current buying behavior. Using machine learning, Lifetimely predicts how much a customer is likely to spend over a set period (e.g., 6 months, 12 months, or longer). Predictive LTV is useful for forecasting revenue, adjusting marketing strategies, and understanding the long-term impact of acquiring new customers.
Historical LTV: This calculates the actual value a customer has brought to your store over time. It’s based on past purchases and gives a clear picture of how much revenue each customer has already generated. Historical LTV is ideal for analysing past performance and comparing customer segments to see which group delivers the most value.

Using both Predictive and Historical LTV together provides a more complete understanding of customer behavior, helping you make informed decisions to grow your business.

How the predictive LTV model works

When you toggle on the “Predictive data” switch, our Predictive LTV Model kicks into action. The goal of the model is to accurately project the future buying behavior of every individual customer. But how are these predictions made?

Essentially, the model takes whatever transaction data is available for your current customers, and then finds past customers that match on factors such as products purchased, reorder frequency, spending patterns, and more. Then it uses these matches as a baseline to predict not just how much each customer will spend in future sales, but when these sales are most likely to occur. What you end up seeing in your LTV report is all of these individual projections added up to the cohort level and broken out into a monthly forecast of the average accumulated sales each cohort will drive.

Let’s return to the report to see it in action.

What your projections are telling you

To get a better sense for what exactly the model's projection represent, let's zoom in on a few cohorts.

In our example report, here is the cohort of customers who placed their first orders in May 2024:

In the example with data for May-2024, the report spans the past six months by default. For the highlighted May-2024 cohort, we have accumulated data for up to six months following their first order.

The initial columns (0 through 4) represent actual historical data for these months, while the column labeled "5" and "6" includes projections using predictive data. Here's a breakdown:

Months 0 through 4: These are the accumulated sales based on actual historical data for each month.
Month 5 ($13,114): This is a projection from the LTV model, estimating the accumulated sales expected by the end of the fifth month, based on customer trends.

These predictive figures allow you to anticipate future revenue from newer customer cohorts.

💡 Tip: Just like in a standard report, a quick way to make sure you understand a cell's value is to hover over the cell with your cursor.

Now let's look closer at a newer cohort. Here are customers who made their first order in September 2024:

Because we only have data from the same month in which first orders were made (or "0" months since the first order), the majority of this row is projections of LTV.

The first predictive cell ($1,164) shows the LTV model's projection of the average accumulated sales for this cohort by the end of October, which is the first month after the cohort's first orders.
The last (or sixth) predictive sell ($994) shows the LTV model's projection of the average accumulated sales for this cohort by the end of March 2025, which is the sixth month after the cohort's first orders. Note how much further this project extends beyond the Mar 1 to Oct 1 date range of the report.

How report settings work with predictive data

Many report settings will work the same whether or not predictive data is enabled, but some settings have some important differences and/or considerations when looking at predictive data.

Time period

In our example above, we saw that a default report with a time window set to the last six months completes your LTV report matrix so that you see historical data and/or projections of LTV for each cohort up to six months. This means that for a default report, the projection that's farthest in the future is five months after your newest cohort's first orders.

But what if you want to project even further out? Your instinct might be to select a time window that extends into the future, but keep in mind that the LTV model needs at least first order data for a cohort in order to run its projections. If it's September 2024, the LTV model can't generate predictions for an October 2024 cohort.

However, the model can project out as far as 24 months! To see longer projections, you just need to choose a time window that reaches further back. Compare the projections here, a report from Mar 1, 2024 to Aug 31, 2024 (top) and Aug 1, 2023 to Aug 31, 2024 (bottom).The end date of both reports is August 2024, but the second report gives you projections out to 12 months after first orders for each cohort.

The end date of both reports is August 2024, but the second report gives you projections out to 12 months after first orders for each cohort:

Perhaps the best way to think about this is that predictive data will fill in all the white space of a standard report. Therefore, to see more projections, you need to start with a report with more white space, which can only be done by selecting a longer time window (or by organizing cohorts by week of first order).

Timeframe

Because the predictive LTV model works on an individual level (projecting future sales for each individual customer), you can still choose to organize your cohorts by week, month, quarter, or year, and your projections will adjust accordingly.

Metrics

Currently, the metrics that integrate with predictive data are:

Accumulated sales per customer
Accumulated gross margin per customer
Cohort sales
Accumulated sales per customer / CAC
Accumulated gross margin per customer / CAC

We're working to integrate the rest of these metrics as soon as we can!

👉 Use case: Let's say that you're building out a financial model based on the report above, and you want to use the predictive LTV model to project total sales over the next month. Remember that the present day in this report is April 1, 2021, and the report looks back on the last six months. Which cells would you add up to see a projection of April sales?

Because it's September 1, April sales projections for each cohort will be in the first predictive cell in each row:

To view September sales projections for earlier cohorts as well, you would just need to choose a longer time period.

To add up October sales projections, you would just need to look at the second predictive cell in each row. For November projections, you'd look at the third predictive cell in each row, and so on.

Filters

Again, because the predictive LTV model projects future sales for each individual customer, all filters can be applied as with a standard LTV report, and you can use these to analyze different customer segments at any level you choose.

CAC payback tool

CAC payback projections will be enabled as soon as the "Accumulated gross margin" metric is added to the model.

The "LTV averages" section

Below the report is a section called "LTV averages":

These figures show you average accumulated sales across all customers in the report for periods of 3 months, 6 months, 12 months, and 24 months. The numbers you see here are often a blend of historical and predictive data.

In the above example, an average customer included in the full date range of the report is expected to generate $238 in accumulated sales in the 6 months following their first order.

The calculations here are meant to zoom out of cohort analysis to give you a more aggregate view of the average values of your customers in the short-term, medium-term, and long-term.

The "Predicted sales" section

Even further down the report is a section called "Predicted sales":

This section leverages your sales projections to forecast total month-to-month revenue across all cohorts. Hovering over each bar will show the breakdown of new customers' and repeat customers' projected contributions towards each month's sales.