CLVTools

CLVTools is an R package for modeling customer purchasing and attrition from non-contractual transaction histories. It is strongest for analysts who want to choose among probabilistic models and tailor them with covariates or constraints. Its narrow focus and R-based workflow make it a poor substitute for a turnkey customer analytics service.

Overview

In non-contractual businesses, customers can stop buying without formally cancelling. CLVTools estimates that behavior and predicts expected transactions and the probability that an individual customer is still active. Those outputs support customer lifetime value analysis, cohort analysis, and segmentation, with a configurable forecast horizon.

The models are generally used with cohorts whose customers joined at the same time, so the package suits aligned customer groups better than unstructured populations with different acquisition periods. Analysis starts with transaction records containing customer IDs and purchase dates; prices also appear in the example. Analysts need to be comfortable working in R and preparing suitable transaction data.

Key features

Model choice and individual forecasts

The package implements Pareto/NBD, BG/NBD, Gamma/Gompertz/NBD, and Gamma/Gamma models. Having several approaches in one toolkit gives analysts room to select a model for their purchase and attrition analysis, while individual forecasts retain customer-level distinctions that cohort averages can hide.

Covariates and extensions

Time-invariant covariates are supported across the models, while time-varying covariates are available for some. Extensions include correlation between purchase and attrition processes, L2 regularization for contextual-factor parameters, and equality constraints between those parameters. This flexibility is valuable when the analysis calls for richer model specification, but it also makes CLVTools a specialist package rather than a ready-made reporting workflow.

Installation and documentation

The stable release is installed from CRAN; a development version can be installed from GitHub using devtools. Building from source requires the external GNU Scientific Library (GSL), an extra dependency that can complicate setup. The project provides a walkthrough, reference manual, and vignettes on modeling, advanced techniques, and package classes. Bug reports go through GitHub Issues, and contributions are accepted as pull requests.

Pricing

The CLVTools R package costs nothing, is open source, and is licensed under GPL-3. There are no paid tiers to trade against, so the package's cost advantage comes with a technical trade-off: users must work in R, and source compilation requires GNU GSL.

Platforms

CLVTools supports Linux, macOS, and Windows. Its installation instructions cover Intel and Apple Silicon Macs as well as Windows and Linux; it requires R, and compiling from source adds the GSL dependency.

Who it's for

Choose CLVTools if you analyze non-contractual customer histories in R and want established probabilistic models, individual forecasts, and control over covariates and model constraints. It is a particularly natural fit for cohort-oriented work. Look elsewhere if your priority is a turnkey interface or a broader customer platform rather than a configurable R package.

Pros and cons

Pros: Four model families cover purchase, attrition, and monetary-value analysis in one package.

Pros: Individual predictions and covariate support enable customer-level analysis beyond cohort averages.

Pros: GPL-3 licensing and a free package remove subscription costs.

Cons: R is required, and source builds need GNU GSL, adding setup work for analysts and teams.

Cons: Its cohort-oriented, non-contractual modeling focus is a mismatch for teams seeking general-purpose customer analytics.

Alternatives

For a different approach to customer lifetime value software, browse Customer Lifetime Value Software.

Pushwoosh is a freemium option with web, desktop, and mobile platforms; choose it instead if you want a broader platform with a free monthly plan that includes 1,000 MAU, 5 AI requests per day, 20,000 email sends, and unlimited push notifications.

RevenueCat is freemium and supports Android, iOS, macOS, web, and API; it may suit teams tracking up to $2,500 in monthly revenue before a 1% charge applies.

Siftmo offers a free plan for up to 50 monthly orders and paid tiers at $29 a month for up to 500 orders and $69 a month; it may suit readers whose needs are framed around monthly order volume.

VOZIQ AI Platform is a separate option for readers considering a predictive subscriber churn solution.

WorthSignal is another free option for readers to consider.

SaaSFlow offers a free plan with all features, unlimited users, and unlimited data sources up to €120k ARR (€10k MRR), with a Pro tier at €100 a month on annual billing; it may suit teams seeking that SaaS-focused plan structure.

Klaviyo offers a free plan for up to 250 active profiles, 500 email sends per month, and $5 of mobile messages; it may suit readers prioritizing those messaging allowances.

Reaktion is a paid alternative with a Rise plan at $169 a month for 1,000 orders and one store.

Verdict

CLVTools is a strong choice for R-comfortable analysts modeling non-contractual customer behavior who value model selection, customer-level predictions, and flexible covariates without a software charge. Its main reason to choose it is the depth of its probabilistic toolkit; its main reason to look elsewhere is the specialized, code-first workflow and the extra GSL requirement for source builds.