Upload transaction data, get CLV predictions per customer with purchase probability and revenue forecasts. Free.
or click to browse · max 3 MB
Running customer lifetime value - bg/nbd model analysis...
Sent to — interactive charts, statistical results, R code, and AI insights.
Analyze another filePredicts how much each customer is worth over their lifetime using a probabilistic model. Estimates future purchase probability, expected transaction count, and revenue contribution — without needing to wait and see.
Use this when you have repeat-purchase transaction data (customer ID, dates, amounts) and want to forecast which customers will buy again and how much they'll spend.
If customers only buy once (e.g., real estate), this model won't work. Use RFM segmentation for a simpler behavioral grouping instead.
Built for: E-commerce manager, CRM analyst, retention marketer, DTC founder
Typical data source: Order history export with customer IDs, order dates, and order values
Transaction-level order data with customer identifiers
Minimum 100 rows · Best with 1000-50000 transactions
Predict customer lifetime value using the BG/NBD probabilistic model with Gamma-Gamma spending extension. Forecasts future purchase probability, transaction frequency, and revenue contribution per customer over a configurable time horizon.
The headline numbers — average CLV, total predicted revenue, and expected transactions per customer. Compare against your current customer acquisition cost to check unit economics.
How CLV is spread across your customer base. A long right tail means a few whales drive most value. If it's flat, value is more evenly distributed.
Customers grouped by predicted behavior — high-value loyalists vs one-time buyers vs dormant. Focus retention spend on the high-value at-risk segment.
Your most valuable customers ranked by predicted lifetime value. These are the accounts to protect and nurture.
Maps purchase frequency against recency. Customers in the top-right (frequent + recent) are your best. Bottom-left (infrequent + stale) are likely gone.
The probability each customer is still 'alive' (will buy again). Customers below 50% are likely churned — don't waste retention budget on them.
The fitted model parameters. Alpha/beta control purchase frequency, gamma/delta control dropout. Higher alpha relative to beta means customers buy more often.
How well the model's predictions match actual behavior. Good calibration means the probability estimates are trustworthy.
Plain-English interpretation — what the numbers mean, what's significant, and what to do next.
Need something simpler? Rfm — Just need behavioral segments without probabilistic modeling
Need more power? Churn Prediction — Subscription-based business with Stripe billing data
Similar: Retention Analysis, Rfm Segmentation
See our FAQ for details on pricing, data privacy, and how the analysis works. Every report includes a Methodology section showing the statistical test, assumptions checked, and diagnostics run.
Run any analysis on your own data — 60+ validated R modules, interactive reports, AI insights, and PDF export.
Try Free — No Credit Card