> For the complete documentation index, see [llms.txt](https://docs.chord.co/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.chord.co/model-your-data/predictive-models/chord-predictive-intelligence-overview.md). # Chord predictive intelligence overview Chord’s predictive data science capabilities help brands turn raw customer data into actionable intelligence. With Personas, Churn Predictions, and Purchase-Likelihood modeling available across the Chord platform—and accessible through both Ask Chord (AI chat) and analytics—teams can quickly activate smarter marketing and retention strategies. ## 1. What Chord predictive models do Chord applies machine-learning models to your customer and commerce data to surface insights such as: * **Customer Personas & Churn Predictions** — Understand who your customers are (e.g., *Deal-Seeker*, *Wellness Enthusiast*, *Loyalist*) and which customers are at risk of dropping off. Personas help you tailor messaging and product experiences, while churn predictions help you intervene proactively. * **Likelihood to purchase or repurchase** — Identify customers most likely to buy next. * **Customer lifetime revenue prediction (CLR)** — Determine who will be most valuable long term. * **Behavioral and commercial patterns** — Insights based on recency, frequency, spend, and engagement trends. ## 2. Why it matters Predictive intelligence helps teams: * Spend smarter on acquisition * Increase retention and customer lifetime value * Personalize communication at scale * Identify the right customers at the right moment * Make decisions proactively rather than reactively Chord’s models turn your customer data into a real competitive advantage—helping marketing, product, and analytics teams drive measurable growth. ## 3. How to use these insights in Chord | Model Name | Predict Level | Output Metric Name | Description | Notes | Input Metric(s) | Data Source(s) | Example Use Cases | Explore(s) | | --------------------------------- | ------------- | ----------------------------------- | ----------------------------------------------------- | --------------------------------------------------------------------------------------- | ---------------------------------------------------------- | ----------------------------- | ----------------------------------- | --------------------------------------------------------------------------------------------- | | Customer Lifetime Revenue (CLR) | User | Predicted Lifetime Revenue | Forecasted customer lifetime revenue | Based on historical patterns + user-specific behavior | Orders data, predicted customer ML features, sessions data | Orders, sessions, ML features | Retention targeting, VIP perks | Users | | RFM | User | Recency | Recency, frequency, and monetary scoring | Days since last order. Higher = more recent | Orders data | Orders | Segmentation, churn risk | Users | | RFM | User | Frequency | Recency, frequency, and monetary scoring | Number of orders in time window. Higher = more orders | Orders data | Orders | Segmentation, churn risk | Users | | RFM | User | Monetary | Recency, frequency, and monetary scoring | Total spend in time window. Higher = more spend | Orders data | Orders | Segmentation, churn risk | Users | | RFM | User | RFM Bucket | Recency, frequency, and monetary scoring | Combined RFM grouping | Orders data | Orders | Segmentation, churn risk | Users | | Predicted Repurchase | User | Repurchase Probability | Probability that the user will repurchase | Likelihood of buying again | Orders data, predicted customer ML features, sessions data | Orders, sessions, ML features | Win-back campaigns | | | Product Recommendations | User | Recommendations 1-5 | Top 5 recommended items for user | Top 5 predicted next purchases | Orders data, predicted customer ML features, sessions data | Orders, catalog, ML features | Cross-sell, personalization | Users | | Segmentation Clustering | User | Marketing Segment ID | Unstructured hierarchical cluster assignments | Used for targeting/lookalike audiences/personalization | Orders data, predicted customer ML features, sessions data | Orders, sessions, ML features | Audience targeting | | | Revenue Forecast | Company | Forecasted Revenue | Forecasted top-level revenue | Time series prediction | Time series order data | Orders | Budgeting, forecasting | Predicted Forecasts | | New Customer Forecast | Company | Forecasted New Customer Count | Forecasted count of new customers | Time series prediction | Time series order data | Orders | Acquisition planning | Predicted Forecasts | | Returning Customer Forecast | Company | Forecasted Returning Customer Count | Forecasted count of returning customers | Time series prediction | Time series order data | Orders | Retention planning | Predicted Forecasts | | Probability to Convert | Sessions | Conversion Probability | Probability a session will convert to a paid customer | Likelihood session converts | Sessions and orders data | Sessions, orders | On-site personalization | Sessions, Marketing Attribution - Order Attribution, Marketing Attribution - User Attribution | | Predictive Marketing Attribution | Orders | Attribution % by Channel | Fractional revenue attribution by channel | Model-weighted attribution | Marketing spend, conversions | Spend, conversions | Channel optimization | Marketing Attribution - Order Attribution, Marketing Attribution - User Attribution | | Customer Personas | Users | User Persona Name | Customer segment grouping based on purchase behavior | Personas group customers with similar purchasing patterns and predicted lifetime value. | Customer email | Customer email | Personalization, audience targeting | | | Likelihood to Churn (Percentile) | Users | User Churn Propensity Percentile | Identify customers at risk of churning | Higher percentiles = higher likelihood of churning | Customer email | Customer email | Retention planning, churn risk | | | Likelihood to Churn (Probability) | Users | User Churn Propensity Percentile | Identify customers at risk of churning | Higher values = higher probability of churning | Customer email | Customer email | Retention planning, churn risk | | --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.chord.co/model-your-data/predictive-models/chord-predictive-intelligence-overview.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.