> For the complete documentation index, see [llms.txt](https://help.smartico.ai/welcome/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.smartico.ai/welcome/products/crm-automation/segmentation.md). # Segmentation Smartico provides four core segment types in the Back-Office, along with analytical models (such as RFM Analysis) that classify players for targeting: 1. [**User State Segments**](/welcome/products/crm-automation/segmentation/user-state-segments.md) - based on the current state of the user. For example, a segment of all users that made 1 deposit might match 10 users right now, but 9 users tomorrow, or in 15 minutes, in case these 10 users make a second deposit. 2. [**Behavioral Segments**](/welcome/products/crm-automation/segmentation/behavioral-segments.md) - segment based on the behavior of the user. It combines data from both the user profile state and his behavior. The segment is based on the historical behavior of the user, e.g. users who did total wagering of more than 100 EUR on Slot games in the last 30 days. 3. [**Imported segments**](/welcome/products/crm-automation/segmentation/imported-segments.md) - segments can also be imported from a CSV file. Imported segments are used when you have a very specific audience that can’t really be grouped by any criteria. They are not that flexible as they remain exactly the same as you uploaded them. 4. [**Common Cases Segment**](/welcome/products/crm-automation/segmentation/common-cases-segments.md) **-** designed to simplify user targeting based on frequently used behavioral patterns. It offers a selection of predefined templates, allowing you to quickly configure conditions and control rebuild settings. 5. [**RFM (Recency, Frequency, Monetary)**](/welcome/products/ai-models/rfm-analysis.md) - segmentation that categorizes players based on their deposit activity. RFM segmentation provides insights into how recently, how often, and how much players have deposited. For creating advanced conditions, inspecting player memberships, and using value-based models, see: * [**Query Builder**](/welcome/products/crm-automation/segmentation/query-builder.md) - the visual interface used to construct segment conditions, logical groups, and property filters. * [**User Profile Page**](/welcome/products/crm-automation/segmentation/user-profile-page.md) - where operators can view an individual player's current segment memberships and attributes. * [**Value Score**](/welcome/products/ai-models/value-score.md) - an AI-driven model that categorizes depositing players into Top, High, Medium, and Low value tiers over 30-day and lifetime windows. {% hint style="danger" %} **Note on Segment Dependencies** Smartico allows you to nest segments—for example, filtering out users of Segment A from your new Segment B. If you choose to build dependent segments, note the following limits: 1. Depth Limit: Chains cannot exceed a depth of 10 segments. 2. No Circular Logic: Segments cannot reference each other in a loop (e.g., A excludes B, and B excludes A). *Note: Smartico's system catches most invalid chains and will throw an error upon saving. However, highly complex logical loops might bypass this initial validation.* {% endhint %} ### Segment Actions and Export Options Once a segment is created, the Back-Office provides several tools to manage and utilize the audience: * **Export Segment (CSV)**: Operators can export the list of players currently in a segment, including custom profile attributes. The export file is prepared in the background and delivered through a secure download link via email and browser notification. * **Data Warehouse (DWH) Export**: Operators can enable a Data Warehouse export toggle on individual segments. This creates and maintains a dedicated table function in BigQuery, allowing business intelligence and analytics teams to query segment members directly from their data warehouse. * **Audience Size and Overlap**: The segment list displays the estimated qualifying player count. Operators can trigger an on-demand audience calculation or compare multiple segments to identify audience overlap. * **Archiving**: Segments that are no longer needed can be archived to keep the workspace organized and immediately free up active segment quota. {% hint style="info" %} Note: Quotas apply only to active (non-archived) segments. Archiving unused segments immediately restores capacity. Default limits per label are: * 400 State-based segments * 50 Behavioral segments * Imported segments (no active segment limit) * 50 Common cases segments RFM segments are included in the state-based segments quota {% endhint %} ### Frequently Asked Questions **What is the difference between RFM Analysis and Value Score segmentation?** Both are AI-powered models that enrich player profiles with segmentation properties: * **RFM Analysis** categorizes active depositing players into 12 behavioral categories (such as Champions, Loyal, or At Risk) based on quantile rankings of Recency, Frequency, and Monetary deposit or casino activity. * **Value Score** categorizes depositing players into four percentile tiers (Top: top 5%, High: next 15%, Medium: next 25%, Low: bottom 54%) based on daily net deposits across rolling 30-day and lifetime windows. Both models update user profile properties daily, which operators can then target using User State Segments. **Why doesn't my behavioral segment update immediately when a player performs an action?** Behavioral segments analyze historical transaction windows (such as deposits or wagers over the last 30 days) and are recalculated in batches on a schedule (typically once per day, or up to hourly if configured). When used as entry conditions in real-time campaigns or automation rules, membership is evaluated against the latest completed batch. For instantaneous filtering based on the player's immediate current state, use User State Segments instead. **How can I nest segments or exclude members of one segment from another?** In the Query Builder, add a condition with one of the segment properties: **Core: State based segments** (user state segments), **Core: Behavioural segments**, or **Core: CSV & Common case segments**. Use the operator **has any of** to include members of a segment, or **doesn't have any of** to exclude them. Segment chains support up to 10 levels of nesting and cannot contain circular references. **What should I do if I reach the segment quota limit for my label?** Quotas apply only to active segments. If you reach your limit, archive unneeded or seasonal segments in the Back-Office to immediately restore available quota. If your operations require higher permanent capacity, administrators can request an increase to the label's segment limit settings. **Can I export segment members or query them in external reporting tools?** Yes. You can click **Export Segment** in the Back-Office to download a CSV file of segment users (with selectable profile properties), delivered via an email link and browser notification. Alternatively, you can enable **Data Warehouse Export** on a segment to generate a queryable table function in your connected data warehouse (such as BigQuery), allowing your BI team to query the segment directly. --- # 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://help.smartico.ai/welcome/products/crm-automation/segmentation.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.