Can the diagram show probabilities and expected values?

Yes. Include numeric probabilities such as "70% chance of approval" and payoff figures in your prompt, and the generator will attach them to the appropriate chance and terminal nodes, often highlighting the path with the highest expected value.

Is this generator useful for data science work?

Definitely. You can prompt it to render classification trees with feature splits, sample counts, and node purity metrics such as Gini impurity or information gain, making it straightforward to illustrate a trained model for a technical audience.

What do the different node shapes mean?

Squares mark decision points where the analyst controls the path. Circles mark chance events where probability governs which branch is taken. Triangles mark terminal nodes that carry the final outcome or payoff value for that path.

How does a decision tree differ from a mind map or flowchart?

A mind map radiates associations from a central concept without any directional logic. A flowchart sequences steps in a process and often loops. A decision tree is strictly hierarchical, branching outward to enumerate outcomes, assign probabilities, and calculate expected costs or returns.

Can I download the finished diagram?

Yes. Once the tree is generated, you can save it as a high-resolution image and drop it straight into a slide deck, research paper, or management report. Free users get standard resolution; upgrading unlocks higher output quality.

For Analysts

Decision Tree Generator Decision Trees

Describe any branching scenario and Figviz will render a structured decision tree on the spot. Built for analysts who need probability-weighted diagrams without the manual layout work.

✓Decision Analysis Diagrams✓Probability & Payoff Nodes✓Expected Value Calculations✓Publication-Ready Quality

Examples

Pick an example as inspiration or generate your own above

Capital Allocation Decision Tree

A capital allocation decision tree weighing product launch, line expansion, and status quo, with probability-adjusted payoffs flowing to each terminal outcome.

businessinvestmentexpected-value

Clinical Pathway Decision Tree

A symptom-driven clinical tree that walks through ordered tests, assigns diagnostic probabilities, and routes each path to the appropriate treatment recommendation.

medicaldiagnosisclinical

Customer Churn Classification Tree

A trained classification tree predicting subscriber churn by splitting on contract length, monthly spend, and support contact frequency, with node-level sample counts and impurity scores.

machine-learningclassificationgini

Software Project Risk Tree

A risk breakdown tree for software delivery that categorizes threats by domain, assigns severity tiers, and maps each scenario to a cost-adjusted mitigation strategy.

risk-analysisproject-managementmitigation

Delivery Methodology Selection Tree

A methodology selection tree that routes teams to the best-fit delivery framework based on headcount and scope complexity, with projected timeline and budget envelopes at each leaf.

project-managementstrategyagile

Should I Learn This Language? Tree

A lightweight binary tree that guides developers through four qualifying questions to reach a clear, reasoned verdict on whether to pick up a new programming language.

basicyes-nobinary

Prompt templates you can copy

Start with one of these examples, then adapt the subject, labels, data, or layout for your own use.

Capital Allocation Decision Tree

A capital allocation decision tree weighing product launch, line expansion, and status quo, with probability-adjusted payoffs flowing to each terminal outcome.

Create a professional decision tree for a business investment decision. Start with a square decision node "Investment Strategy" branching into three options: "Launch New Product", "Expand Existing Line", "Maintain Status Quo". Each branch leads to circular chance nodes with market outcomes: "Strong Market (0.4)", "Moderate Market (0.35)", "Weak Market (0.25)". Show expected monetary values at triangular terminal nodes ranging from -$500K to +$2M. Use green for positive outcomes, red for negative. Professional business consulting style, white background.

Clinical Pathway Decision Tree

A symptom-driven clinical tree that walks through ordered tests, assigns diagnostic probabilities, and routes each path to the appropriate treatment recommendation.

Create a medical diagnosis decision tree starting with "Patient presents with chest pain". Branch into "Cardiac origin suspected" and "Non-cardiac origin suspected" based on initial assessment. Each branch continues with diagnostic tests (ECG, blood tests, imaging) leading to specific diagnoses and treatment plans. Include probability percentages at each chance node. Use medical blue color scheme. Professional clinical guideline style, white background.

Customer Churn Classification Tree

A trained classification tree predicting subscriber churn by splitting on contract length, monthly spend, and support contact frequency, with node-level sample counts and impurity scores.

Create a machine learning classification decision tree for predicting customer churn. Root node shows "Total Samples: 1000, Gini: 0.48". Split on features like "Contract Length <= 12 months", "Monthly Charges > $70", "Customer Service Calls > 3". Each internal node displays sample count, Gini impurity, and class distribution bar. Leaf nodes show predicted class (Churn/Retain) with confidence percentage. Color nodes by majority class (blue for retain, orange for churn). Data science style, white background.

Software Project Risk Tree

A risk breakdown tree for software delivery that categorizes threats by domain, assigns severity tiers, and maps each scenario to a cost-adjusted mitigation strategy.

Create a risk analysis decision tree for a software development project. Start with "Project Risk Assessment" and branch into categories: "Technical Risk", "Schedule Risk", "Budget Risk". Each risk branches into severity levels (High/Medium/Low) with probability percentages. Terminal nodes show recommended mitigation strategies and expected cost impact. Use red for high risk, yellow for medium, green for low. Include expected value calculations. Professional risk management style, white background.

Turn Tangled Choices into a Clear Decision Tree

Every high-stakes decision hides a branching structure underneath: a set of competing actions, uncertain outcomes, assigned probabilities, and downstream consequences. A decision tree makes that structure visible so you can reason about it rigorously. Figviz reads a plain-language description of your scenario and renders a properly formatted, mathematically coherent diagram in seconds, no manual node placement required.

The Three Building Blocks of Every Decision Tree

Decision Nodes (Squares): Points where the decision-maker actively chooses between two or more defined paths.

Chance Nodes (Circles): Points where the outcome is uncertain. Each branch carries a probability that sums to 1.0 across siblings.

Terminal Nodes (Triangles): The leaves of the tree, where a final payoff, cost, or utility value is assigned.

Expected Monetary Value (EMV): The weighted average payoff of a chance node, calculated by multiplying each outcome value by its probability and summing the results.

Where Decision Trees Get Used

Strategy teams use them to stress-test product launch scenarios and capital allocation plans. Data science teams use classification variants (CART, Random Forest) to model how input features predict target labels. Clinical teams embed them in diagnostic protocols to standardize care pathways. Risk offices use them to quantify the expected cost of mitigating versus accepting a given threat.

Five Steps to a Well-Formed Decision Tree

Step 1: Anchor the Root: Name the central decision or diagnostic question that starts the analysis.

Step 2: Branch on Actions: List every option or alternative available at the root and subsequent decision nodes.

Step 3: Layer in Uncertainty: Add chance nodes for factors outside your control, then assign probability estimates to each branch.

Step 4: Value the Endpoints: Assign a payoff, cost, or utility score to every terminal node.

Step 5: Generate: Feed those parameters into the prompt field and let Figviz produce a structured, labeled diagram ready for slides or reports.

Decision Trees vs Flowcharts: What Sets Them Apart

Flowcharts trace the steps in a repeatable process, often looping back when conditions repeat. Decision trees do something different: they radiate outward from a single root to enumerate every possible path through a choice problem, attaching probabilities and payoffs along the way. That quantitative framing is what makes a decision tree an analytical instrument rather than a process map.

Frequently asked questions

Write a short description of your scenario in the prompt field: name the root choice, list the branches, mention any uncertain outcomes and their rough probabilities. Figviz parses that context and builds a properly structured diagram automatically.

More Tools

All tools →

Make your own decision tree with Figviz

Create a free account and get starter credits to generate your own. No credit card required.