Forecast recurring revenue regimes

What it's for

Shows boards whether growth, retention, margin and burn have entered a different operating regime—and forecasts ARR and liquidity from those joint dynamics instead of extrapolating one headline growth rate.

What you give it

Inputs split into evidence read from your connected systems, calibration your team owns, and numerical controls that affect precision but never the result's meaning.

{
  "current_recurring_revenue": 100,
  "current_unrestricted_cash": 200,
  "historical_periods": [
    {
      "evidence_verified": true,
      "gross_margin": 0.4,
      "gross_revenue_retention": 0.85,
      "id": "revenue-history-0",
      "net_cash_burn_per_opening_arr": 0.2,
      "organic_arr_growth_rate": -0.055,
      "period_index": 0
    },
    {
      "evidence_verified": true,
      "gross_margin": 0.4,
      "gross_revenue_retention": 0.85,
      "id": "revenue-history-1",
      "net_cash_burn_per_opening_arr": 0.2,
      "organic_arr_growth_rate": -0.05,
      "period_index": 1
    },
    {
      "evidence_verified": true,
      "gross_margin": 0.4,
      "gross_revenue_retention": 0.85,
      "id": "revenue-history-2",
      "net_cash_burn_per_opening_arr": 0.2,
      "organic_arr_growth_rate": -0.045000000000000005,
      "period_index": 2
    },
    {
      "evidence_verified": true,
      "gross_margin": 0.4,
      "gross_revenue_retention": 0.85,
      "id": "revenue-history-3",
      "net_cash_burn_per_opening_arr": 0.2,
      "organic_arr_growth_rate": -0.055,
      "period_index": 3
    },
    {
      "evidence_verified": true,
      "gross_margin": 0.4,
      "gross_revenue_retention": 0.85,

What you get back

This is the actual output of running the example above — computed by the same function the platform calls, not an illustration.

{
  "configuration": {
    "confidence_level": 0.9,
    "horizon_periods": 6,
    "simulations": 500
  },
  "decision": "recurring_revenue_regime_forecast_supported",
  "failed_gates": [],
  "fit_diagnostics": {
    "converged_before_iteration_limit": true,
    "em_iterations_completed": 2,
    "minimum_regime_effective_periods": 12
  },
  "forecast_regime_probability_by_period": [
    {
      "period": 1,
      "probabilities": {
        "regime-1": 0.138,
        "regime-2": 0.058,
        "regime-3": 0.804
      }
    },
    {
      "period": 2,
      "probabilities": {
        "regime-1": 0.212,
        "regime-2": 0.138,
        "regime-3": 0.65
      }
    },
    {
      "period": 3,
      "probabilities": {
        "regime-1": 0.244,
        "regime-2": 0.2,
        "regime-3": 0.556
      }
    },
    {
      "period": 4,
      "probabilities": {
        "regime-1": 0.274,
        "regime-2": 0.24,
        "regime-3": 0.486

How it works

Markov & state-space control — Choose a policy over evolving states when today's action changes tomorrow's options.

1. 1 Freeze consecutive finance-approved period features and standardize them; initialize multiple latent states by growth rank, then fit transition, mean and diagonal-variance parameters with forward-backward EM and Dirichlet transition smoothing.
2. 2 Relabel fitted states from weakest to strongest organic growth, calculate posterior historical/current state probabilities, effective periods, transition matrix and per-period log-likelihood improvement over one diagonal Gaussian state.
3. 3 Simulate future regime transitions and joint growth/margin/burn observations under one common market scenario per path; propagate opening ARR and unrestricted cash and apply evidence, support, model-improvement, target-ARR and liquidity gates.

Before you trust it

Every tool in the catalog ships with the conditions under which its answer is meaningful — and the conditions under which it should abstain instead of guessing.

Calibrating it to your org

Calibration workflow

1. 1 Define the management decision, target outcome, aggregate unit, privacy boundary, cadence, and prediction/intervention horizon for this organization.
2. 2 Build a tenant-scoped historical cohort using only information available before each prediction or decision; preserve zero periods, censoring, assignment probabilities, and unresolved outcomes when the method requires them.
3. 3 Estimate statistical parameters on training history, but obtain costs, utilities, risk tolerance, practical-effect thresholds, capacity, and policy constraints from accountable decision owners.
4. 4 Validate on later time windows or held-out aggregate units at the deployment grain, against a simple baseline and the function-specific validation strategy.
5. 5 Deploy only if the returned decision clears evidence, overlap, calibration, robustness, and guardrail checks; warning, unsupported, schema-gap, and fallback decisions are abstentions.
6. 6 Monitor realized outcomes, data drift, coverage, and decision regret; recalibrate at a governed cadence or after a detected regime/definition change, never merely because a stakeholder dislikes the result.

Call it from your AI

You don't wire up 388 tools in your MCP client. The GitRevio MCP server exposes 18 tools, three of which let an agent search the catalog, read a tool's schema, and run it — so the assistant finds this one on its own.

gitrevio_capabilities_search
  { "q": "fit a diagonalgaussian hidden markov model" }
  → finds "forecast_recurring_revenue_regimes"

gitrevio_capability_describe
  { "capability_id": "forecast_recurring_revenue_regimes" }
  → returns the input schema and agent guidance shown on this page

gitrevio_capability_run
  { "capability_id": "forecast_recurring_revenue_regimes", "arguments": { ... } }
  → returns the result shown above

Works in Claude Desktop, Claude Code, Cursor, Cline, Continue.dev, Goose and Aider. See the MCP server.

Related tools

See every tool in Customer, revenue & pricing →