Rank features by evidence adjusted ROI

What it's for

Stops weakly evidenced feature forecasts from outranking credible investments merely because their point-estimate ROI is larger.

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.

{
  "features": [
    {
      "contribution_value_per_incremental_outcome": 12000,
      "evidence_reliability": 0.82,
      "fully_loaded_investment_cost": 180000,
      "id": "credible-retention-workflow",
      "incremental_outcome_scenarios": [
        10,
        18,
        28
      ]
    },
    {
      "contribution_value_per_incremental_outcome": 12000,
      "evidence_reliability": 0.25,
      "fully_loaded_investment_cost": 150000,
      "id": "weakly-evidenced-ai-widget",
      "incremental_outcome_scenarios": [
        18,
        32,
        60
      ]
    }
  ],
  "maximum_negative_roi_probability": 0.4,
  "minimum_evidence_reliability": 0.5,
  "minimum_expected_adjusted_roi": 0.05,
  "scenario_probabilities": [
    0.2,
    0.5,
    0.3
  ],
  "skeptical_prior_incremental_outcomes": 0
}

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.

{
  "assumptions": [
    "Incremental outcome scenarios come from a valid causal or explicitly non-causal forecast design, and contribution per outcome plus fully loaded cost share one finance counterfactual, horizon, and currency.",
    "Evidence reliability is calibrated on resolved comparable claims; it is not confidence, sample size, experiment label, or stakeholder belief by another name.",
    "The ranking does not handle dependencies, capacity, mutually exclusive features, adoption coupling, or strategic constraints and therefore is not a portfolio allocation."
  ],
  "configuration": {
    "maximum_negative_roi_probability": 0.4,
    "minimum_evidence_reliability": 0.5,
    "minimum_expected_adjusted_roi": 0.05,
    "scenario_count": 3,
    "skeptical_prior_incremental_outcomes": 0,
    "tail_probability": 0.1
  },
  "decision": "evidence_adjusted_feature_roi_supported",
  "feature_ranking": [
    {
      "clears_evidence_and_roi_gates": true,
      "cvar_roi_loss": 1,
      "evidence_adjusted_expected_roi": 0.0605,
      "evidence_reliability": 0.82,
      "feature_id": "credible-retention-workflow",
      "fully_loaded_investment_cost": 180000,
      "observed_model_expected_roi": 0.2933,
      "probability_negative_roi": 0.344
    },
    {
      "clears_evidence_and_roi_gates": false,
      "cvar_roi_loss": 1,
      "evidence_adjusted_expected_roi": -0.248,
      "evidence_reliability": 0.25,
      "feature_id": "weakly-evidenced-ai-widget",
      "fully_loaded_investment_cost": 150000,
      "observed_model_expected_roi": 2.008,
      "probability_negative_roi": 0.75
    }
  ],
  "method": "evidence_mixture_feature_roi_ranking_v1",
  "summary": {
    "feature_count": 2,
    "supported_feature_count": 1,
    "supported_feature_ids_in_rank_order": [
      "credible-retention-workflow"
    ],

How it works

Forecasting & survival — Estimate when something completes or fails, with censoring and unresolved work handled honestly rather than dropped.

1. 1 Freeze the causal or forecasting estimand, fully loaded incremental cost, contribution per incremental outcome, aligned scenarios, and a skeptical prior over no or limited uplift.
2. 2 Calibrate evidence reliability on resolved comparable claims, mix the claimed outcome distribution with the skeptical prior, and calculate expected ROI, negative-ROI probability, and lower-tail CVaR.
3. 3 Rank only features clearing reliability and downside gates, then pass supported features to a dependency-, capacity-, and constraint-aware portfolio optimizer before funding.

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": "rank feature investments by reliabilityshrunk roi" }
  → finds "rank_features_by_evidence_adjusted_roi"

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

gitrevio_capability_run
  { "capability_id": "rank_features_by_evidence_adjusted_roi", "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 →