Estimate portfolio company execution beta

What it's for

Separates portfolio-wide execution exposure from idiosyncratic movement so investors can see which companies amplify common shocks without overreading noisy raw correlations.

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.

{
  "confidence_level": 0.9,
  "material_beta_deviation": 0.2,
  "minimum_periods_per_company": 8,
  "observations": [
    {
      "company_id": "company-a",
      "execution_return": -3.03,
      "id": "company-a:0",
      "period": 0,
      "portfolio_execution_return": -2
    },
    {
      "company_id": "company-a",
      "execution_return": -2.25,
      "id": "company-a:1",
      "period": 1,
      "portfolio_execution_return": -1.5
    },
    {
      "company_id": "company-a",
      "execution_return": -1.47,
      "id": "company-a:2",
      "period": 2,
      "portfolio_execution_return": -1
    },
    {
      "company_id": "company-a",
      "execution_return": -0.78,
      "id": "company-a:3",
      "period": 3,
      "portfolio_execution_return": -0.5
    },
    {
      "company_id": "company-a",
      "execution_return": 0.75,
      "id": "company-a:4",
      "period": 4,
      "portfolio_execution_return": 0.5
    },
    {
      "company_id": "company-a",
      "execution_return": 1.53,
      "id": "company-a:5",

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": [
    "The portfolio execution factor is externally defined, point-in-time, common within period, and excludes the focal company to avoid mechanical self-correlation; company and factor returns share cadence and units.",
    "Company relationships are approximately linear and stable over the selected epoch, residual dependence and serial correlation are limited, and at least the governed minimum periods span meaningful factor variation.",
    "Empirical-Bayes shrinkage and normal intervals quantify model-based association, not causality, investment quality, valuation, misconduct, or person performance; regime changes and common measurement error require separate tests."
  ],
  "company_diagnostics": [
    {
      "classification": "amplified_portfolio_exposure",
      "company_id": "company-a",
      "execution_beta_interval": [
        1.4905,
        1.5134
      ],
      "period_count": 8,
      "posterior_execution_beta": 1.5019,
      "raw_execution_beta": 1.502,
      "shrinkage_toward_portfolio_beta": 0.0001,
      "systematic_execution_variance_share": 0.9999
    },
    {
      "classification": "defensive_portfolio_exposure",
      "company_id": "company-b",
      "execution_beta_interval": [
        0.5906,
        0.6135
      ],
      "period_count": 8,
      "posterior_execution_beta": 0.6021,
      "raw_execution_beta": 0.602,
      "shrinkage_toward_portfolio_beta": -0.0001,
      "systematic_execution_variance_share": 0.9991
    }
  ],
  "configuration": {
    "confidence_level": 0.9,
    "material_beta_deviation": 0.2,
    "minimum_periods_per_company": 8
  },
  "decision": "portfolio_company_execution_beta_estimated",
  "method": "empirical_bayes_random_effects_execution_beta_v1",
  "summary": {
    "amplified_company_count": 1,
    "between_company_beta_variance": 0.405,

How it works

Constrained optimization — Pick the best feasible option under real limits — budget, headcount, dependencies, capacity — rather than ranking a list and hoping it fits.

1. 1 Freeze a point-in-time aggregate execution return, cadence and stable epoch for every company plus an external leave-one-company-out portfolio factor that is identical within period.
2. 2 Fit company factor regressions, estimate sampling variance and cross-company random-effects heterogeneity, then shrink noisy raw betas toward the portfolio relationship with model-based intervals.
3. 3 Classify only interval-supported amplified or defensive exposure relative to beta one, and report systematic variance share while keeping regime, serial/dependent error, and measurement audits separate.

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": "estimate company sensitivity to an external" }
  → finds "estimate_portfolio_company_execution_beta"

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

gitrevio_capability_run
  { "capability_id": "estimate_portfolio_company_execution_beta", "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 Investment & portfolio choice →