Build a Comparable Company Selection and Normalization Workbench

An analyst preparing a public-company valuation comparison.

Construct a defensible peer set and comparable multiples. Show why companies were included, excluded, or adjusted before presenting a valuation range.

Key: issuer_id + valuation_date + metric_definition.

Fields: price_asof, diluted_shares, enterprise_bridge, fiscal_period, reported_metric, adjustment_evidence.

Negative denominators remain not-meaningful rather than being converted into attractive positive multiples.

Document business and financial peer-selection rules.

Align measurement periods and accounting treatments.

Calculate multiples with explicit excluded-denominator cases.

Export the peer range and sensitivity to each exclusion.

A peer selection table with exclusion reasons, filing links, and leave-one-peer-out range charts.

A reproducible peer-selection and metric registry.

A comparable valuation workbook with dated market inputs.

Runnable local application, setup commands, and a dependency lockfile.

Versioned input data, data dictionary, acquisition instructions, and rights notes.

Calculation traces, source references, assumption records, and exported review artifacts.

A deterministic baseline and tests for normal, incomplete, contradictory, and failure-recovery cases.

A recorded complete workflow with a reproducible manifest and explicit limitations.

No price observation occurs after the valuation date.

Use the same denominator definition across included peers.

A negative or zero denominator does not produce a ranked positive multiple.

Every manual exclusion appears in the exported audit trail.

Keep enterprise value fixed and change the operating metric sign. A usable multiple becomes not meaningful.

The attached starter files are prototype inputs. Expected starter answers are visible. They are not independent holdouts.

Full target: Use eight issuers with dated filings and separately authorized price snapshots. Supply a frozen fictional price file if market-data rights are unavailable.

Complete target contracts and expert review remain pending. Public observations are not historical release vintages.

pandas, DuckDB, Plotly

Use an available model appropriate to the task. Record provider, model identifier, version or retrieval date, settings, cost, and latency. Use deterministic code for calculations. Models may extract, retrieve, or explain evidence. They must not invent missing records, override approval rules, or claim professional authority.

The peer set is a documented analytical choice, not an objective market truth.

No fabricated records, source citations, professional endorsements, or expert-adjudication claims.

No future-data leakage into dated decisions, model fitting, or historical valuation inputs.

No unauthorized payments, account restrictions, regulatory filings, or production changes.

No automated appraisal certification, tax-compliance determination, or unsupported fraud accusation.

No concealed uncertainty or silently invented inputs required for a numerical conclusion.

Correct domain calculations and justified methods with documented assumptions. Weight: 30.

Source lineage, temporal integrity, rights checks, and explicit synthetic-data labels. Weight: 25.

A working application with review, export, error handling, and reproducible state. Weight: 20.

Adversarial cases, uncertainty, missing-data behavior, and sensitivity analysis. Weight: 15.

Evidence-linked conclusions that distinguish facts, assumptions, and unresolved judgments. Weight: 10. Score each dimension from zero to two. Weighted score = sum(weight * score / 2). A failed safety gate blocks acceptance.