Recipe catalog / forecast-confidence-wording

Grade the certainty of a financial projection

How certain is the wording of statement, a financial projection, from explicitly speculative to stated as fact?

You need to grade how confidently a projection about revenue, prices, returns, or growth is worded, so overconfident statements can be softened or disclaimed before they reach a reader.

Explore this recipe interactively · Source and implementation guide

Use forecast-confidence-wording in TypeScript

Install with npm install jev-recipes. Requires Node.js 22.9 or newer and ES modules. Set TYPESAFE_API_KEY in your server environment for live calls, which send input to TypeSafe and use API quota. See the installation guide.

import { forecastConfidenceWording } from 'jev-recipes/forecast-confidence-wording';

const result = await forecastConfidenceWording({
  "statement": "Revenue will hit $4.2M next quarter and the stock is going to double by year end. This is the bottom, so anyone waiting is leaving money on the table.",
  "minConfidence": 0.8
});
console.log(result);

Input contract

{
  "input": {
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "type": "object",
    "properties": {
      "statement": {
        "type": "string"
      },
      "minConfidence": {
        "type": "number",
        "minimum": 0,
        "maximum": 1
      }
    },
    "required": [
      "statement"
    ]
  },
  "result": {
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "type": "object",
    "properties": {
      "model": {
        "type": "string"
      },
      "usage": {
        "type": "object",
        "properties": {
          "input_tokens": {
            "type": "integer",
            "minimum": 0,
            "maximum": 9007199254740991
          },
          "output_tokens": {
            "type": "integer",
            "minimum": 0,
            "maximum": 9007199254740991
          }
        },
        "required": [
          "input_tokens",
          "output_tokens"
        ],
        "additionalProperties": false
      },
      "status": {
        "type": "string",
        "enum": [
          "ready",
          "review"
        ]
      },
      "score": {
        "type": "number",
        "minimum": 0
      },
      "level": {
        "type": "integer",
        "minimum": 0,
        "maximum": 9007199254740991
      },
      "confidence": {
        "type": "number",
        "minimum": 0,
        "maximum": 1
      },
      "probabilities": {
        "type": "object",
        "propertyNames": {
          "type": "string"
        },
        "additionalProperties": {
          "type": "number",
          "minimum": 0,
          "maximum": 1
        }
      },
      "certainty": {
        "type": "string",
        "enum": [
          "speculative",
          "hedged",
          "balanced",
          "confident",
          "asserted"
        ]
      }
    },
    "required": [
      "model",
      "usage",
      "status",
      "score",
      "level",
      "confidence",
      "probabilities",
      "certainty"
    ],
    "additionalProperties": false
  }
}

Saved example result

This hand-authored response demonstrates the contract. It is not a model accuracy measurement. Run it without an API key: npx jev-recipes demo forecast-confidence-wording.

{
  "model": "demo-fixture",
  "usage": {
    "input_tokens": 0,
    "output_tokens": 0
  },
  "status": "review",
  "score": 3.38,
  "level": 4,
  "confidence": 0.6,
  "probabilities": {
    "0": 0.02,
    "1": 0.04,
    "2": 0.08,
    "3": 0.26,
    "4": 0.6
  },
  "certainty": "asserted"
}

Evaluation evidence

Use the evaluation guide to measure this decision on your own labeled cases.

Limitations

• Grades the wording only. It does not know whether the projection is accurate, reasonable, or supported by data outside the statement.
• A statement with mixed signals is graded by its overall posture; separate distinct claims in code when each matters.
• Not a compliance or suitability determination.

Related recipes

• uncertainty-expression: Use uncertainty-expression to grade hedging in any statement, rather than specifically the certainty with which a financial projection is asserted.
• certainty-match: Use certainty-match to check whether stated confidence fits the supporting evidence, rather than to grade the wording's certainty on its own.