Topic 18 of 20 · Part V : Advanced Decision Intelligence

Explainability

An explanation should be faithful to the actual system rather than a persuasive story generated after the fact.

The control pattern

Data asset

Evidence, metadata and model trace data

Knobs

Provenance depth, Factor visibility, Lineage, Citation granularity, Confidence reporting, Version disclosure

Outcome

Auditable decisions and understandable scores

Measurement

See how to measure this below

What it is

Explainability shows how an output was produced and what evidence supports it. Evidence and metadata are the data asset; the depth of provenance, factor visibility, citation granularity, confidence reporting and version disclosure are the knobs.

An explanation should be faithful to the actual system rather than a persuasive story generated after the fact. For deterministic scores, expose the inputs and calculations. For model interpretations, show supporting passages, uncertainty and reasonable alternative readings.

Good explainability does not claim that a model's internal reasoning is fully knowable. It gives users the external evidence, transformations, assumptions and limitations needed to audit the result.

The knobs in detail

Each row is one adjustable property of the data asset, and what moving it tends to do.

KnobWhat you adjustLikely effect
Provenance depthHow far back the trail goesDetermines what can be audited
Factor visibilityWhich contributions are shownMakes a composite score legible
LineageWhich transformation produced the valueConnects display to source
Citation granularitySection and passage vs. homepage linkDecides whether evidence is checkable
Confidence reportingDecomposed or single numberConveys why certainty is what it is
Version disclosureWhich formula and model produced thisEnables reproduction later

Applied: Stocks Assistant

The Stocks Assistant Health Score is naturally explainable because it decomposes into Momentum, Fundamentals, Sentiment and Outlook. Display each sub-score, its weight, major contributing factors, peer group, data timestamp and formula version. A counterfactual view can answer questions such as how the score would change if outlook weight were lower, or if the company were compared only with sector peers. For earnings summaries, citations should open the exact filing section or transcript passage rather than merely link to a company homepage.

How to measure it

Evidence that the knob produced the intended behaviour, rather than shifting the problem elsewhere.

  • Explanation coverage across outputs
  • Citation validity
  • User comprehension
  • Whether stated factor contributions reproduce the displayed score
  • Confidence decomposed into source quality, completeness, extraction certainty and signal stability

Common mistakes

Post-hoc narratives that sound convincing but do not describe the actual computation.

One opaque confidence percentage where four components would say far more.