Topic 13 of 20 · Part IV : Data and Learning Operations

Feedback learning

Feedback signals are not equally trustworthy : a click may indicate curiosity rather than agreement.

The control pattern

Data asset

User reactions and expert corrections

Knobs

Feedback type, Reviewer reliability, Weighting, Recency, Context, Aggregation

Outcome

Behaviour that improves with real-world use

Measurement

See how to measure this below

What it is

Feedback learning uses reactions to model outputs as data. Explicit signals include ratings, corrections and written comments; implicit signals include whether a user opens a source, edits a watchlist, asks a follow-up, or abandons a workflow.

These signals are not equally trustworthy. Feedback type, reviewer expertise, context, freshness and weighting are knobs that determine how much influence each observation receives. A click may indicate curiosity rather than agreement, and high engagement does not necessarily mean high-quality financial guidance.

Feedback should be linked to the exact model, prompt, data snapshot and evidence bundle that produced the answer, so the issue can be reproduced.

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
Feedback typeExplicit rating vs. implicit behaviourDifferent signals mean different things
Reviewer reliabilityExpert vs. general userWeights factual corrections appropriately
WeightingInfluence per observationStops loud minorities dominating
RecencyHow current the signal isKeeps stale complaints from steering the roadmap
ContextWhat produced the answerMakes issues reproducible
AggregationHow signals combineDetects campaigns and duplication

Applied: Stocks Assistant

Stocks Assistant can ask targeted questions instead of relying only on a generic thumbs-up control. Users might flag an incorrect number, a stale source, a missing risk, a confusing explanation, or an irrelevant recommendation. Each category routes to a different fix. Domain-expert corrections should carry more weight for factual labels, while broad user feedback is valuable for clarity and workflow design.

How to measure it

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

  • Whether feedback-driven changes improve a held-out benchmark
  • Long-term trust metrics rather than short-term clicks
  • Recurrence of the specific issue that was reported
  • Rate of duplicated or abusive feedback detected

Common mistakes

Training directly on raw feedback without deduplication, abuse detection and verification.

Optimising for trading frequency or emotional engagement rather than informed decisions.