Learn by Directing AI
All materials

quality-assessment-template.md

Data Quality Assessment

1. Data Overview

Describe the data source, date range, total row count, and a brief summary of what the data contains. List the key columns and their types.

Field Value
Source
Date range
Row count
Key columns

2. Quality Issue Classification

For each quality issue discovered during profiling, classify it and assess its business impact.

Categories:

  • Fixable -- can be resolved with a clear transformation (e.g., standardize casing, parse dates)
  • Flaggable -- requires investigation or a decision before proceeding (e.g., unexpected patterns, potential data entry issues)
  • Blocking -- prevents reliable analysis until resolved (e.g., primary key violations, impossible values in critical fields)
Issue Category Evidence Business Impact

3. Business Impact Summary

Translate the technical findings into business terms. What do these quality issues mean for the analysis? Which findings affect which metrics? Write 2-3 paragraphs that a non-technical stakeholder could understand.

4. Recommendations

Prioritized list of actions. For each recommendation, state what to do, why it matters, and whether it should be done before or during the analysis.