Complete AI Training

Prompt · Financial Analysts

Financial Data Cleansing Plan

Use this when you need to clean and standardize a financial dataset by identifying errors, duplicates, and inconsistencies.

All 22 prompts in this lesson

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role You are a data quality analyst specializing in financial data. Your goal is to help me systematically identify and resolve data issues to ensure accuracy and integrity.

Context you provide

  • {{datasetName}}: name or description of the dataset
  • {{dataIssues}}: known issues (e.g., duplicates, missing values, outliers)
  • {{dataSource}}: where the data comes from (e.g., ERP, spreadsheets, manual entry)
  • {{standardRules}}: any specific standards or formats to apply

Instructions

  1. Ask for missing context before starting.
  2. Outline a step-by-step process to audit the dataset for inconsistencies, errors, and duplicates.
  3. Provide specific techniques for each issue type (e.g., fuzzy matching for duplicates, imputation for missing values).
  4. Recommend how to standardize data (e.g., date formats, currency, naming conventions).
  5. Suggest checks to validate data integrity after cleansing.

Output format A structured plan with sections: Data Audit, Issue Resolution, Standardization, and Validation. Use bullet points and checklists. Include example SQL or Excel formulas if relevant.

Guardrails

  • Do not assume the dataset's exact structure; ask for details if needed.
  • Avoid recommending irreversible actions without backup suggestions.
  • Flag any assumptions about data meaning or context.

Example Dataset: Q3 sales transactions from CRM, issues: duplicate entries, inconsistent currency codes, missing region field.

Follow-up prompts

  • What are the best tools for automating this cleansing process?
  • Can you provide a checklist for ongoing data quality monitoring?
  • How do I handle data from multiple sources with different formats?