Building with AI

How to analyze financial statements with ChatGPT

You can analyze financial statements with ChatGPT if you prepare the files, ask for formulas with references, and check the results. It can help compare periods and explain changes, but your finance team should review the numbers before making decisions.

In short

  • Use three financial statements: the balance sheet, income statement, and cash flow statement.
  • Ask for formulas and source cells so you can check each metric.
  • Compare the answers with a verified spreadsheet before automating the analysis.
  • Check file permissions and retention before uploading sensitive information.

How can you analyze financial statements with ChatGPT?

Start with comparable data and finish with a review by your finance team.

  1. Prepare the files. Gather the balance sheet, income statement, and cash flow statement for the periods you want to compare. Specify the currency, scale, and sign convention. Use consistent account names and keep the original files.
  2. Check the format. The OpenAI data analysis guide lists support for .xls, .xlsx, and .csv files, as well as PDFs. Availability depends on the model, plan, and settings. Use a spreadsheet or text-based PDF when possible. Scanned tables can cause extraction errors.
  3. Ask for traceable calculations. Specify the accounts, periods, and formulas ChatGPT should use. Ask it to show the source values and cells, and flag missing data rather than fill it in. Also specify how to handle negative values and zero denominators.
  4. Check and interpret. Calculate the metrics in a separate spreadsheet and compare each result. Then ask for an explanation that separates observed changes from possible causes. Your finance team should review discrepancies and approve the conclusions.

What can you ask? An example

This example is illustrative; it doesn't describe a client. A company wants to compare its liquidity, sales, and cash generation.

The input is a spreadsheet with columns for the previous and current periods. The rows show current assets of 120 and 150, current liabilities of 80 and 100, and sales of 200 and 240. The next rows show net income of 20 and 24, and operating cash flow of 30 and 18. All figures use the same currency and scale.

You could write: “Compare the two periods in this spreadsheet. Calculate the current ratio, net margin, and changes in sales and operating cash flow. Show the formula, values, and cells. Don't invent data or causes; identify any missing information.”

The verified spreadsheet should show that the current ratio stays at 1.5: current assets divided by current liabilities. Net margin also stays at 10%: net income divided by sales. Sales rise 20%, calculated as (240 − 200) / 200.

Operating cash flow falls 40%, calculated as (18 − 30) / 30. ChatGPT can point out that net income grew while operating cash flow fell. These figures don't establish that accounts receivable caused the change. To investigate, the team needs to review receivables and the details of the cash flow statement.

A useful result includes a table with formulas and references to the source cells. If the spreadsheet and ChatGPT disagree, first check the extraction, signs, and cells used. Don't accept an explanation until you've resolved the discrepancy.

Which tool fits your analysis?

How often you do the work and the variety of files you use can help you choose.

OptionWhen it fitsWhat to check
Excel or accounting softwareDefined metrics and consistent filesFormulas, closing procedures, and review responsibilities
ChatGPT with manual uploadsOne-time analysis to explore or explain changesSensitive data, calculations, and references
Automation platformRecurring files with repetitive delivery stepsConnections, permissions, and exception handling
Custom developmentMultiple sources and controls that available tools don't coverIntegrations, evaluation, and maintenance

Cost and timing depend on file quality, required connections, and access controls. Human review and maintenance also affect the scope.

How can you measure errors before automating?

Prepare a small set of questions with answers reviewed by your finance team. Save the input files and the formulas behind each answer.

Using the example above, you can test these answers: a current ratio of 1.5, a net margin of 10%, sales growth of 20%, and an operating cash flow decline of 40%. Ask for the cells used, not just the result.

Add cases with a missing account or a zero denominator. In those cases, the expected answer should say that the metric can't be calculated. An invented number counts as an error, even if it sounds reasonable.

Run the test set before changing the system and after each change. We measure the share of correct calculations, the share with correct references, and whether the system recognizes missing data. Review conclusions that attribute causes without evidence separately.

Your finance team should set an acceptance threshold based on the risk of the intended use. If errors appear, fix the data preparation or instructions and repeat the test.

What should you check before uploading financial information?

A financial statement may contain confidential company or third-party data. Permission to analyze it doesn't mean you can upload it to any account.

  • Confirm with the person responsible for the information which files you can upload. When possible, remove names and other data the analysis doesn't need.
  • Check your plan and settings. OpenAI says it doesn't train models on ChatGPT Business, Enterprise, or API data by default. That doesn't mean data retention is zero.
  • For personal accounts, check the “Improve the model for everyone” setting. Turning it off controls use for training; also check the applicable storage terms.
  • Define who can access files and conversations. Deleting a conversation doesn't necessarily delete a file saved in the Library.
  • If you connect internal sources, validate permissions with your administrator and test access for each user profile.

What we do

Frequently asked questions

Can ChatGPT analyze a scanned PDF or an image with tables?
It can try to read them, but a scanned table or complex layout can cause errors in figures and headings. For financial analysis, use a spreadsheet or a PDF with selectable text when possible. If you only have a scan, transcribe or extract the data and check it against the document before calculating metrics.
Can ChatGPT access connected files I don't have permission to view?
Access depends on the connection, workspace settings, and source permissions. Don't assume an integration automatically follows your company's internal policy. Ask your administrator to review permissions and test different user profiles before connecting financial information.
Which model should I use to build an agent that analyzes financial statements?
No single model fits every case. First define the sources, calculations, and decisions a person will make. Then compare models using the same set of verified questions. Review errors, references, and handling of missing data, along with access and storage terms.
How can I catch ChatGPT errors in a financial analysis?
Ask for formulas, source values, and the cells used. Compare the calculations with a spreadsheet reviewed by your finance team and test cases with missing data. If a conclusion attributes a cause, ask for additional evidence. Don't publish the report or use it to make a decision until you've resolved discrepancies.
Can ChatGPT help analyze investments?
It can help organize information and prepare questions, but don't treat its answer as investment advice. Check the data against its sources and verify that it's current. Someone with financial experience should assess the risks and context before making a decision.
Message on WhatsApp