My simple 3-step process for analyzing data with ChatGPT

A Beginner's Guide

Hey Warrior,

We have another guest post for you today.

My friend Jerry is the founder of Workwiz and writes the Workwiz AI Newsletter. He shares AI tools and tips on how to work smarter with AI every week.

I’m really excited to have Jerry contribute to The Prompt Warrior with today’s post about data analysis using AI.

I’ll let Jerry take it from here…

Data analysis is a great use for AI. It can quickly go through big amounts of data, and provide a helpful and clear analysis with generated charts—pretty much instantly.

However, it’s often done wrong. It requires a different kind of approach compared to how you would normally do it. 

In this tutorial I’m going to cover how you can do data analysis with ChatGPT by turning any kind of data into a complete analysis and saving tons of time in the process. 

Before we get started

In this mini-guide I’ll be working with ChatGPT plus. If you don’t have ChatGPT Plus, then is a great free alternative. It uses the same technology as GPT-4 and is designed for data analysis.‍

If you want to follow along and you don’t have a dataset to analyze, you can download this example survey here. This dataset consists of sample data from a customer satisfaction survey that we want to analyze.

Let’s pretend that we want to learn how satisfied customers are on different tiers, and how we can improve that.

Clean data

To make data analysis work with AI you need clean data. If you upload a random file and expect a complete analysis, then it won’t work.

What clean data is to AI:

  • Clear and consistent headers: The first row should contain headers, which are the names of each column. These names should be clear and consistent. 

  • One row per record: Each row in the data file should represent a single record or data point (for example one customer). 

  • Raw data: It should avoid any modifications like including subtotals, summaries, or cells with formulas in your file.

❌ This won’t work

✅ This will work

Most of the times when you export data from a tool you already have the raw-data that already meets the criteria above.

If this is not the case then this is the only manual type of work you need to complete first. ChatGPT can do some data cleaning by removing empty rows or meta-data, but it won’t be able to turn a highly formatted sheet into a clean one.

Analyzing the data with ChatGPT

Step 1: Let ChatGPT describe the contents

To start the analysis, upload your file to ChatGPT and simply start by asking “Read this dataset and describe its contents”.

In this step we want to know if ChatGPT can open the file and understand the contents of the file.

Once everything looks good and it has a solid understanding of your dataset, we can continue to the next step.

Step 2: Exploratory Data Analysis

Now we are getting serious and start entering the domain of data scientists as we are going to do an Exploratory Data Analysis (EDA).

This is an important step in data analysis as it will help you spot trends, unusual bits, and interesting connections in your dataset.

‍Luckily we don’t really have to know how this works, we can simply instruct AI to do it for us.

“Start with an exploratory data analysis of the file I’ve attached.”

You'll get a detailed summary of your data. This summary will already provide high-level insights by summarizing important findings, patterns, and features in your data.

It can even find ways to clean your data and continue to do so by removing e.g. empty rows and meta-data. 

Step 3: Deep dive

With our data now clean and checked for quality, we're ready to start with the most exciting part: the deep dive analysis. This is where we start asking targeted questions to get to practical insights. 

To complete our objective to figure out how happy customers are with our different levels of service, we can start asking this question:

“How do satisfaction scores vary among Basic, Plus, and Enterprise tiers? Also visualize your findings.”

And it doesn’t limit to flat text, it can even visualize all your findings in charts. 

The satisfaction score for large enterprises is a lot lower than the other service tiers.

As pointed out by ChatGPT and seen in the chart it’s clear that customer service is the main problem that scores significantly lower than the rest.

Step 4: Analysis into action

Now that we have identified a problem, we can work on a solution. The great thing about ChatGPT is that it can go from data analyst to business consultant instantly.

To find a solution we can ask ChatGPT (within the same chat) on a solution:

“Based on the findings of the dataset, what ideas do you have to bring our satisfaction-score up within the enterprise tier?”

And as expected the main focus is on the customer service, the culprit that we identified with our analysis.

From this point onwards you can dive deeper into the solutions with ChatGPT, but that falls outside the scope of this analysis.

Wrapping it up

I hope that was helpful and you enjoyed this guide!

If you would like more practical AI solutions to work smarter with AI, consider subscribing to my newsletter. 


What did you think of today's email?

Your feedback helps me create better emails for you!

Login or Subscribe to participate in polls.

See you in the next one!

P.S. Whenever you’re ready, here are two ways I can help you:

  1. Get your product in front of 20,000+ solopreneurs, business owners and professionals. Sponsor this newsletter here.

  2. You’re a maker, content creator or solopreneur and want to accelerate your product growth? Pre-order my AI Growth Kit here.

Join the conversation

or to participate.