Analyzing Data with GPT4: Are Data Analysts Doomed?

In this video, I’m going to show you how GPT-4 is capable of doing actual data analysis and extracting valuable insights from data. We're going to ask ChatGPT to analyze ecommerce data and make a comparison between GPT-3.5 and GPT-4.
For an overview of how to predict CLV check out this video
• Measuring Customer Lif...
▬▬▬▬▬▬ V I D E O C H A P T E R S & T I M E S T A M P S ▬▬▬▬▬▬
0:00 Introduction and overview
0:38 GPT-3.5 generates high-level insights from data
1:25 GPT-3.5 calculates AOV
1:50 GPT-3.5 is asked to return a list of orders
2:10 GPT-3.5 is asked to calculate CLV
2:55 GPT-4 generates high-level insights from data
3:40 GPT-4 is asked to put orders in a table
4:20 GPT-4 is asked to calculate CLV
5:02 GPT-4 is asked about predicting future CLV
8:40 What are the implications for data analysts?

[@4p4k]

I work at Disney. No upper management would approve sending over company data to open ai for processing. This will have to run on a local system.

[@zyvex128]

It’s gonna be easy to spin up your own open source LLM website as powerful as gpt4 in the next 6 months. AWS is one player going to benefit the most from this space.

[@angelo3108]

Another wonderful video. How long would creating this analytics app take? you made it look easy, yet again!

[@rotormeeeeeeee]

Excellent video!
👍

[@gridplan]

Doesn't this approach only take one so far? Isn't there a practical upper limit to how much raw data one can paste into the prompt?

[@OneOfTheAndrews]

I wonder how embeddings would handle this type of data for a vector database....

[@rabbitmetrics]

I'm planning to do a video about that

[@AssassinUK]

GPT 3.5 turbo has a smaller memory than GPT 4. This is why 3.5 forgot the data you gave it as it had too much to remember for the size of memory it has.

[@garygerigorian8481]

dude holy shit

[@shubhmishra66]

Every profession is crushed bro... Nothing can beat AI..
So relax, do what u can in whatver profession u r in or do some perennial business