I Built a Trading Bot with ChatGPT
The GPT Trader is a trading bot that I built with chat GPT and I want to show you how to use this with the live trading. At the end of the video did I make money with my two thousand dollar investment or did I lose. money find out at the end. Let's start with our first question for chat. GPT what are the best techniques to be using here so let's ask it that. What are 10 of the best machine learning techniques for stock prediction. We're going to use the scikit-learn library to make a statistical model called a neural network. It's using the Yahoo data set of past stock prices to make predictions Based on data it's using a CSV file the CSV file is not coming from anywhere it's just assuming that we. have this data so what we are going to have to do is try to compile this in a in a code window and see what this does. for us and as you can see it's telling us what this code does so. let's take all this code and run it with the python command now what do you think is going to happen. any guesses instead of just installing these why don't we ask chatgpt for the requirements dot txt5 what does the requirements.txt file. look like look like for the previous code so all those dependencies it's going to give it to us look like. We've got to install tensorflow and there's a way to install Tensorflow so we'll go back to the source code and remember that we're working with CPT for a better data source. CPT is not a perfect coder but it's giving us a scaffolding.olding. CPT isn't a perfect but it is a good enough tool for us to work with. We can just copy that and we can just create a new requirements.pi file and once we've done that we can run that as pip installs. pip install we can do a new app. We'll call it stockprediction.pi in stock prediction and it's immediately going to do that it knows that. this is referring to a. neural network it knows to use Keras on top of that number six is neural network. and it knows the next question is show me a python. web example of using a of using that to predict the price of Yahoo stock. Let's just pick a stock and we're immediately going on that it's Immediately going to doing that it know that. It knows that it's. using the scipy-learnlibrary to make an analysis of past data that is. spread out across the time domain but the most popular one are neural networks that's. what everything is based off of these days deep learning so let’s pick number six.Let's ask chat gbt another question because remember chat EBT unless unlike other AIS is able. to remember the context so let't ask it the next questions. I can say XG boost. is a way of improving predictions on the popular website kaggle I can says that. time series analysis that's a technique to making predictions based on past data. I'll give you a little brief uh preview of what's happening it's used to improve predictions on a popular website. I'm going to explain this to you later. I've got the alpaca dashboard and I'll. explain this and I'm using test data so using testData I. was able to made predictions on different stocks including spy and Nvidia and chat G PT. helped me build this bot now that's just using paper trading. I will show you. how to used this with live trading and that's what I'm calling it once we. log into this app we can see that I've been able to use it to make the predictions. We have all of our dependencies right so it's doing that and I've done a new code that I'll explain this. We are now going to go back and we'll use that to run that and then we can use the code that we just created to run the app. I guess it's not perfect what we're learning is chat gPT clearly isn't perfect what's not going to work because the data isn't legit so I guess we're not working off the source data so I'll ask CPT to help us get a better source of data so we're back to working on a better code for this code we're going back to remember that this code that's working for us. I hope you'll all have a better understanding of the data that's already working for CPT. I want you to try and use this code to make better stock prediction predictions. You can find out what's going on in the video at the bottom of the page. The video is based on paper trading and I will explain it to you in more detail later.