no complex math
✅
no derivatives & integrals
✅
elementary school math
✅
plain old english
✅
no signups & newsletters
✅
everything is here
⬇️⬇️
(powered by my drawing “skills”)
This is a series of blog posts covering neural network price predictions 📈, everything from a single neuron to a more complex structure.
We will go from “do you know how to multiply 2 numbers” to building a fully-fledged AI bot that can trade LIVE using real capital.
The main idea is to go through entire process slowly and incrementally, and to build upon previous solutions. 🏗️
Even your grandma could follow along. 👵
This allows you to never be lost and/or overwhelmed. 💪
Now let’s get into the course…
Chapters / Lessons
This is optional but extremely useful. If you have any questions regarding this course, anything unclear or is missing… don’t hesitate to send a message on Discord.
1) SINGLE NEURON EXPLAINED (AI)
Showcasing how a single neuron works, its abilities and limitations. No knowledge on derivatives or integrals required. Just plain multiplications, divisions, additions, and subtractions. ＋−✖️÷
2) CRUCIAL PART OF THE NEURON (AI)
People are usually confused why this part is even needed, but without it, neurons can never learn the data properly. 🧐
3) LIMITS OF THE SINGLE NEURON (AI)
If a single neuron is so awesome then why do we even need 🧠 neural networks? Because we reach neuron limits fairly quickly.
4) MULTI-NEURON NETWORK EXPLAINED (AI)
Minimum of 3 neurons are required to vastly surpass the power of a single neuron. Training examples that were previously unlearnable are now easily handled by the neural net. 🕸️
5) SINGLE NEURON MARKET PREDICTIONS
Now we’re taking all we’ve learned and applying it to the real market. 📈 Here I’m using algo-bot starter code to backtest and verify whether a winning strategy was found or not. 🏆
6) NEURAL-NETWORK MARKET PREDICTIONS
💪 Armed with a much stronger tool (neural network), we’re going to test 🧪 it again with the same data from previous lesson and see if our trading bot improved or not. 📈📉
7) RECOGNIZING CANDLE PATTERNS USING NEURAL NETWORK
Aside from introducing a better model, we also need to provide better data. Specifically, instead of providing just a single historical candle (on which we based our predictions), we’re going to provide multiple candles. 📊
8) PREDICTING TARGET/STOP PRICES WITH NEURAL NETWORK
Instead of just predicting the next candle, let’s try to predict whether the price will reach our price target 📈 or hit our 📉 stop loss instead.
9) SEPARATING TRAINING AND TESTING SETS
So far we made our predictions on the same data we used for training. 🏋️ In reality, we cannot do that because we don’t have the future data. ⏱️
10) AI MODEL OPTIMIZATION AND NEXT STEPS…
Testing different ideas, introducing more datasets, getting the 🦡 Badger bot starter code, etc.
Finished the course?
Now you have the skills… but to multiply your productivity you need proper tools. 🛠️
(otherwise you’re just wasting time) ⏳
The Badger algo-bot starter code is much faster way to test and iterate your ideas. 💡
I personally use it (and continuously build upon it) every single day. 🏗️