ML-Trader

• 

  model metrics

• 

  sample code

Inspiration

Being a trader, we rely the most on our intuition which is limited in order to make decisions. As part of fundamental analysis, we first arrive at an entry point (Buy of tock is done), target (Profit is taken out) and a stoploss (Minimise loss). As we cannot monitor the market every second, we would be wanting an automated trading system to make trades for us optimally.

What it does

ML-Trader is a machine learning software that can predict the optimal time to buy, sell, and keep bitcoin to maximize profits and minimize losses. It can be used by newbies who want to get into the stock market but don't have enough knowledge on how to trade.

How we built it

I used jupyter notebook along with the libraries pandas, xgboost, and technical analysis in order to train a machine learning algorithm (xgboost) to predict optimal times to buy, sell, and keep over the lifespan of bitcoin.

Challenges we ran into

I am still learning python and how package managers work so it was difficult to learn how to use the pandas library. It was also difficult for me to train a machine learning model like an LSTM or a Neural Network so instead I used the xgboost library which does a lot of work for me.

Accomplishments that we're proud of

I am proud that I was able to get such high percent accuracy and that I was able to finish this project. It was a difficult project for me because I didn't know how to use python before this project.

What we learned

I learned basic python, how to use pandas library, how to install packages with pip (python package manager) and how xgboost works. I also learned how to use git and github.

What's next for ML-Trader

Increase accuracy with better algorithms and deploy as a web application. Maybe even automated trading.

Built With

• jupyter
• pandas
• python
• scikit-learn
• technical-analysis
• xgboost