Good morning everyone,
Yesterday we published the first tutorial in a planned series to follow, geared exclusively towards providing a detailed introduction to a typical Quant’s workflow and approach to algorithmic trading strategy development with the DARWIN API.
If you’ve ever wondered how we conduct alpha research in Darwinex Labs, this tutorial gives you a rich bird’s eye view of the process, including everything from process to source code
If you’ve ever used any assessment criteria at all for selecting DARWINs, this tutorial shows you how you can quickly backtest your ideas in Python using the DARWIN API.
Finally, it also caters to algorithmic traders at different levels of Python fluency - regardless of where you think you stand in terms of ability to code strategies, this tutorial also serves as a crash course in Python for Algorithmic Trading
It is structured as follows:
1) Developing a hypothesis
2) Assessing data requirements
3) Creating the required dataset
4) Generating hypothesis factors
5) Calculating strategy returns
6) Evaluating results
7) Running statistical tests e.g. what is P(μ != 0) ? (we’ll cover this in detail in future tutorials)
Source code is pre-written for you at each step, available in the DARWIN API Tutorials GitHub repository.
For this tutorial we’ve presented everything in a Jupyter Notebook, making it much simpler and more interactive to follow the tutorial - please click on the following link to open it in your web browser:
If you find any Darwinex content useful, ** please hit the LIKE button on YouTube **, and share it on your social networks if possible
As you know, Darwinex lives and breathes referrals.
Your support in the form of likes and shares on YouTube will go a LONG way, as YouTube’s algorithms are geared towards referring content to a larger base of relevant users when they observe engagement from existing communities.
The more eyeballs we get, the more Darwinex grows, the more serious individuals like you who join the #tradermovement