Share New Research 
I am quite new to Quantconnect but determined to study hard to advance quickly.
One of the issues i want clarifications on is about Technical Indicators Algorithms and Machine learning Algorithms.. Are these 2 trading methods strictly independend of each other or not. Specifically i want to know whether technical indicators such as RSI, MCAD, Bollinger bands etc can be used to develop machine learning algorithms and if so how? . Some machine learning models are Linear Regression, SVM, KNN, Logistic Regression, Random Forest, Decision Trees etc. So how can technical indicators be used in any of these machine learning algorithms if it is possible, I am a python programmer.
Please i will be most grateful for an elaborate education on this matter.
John.
Adam W
Technical indicators are typically some function of price history, whereas (supervised) machine learning is a branch of computational statistics that is most generally just training a model to find a mapping f: X -> Y where X is a vector of features and Y the targets.
Depending on the machine learning algorithm, some can benefit (either through convergence speeds or to reach a lower local minima of the loss function) by including technical indicators in the features X.
Derek Melchin
Hi John,
Some examples would include using technical indicator values for the independent variables in a regression model, the inputs to an artificial neural network, or as tests in decision trees and random forests. As a quick example, I've attached a backtest that uses technical indicator values in a regression model to predict future returns.
Best,
Derek Melchin
The material on this website is provided for informational purposes only and does not constitute an offer to sell, a solicitation to buy, or a recommendation or endorsement for any security or strategy, nor does it constitute an offer to provide investment advisory services by QuantConnect. In addition, the material offers no opinion with respect to the suitability of any security or specific investment. QuantConnect makes no guarantees as to the accuracy or completeness of the views expressed in the website. The views are subject to change, and may have become unreliable for various reasons, including changes in market conditions or economic circumstances. All investments involve risk, including loss of principal. You should consult with an investment professional before making any investment decisions.
John Addae
Hello Derek,
Thanks very much for the responese and information, i do appreciate it so much.
Please i would like you to educate me more concerning sources of tutorials and materials to obtain to use to be able to build this kind of strategies and algorithms that combine technical indicators, machine learning and Alpha. In fact help me with all resources i need to start and finish this please.
Regards
John
Shile Wen
Hi John,
The very first step is to learn how to use our platform. I strongly suggest going through our BootCamp to get familiar with our platform. Some of them cover how to use indicators, which may be helpful.
The next step in the process would be understanding Machine Learning. I personally suggest Statquest by Josh Starmer for statistical-based Machine Learning. After that, we need to learn how to use Machine Learning APIs, such as sklearn, and we provide a brief guide on how to use it in our research notebooks here.
Now to combine indicators and Machine Learning, I suggest this paper by Justin Xu Dhruv Medarametla, which incorporates a few indicators, such as Maximum, Minimum, and Simple Moving Average (called AP in the paper) with Machine Learning. Note although this is one of the easier technical papers to understand, it is may still be a challenge for beginners.
Best,
Shile Wen
John Addae
The material on this website is provided for informational purposes only and does not constitute an offer to sell, a solicitation to buy, or a recommendation or endorsement for any security or strategy, nor does it constitute an offer to provide investment advisory services by QuantConnect. In addition, the material offers no opinion with respect to the suitability of any security or specific investment. QuantConnect makes no guarantees as to the accuracy or completeness of the views expressed in the website. The views are subject to change, and may have become unreliable for various reasons, including changes in market conditions or economic circumstances. All investments involve risk, including loss of principal. You should consult with an investment professional before making any investment decisions.
To unlock posting to the community forums please complete at least 30% of Boot Camp.
You can continue your Boot Camp training progress from the terminal. We hope to see you in the community soon!