Search
× Search
Saturday, April 27, 2024

Archived Discussions

Recent member discussions

The Algorithmic Traders' Association prides itself on providing a forum for the publication and dissemination of its members' white papers, research, reflections, works in progress, and other contributions. Please Note that archive searches and some of our members' publications are reserved for members only, so please log in or sign up to gain the most from our members' contributions.

Use Decision Trees in Machine Learning to Predict Stock Movements

photo

 Nitin Thapar, Content Marketing Manager at QuantInsti

 Friday, October 6, 2017

Learn how you can predict stock movements (that’s either up or down) with the help of ‘Decision Trees’ one of the most commonly used ML algorithms. http://ow.ly/VCK630fGjtP


Print

6 comments on article "Use Decision Trees in Machine Learning to Predict Stock Movements"

photo

 Peter Button, Product Management bei Nectar Financial AG

 Monday, October 9, 2017



Good post. Decision trees are powerful indeed. I pretty much built this on my webpage to demonstrate applications of machine learning for traders. You can play around with different indicators and see real results on abaca.ai


photo

 private private,

 Tuesday, October 10, 2017



Really interesting post. Thank you


photo

 private private,

 Tuesday, October 10, 2017



Interesting in particular because it shows some key weaknesses of the approach


photo

 Vitaly Khudyakov, Proprietary trader and developer of trading robots/trading algorithms (MQL4, Metatrader 4)

 Wednesday, October 25, 2017



Peter Button, unfortunetly your link (abaca.ai) don't work. Msg me correct link, please


photo

 Oscar Cartaya, Private Investor

 Sunday, November 5, 2017



Your example has 16 days worth of data and you talk about splitting the dataset into a training dataset and a test dataset. That is like 8 days worth of data for each dataset. Are you kidding me? A 16 day dataset which includes both the training and test datasets is what you are going to use in your example to predict future stock movements? How far into the future and for how long do you pretend that anything coming out of this tiny dataset will be of use for the stated purpose? Let's get real here.


photo

 Nitin Thapar, Content Marketing Manager at QuantInsti

 Monday, November 6, 2017



Hi Oscar Cartaya, We have taken data from 2010-01-01. The code snippet for the same is already shown in the blog. The excel table only illustrates the data used and the technical indicators added for prediction.

Please login or register to post comments.

TRADING FUTURES AND OPTIONS INVOLVES SUBSTANTIAL RISK OF LOSS AND IS NOT SUITABLE FOR ALL INVESTORS
Terms Of UsePrivacy StatementCopyright 2018 Algorithmic Traders Association