Quantopian's community platform is shutting down. Please read this post for more information and download your code.
Back to Community
Feature matrix generation with future price
Abdulla Al-Qawasmeh
posted Jun 21, 2016

Hello,

I'm new to Quantopian. I'm trying to build a feature matrix to run machine learning in a supervised manner.

The features can be anything relating to a stock in a trading day (fundemantal and/or technical). For example, some features can be high, low, close, market cap, PE ratio. Based on these features, I want to make a prediction on how high the price will be three calendar months in the future (the label).

What's the best way to go about what I'm trying to do?

I already know how to generate the features using a daily scheduled function that accumulates the features in a pandas dataframe (let me know if there is an easier way to generate the features). However, I do not know how to query for a stock price three calendar months in the future.

I don't think what I'm trying to do is untypical, so I'm sure some of you folks have tried to do something similar and I want to learn from your wisdom.

1 response
Luca
Jun 21, 2016

How do you generate the features using a daily scheduled function? Are you talking about research environment or backtesting?

I would suggest to code each feature calculation as a pipeline factor, so that you can easily swap them between research and backtest environment. Also you might have a look at factor tear sheet. That's not related to machine learning but it is used to analyse the ability of a pipeline factor (or a feature in your case) to forecast price change. That NB would show you how to use Q API to conduct your own research and I am pretty sure you might reuse lots of the code in there.

About Quantopian
Careers
Community
Events
Documentation
Academia
Lectures
Status
Facebook
Twitter
LinkedIn
YouTube
Terms of Use
Privacy Policy

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 Quantopian.

In addition, the material offers no opinion with respect to the suitability of any security or specific investment. No information contained herein should be regarded as a suggestion to engage in or refrain from any investment-related course of action as none of Quantopian nor any of its affiliates is undertaking to provide investment advice, act as an adviser to any plan or entity subject to the Employee Retirement Income Security Act of 1974, as amended, individual retirement account or individual retirement annuity, or give advice in a fiduciary capacity with respect to the materials presented herein. If you are an individual retirement or other investor, contact your financial advisor or other fiduciary unrelated to Quantopian about whether any given investment idea, strategy, product or service described herein may be appropriate for your circumstances. All investments involve risk, including loss of principal. Quantopian 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.