I've been using Alphalens a lot, but I had a question about implementing the Alphalens results into a successful backtest. What would be the best way to go about this (mainly regarding quantiles)?
Say I have good results from my alpha factors in Alphalens, and I want to go long/short on specific quantiles. What would be the best way to go about this?
Thanks
If the problem is only about the quantiles the answer is short and easy: the pipeline Factor class has the method 'quantiles' which does the job.
def make_pipeline(context):
[...]
factor = MyFactor(...)
factor = factor.quantiles(bins=5, mask=myuniverse)
pipe.add(factor, "factor")
[...]
def before_trading_start(context, data):
results = pipeline_output('mypipe')
longs = results[ results['factor'] == 5 ]['factor']
shorts = results[ results['factor'] == 1 ]['factor']
longs[:] = 1.0 / longs.sum()
shorts[:] = -1.0 / shorts.sum()
Thanks Luca,
So there's no disparity between the quantile outputs in Alphalens and through the pipeline? This is mainly what I was unsure about, I didn't know if there was something going on with Alphalens that I maybe couldn't see.
Both Alphalens and Pipiline Factor use pandas.qcut function to compute quantiles, but you can also let Pipeline computes the factor and run pandas.qcut on the results if you like.
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.
