New Strategy in my Research Group
https://www.portfolio123.com/app/group/317/home
Here we go (click on live strategies in the group to find it).
Ranking System —> Core: Sentiment
+ I added some stuff (last three nodes!)
Backtest of the above Ranking System (on Russel 3000):
In general:
I almost always use out of the box stuff from P123 and then add ideas, tweak it to my risk profile. My best ranking system that I use (and do not publish) comes from a research group that worked > 10 years for it (and I was mainly learning from the research group, I could not contribute much).
I would say 80% of my systems come from working together with research groups and using standard stuff (which is built by very experienced Quant from P123!) from P123.
This way you are much faster than if you start from scratch.
I see too many users trying to start from scratch, it gets hard fast, people get frustrated and give up.
Yes, I also know new investors (one 35-year-old Math PHD, CEO of own Software Firm based on Big Data, Statistics and AI, so perfect background!) that start from scratch and are super-fast. But not everybody (certainly not me!) has that background, this is the exception.
Also, if you build something, ask yourself, is it beating standard stuff? No reason to just trade your own strategy, if (free!) standard strategies would outperform (or did outperform your backtest out of sample) or would fit better to your risk profile.
This week I had a chat with a young person (25 years younger than me!) writing a thesis on AI. Guess what, he knew 10 times more about that stuff than I do, I learned a ton. He explained the Machine Learning Algos to me P123 has out of the box to me. Strengths and weaknesses of each ML Algo. I learned that theP123 Ranking systems treat ranks linear (still the right tail can be captured!), but (some) Machine Learning Algos might find nonlinear stuff. Reach out, collaborate.
Sorry for the rant, but I see too many people going in the wrong direction.
We all do it, at the end we all trade stuff that has been documented by 1000s of Academics (which they picked up from practitioners, e.g. investors / traders in the first place!). We all trade the big 6-8 Factors: Quality, Momentum / Trend (with or without relative strength), Value, Growth, Mean Reversion, Size, (low) Liquidity (on the stock or aggregated on Subindustry, Industry, Subsector or Sector / Theme). Gun to my head (almost) nobody finds new stuff, the question is do you have the (clean Point in Time) Data fast enough and how you express the above 6-8 factors and how do you use the advantage of small assets under management (e.g. a sub 1 million account ;-))
_________________________________________
Example:
The same with this strategy (build it based on suggestions of a user via a support Question):
…with just one ranking node on relative strength in the ranking system:
Now the same system (with buy and sell rule ideas from the user that I will not show) with the Core: Momentum Ranking System (out of the box from P123!!!)
So here is the same system with the Core: Momentum Ranking System —>
The idea from the user was super great (I definitely learned a ton!) but combined with some standard stuff from P123 we got to a very good point in the strategy design very fast.
My take: use what P123 has out of the box or is in research groups, test it, expand it, combine it.
All the best and best regards.
Andreas
____________________________________________
The information on from Andreas Himmelreich / QuantStrike and this video / blog is for information and discussion purposes only. It does not constitute a recommendation to purchase or sell any financial instruments or other products. Investment decisions should not be made with this video, and one should consider the investment objectives or financial situation of any person or institution.
Investors should obtain advice based on their own individual circumstances from their own tax, financial, legal and other advisers about the risks and merits of any transaction before making an investment decision, and only make such decisions based on the investor’s own objectives, experience, and resources.
The information from Andreas Himmelreich / QuantStrike and this video / blog is based on generally available and paid information and, although obtained from sources believed to be reliable, its accuracy and completeness cannot be assured, and such information may be incomplete or condensed. All performance results are hypothetical and the result of back testing only. Out-of-sample performance may be different. No claim is made about future performance.
Investments in financial instruments or other products carry significant risk, including the possible total loss of the principal amount invested. Andreas Himmelreich / QuantStrike and this video / Blog do not purport to identify all the risks or material considerations which may be associated with entering any transaction. Andreas Himmelreich / QuantStrike and this video / blog accepts no liability for any loss (whether direct, indirect or consequential) that may arise from any use of the information contained in or derived from Andreas Himmelreich / QuantStrike and this video / blog.