I wonder how Portfolio123 users did in 2023. It certainly was an excellent year for stock investing on the whole, especially if you used Portfolio123 to run an algorithmic strategy.
My own portfolio went up 56%. I used a little bit of margin (around 10%) and hedged with put options (around 15%). The performance was very low beta: I had only one negative month, and about half the volatility of the Russell 2000.
How did you fare?
Yuval,
Here is the performance of my Combined ETF system. I started removing the XLK/XLE screen in Sept and the last 3 months is out of sample.
I also started a crypto stock screen around the same time and here is the performance also with the past 3 months out of sample.
I will give you authorization to verify the screens under the screen name crypto3 and Combined Screen 3 in my account. (pls don’t use them to trade on your own behalf).
However, I want to mention the performance of the crypto hedge fund manager Calvin Tsai (also the crypto algo tutor for my wife).
He re-opened two new personal accounts in Binance around the beginning of 2023 (due to the change in regulations) and here is the performance trading mostly only Bitcoin and Ethereum futures based on algo/rules trading. He also maintain seperate accounts at Bybit and OKX with same positions to diversify the exchange platform risk.
EDIT : I have included the links (below the screenshots) to the performance of Calvin Tsai’s personal accounts which is updated everday. (very transparent in Binance)
Link:
Link:
There is a lot of potential for algo trading in crypto as the market is still inefficient with less (but growing rapidly) number of institutional players comparing to the US stock market. The daily trading volume of total cryptocurrency is fast approaching total US stocks.
Perhaps Yuval and Marco should consider adding this as a new asset class in Porffolio123.
Regards
James
It ended up being another good year, though I did struggle a bit in Europe. My Nordics+Germany portfolio has underperformed since the startup in 2022, so I spent some time over the summer rethinking the ranking system and extending the universe to many other European countries. From the new start in late August to the end of December I got 2% outperformance, which is fine.
In the US, where most of my money is invested, things went much better. My 20-stock portfolio returned 51%, and the 14-stock version of the same system got 61% return. Returns were good for most months except October and November, I don’t think my system likes high interest rates.
I’m very happy with the results, my model-building method is mostly based on your advice, so I want to thanks you again for your generosity!
With all due respect to ustonapc, please don’t pivot to crypto.
test_user,
Thank you for the comment.
I am interested in any new asset class that is likely to perform well without restricting myself only to the traditional asset classes.
I don’t suggest P123 members pivot to crypto but it is a good asset class to diversify the portfolio and improve risk adjusted return.
For reference, only 20% of my assets is now in crypto-related assets.
Regards
James
It was OK year for me. My own us portfolio went up by 30.25%, with SR 1.78, Max DD 7.67%. I have not used any margin and I hedged portfolio with with etfs on bonds the whole year. The performance was low beta, higher SR and lower standard deviation in comparison to IWM and VOO. I invested mostly in small stocks. So it was quite hard this year to beat SP500 but I was successful at the end.
The stocks that made me the most money were PFIE, VIRC, ALAR.
Most importantly it was a fourth in row year when I achieved higher return than iwm and voo etf.
I trade only once a month due trading restrictions imposed by my employer.
My return in 2023 was 13% (long-only in small cap stocks), a bit unsatisfying, but it was my first year of investing with Portfolio123, and I haven’t tried any similar tools before either, so I will call it a learning year. And it’s been quite exciting to learn and explore P123, by the way.
Happy New Year, Per.
Pitmaster,
Being able to trade only once a month is a big hurdle and limitation to performance (especially during period of crisis like 2007-2008 and COVID.)
Do you mind disclosing what roles and industry you are working in?
Regards
James
Yes, it is very painful for me, since I love trading:(
I’m a data scientist in a big US bank in a credit risk analytics division (non-retail PD models).
Pitmaster,
You may find this interesting.
It was sent to me a while ago about incorporating credit analytics in investing.
Regards
James
All,
Here are all of my stock ports with no survivorship bias meaning I did not start any other stock ports during this period (I do an ETF port that I have not included for diversity). I have been trading during the day. I added a port at the close for liquidity reasons as the close has the higherst trading volume of the day (generally) with little out-of-sample performance but included it to avoid any survivorship bias.
While generally consistent my port has been evolving (probably a better port now than when I started last year). The bench was the SP1500 Pure Value Index as my sim has a 0.78 correlation with this index:
.No optimizer. All statistics and machine learning except sims were used to adjust the sell rule (i.e., RankPos > X) and to find the optimal number of stocks to hold (using time-series cross-validation).
My out of sample results are consistent with my walk-forward validation of this port (including a walk-forward validation of the feature selection). Suggesting this can be a useful way to select a port and get some idea of the expected out-of-sample performance. More out-of-sample data will be necessary to drawn any definite conclusions about this.
My median port (Tuesday) has the following level of statistical significance for excess returns relative to the benchmark:
I am for whatever works and I am happy for everyone’s success. Machine learning and statistics can work. I intend to fully support @Marco in his efforts to bring machine learning to this platform (see above for support of his plan).
Jim
I started with P123 in around May, but did not invest until June/July. So my results are only for about half the year. However, my total portfolio did about 26%. Here are the P123 parts and crypto since it has been mentioned by others:
Considering my P123 portfolios are only for the latter half of the year I am looking forward to what it can do for me going forward! I did also try options hedging, but with less than 2k, and after realizing my method was not working I set it aside until I can revisit.
*Note for the cypto: while these returns look great I am still below my principle investment… 
Jonpaul,
Momentum is the most important factor investing in crypto and crypto-related assets. Never buy-and- hold crypto assets, most of them has a max drawdown of 80%+.
Pls see this screenshot from a research paper (that I sent to Jim before) comparing momentum trading between crypto and S&P 500 on different timeframes.
Regards
James
Thanks for starting the thread Yuval and for all to share.
I managed 26% across my main 4 strategies (2 US & 2 CAD). No leverage or hedging.
Certainly not bad, but I believe I could have done better (relative to previous years).
As I do not hedge, I did see a great deal of volatility (so Kudos to Yuval for only have 1 negative month).
US strategies performed notably better than Canadian strategies (35% return vs 15% US & CAD resp).
A headwind for me was Canadian exposure. I’m roughly 2/3 US, 1/3 CAD.
My Canadian strategies were/are overweight energy names, despite the general weakness in oil (and that the energy sector was the 2nd worst performing sector of 2023). I find this perplexing, as I have several momentum rules in place to avoid this, still working thru a post-mortem.
Canadian strategies also seemed lower turnover than previous years, another question I’m working thru as to the reason why.
Overall performance since 2020: 4 year CAGR of 37% which I will certainly not balk at, and have nearly 4X’d my initial capital since starting these live strategies in early 2020.
Thanks for starting this thread. My aggregate portfolio exclusive P123 returned ~13% in line with my expectations of ~15%. The P123 portfolio is constructed conservatively where at least 30% sits in cash as I sell out of the money puts for income (3% - 6% on overall portfolio).
Yuval - If you wouldn’t mind, can you please share your approach to using puts for hedging.
Hey Yuval,
When you say put options were 15% of your portfolio, are you saying the 15% represents the value of the underlying in the options or the 15% is the value of the option premium you bought, and if they expired worthless, you would be risking 15% of your portfolio?
I’d like to see what the minimum liquidity requirements and average number of positions for each of these ports. Without that, the performance seems somewhat meaningless.
Tony
Did 52% this year. No leverage. 30 positions (static)
Liquidity requirements: MedianDailyTot(126) > 50000)
Hope to get more into either short selling or put option strategies as we cannot really expect having this level of backwind this year!
You are right. Go ahead then!
Mine was easy to trade mostly but much higher initially; I increase my liquidity this year (with no results yet).
The portfolio is an IRA in withdrawal mode with a definite tilt towards limiting drawdowns. Universe is liquidity constrained NOOTC based with $200k daily median and a less than 1% spread. Policy has the cash position at 15%.
Return was 23.92% with a max drawdown of 9.07%. Sharpe is 1.13 and Sortino is 1.73. With IWM as the benchmark the beta is 0.66 and alpha is 13.02%.
A good year, cheers.
Rich
that would be useful.
BTW, is there a document or a tutorial on using AI for someone starting at the ground floor? (maybe basement 
)
