Intro
Superior algo returns can be thought of as being the result of two components: a great strategy regarding ‘what stocks to buy’ (the stock selection component, SEL) and a ‘clever timing’ (the in & out component, I/O) regarding when we are ‘in’ the market and hold the stocks versus when we are ‘out’ of the market and hold alternative assets such as bonds. We often focus on optimizing SEL and tend to neglect I/O; thus, for an important discussion of recent I/O tactics, see here.
Focus of this thread: Optimal SEL + I/O combinations
It is worthwhile to separately optimize SEL and I/O. However, the ultimate total return will also be determined by a certain synergy or dissonance between the two components. So, it seems that we won’t get around the arduous task of individually testing (all possible) combinations to identify optimal SEL + I/O pairs, which is the eventual focus of this thread. I reckon a preparatory step can be to dig up all the hidden SEL and I/O treasures from this forum and beyond to see what inputs are available for the combinations.
Ultimate objective
Let's get rich together, why not?
Nathan Swenson
I'm thinking to set up the live trading, but to use it with paper trading just to get the signals in real time. I guess it would be better if it alerts ahead of time, like at open that there will be a trade at 2 hours after open. Because this strategy has so few trades, it's easy enough to just do the trades manually. I'm thinking I'll use a small amount in futures to trade NQ and ZB pair and my TD Ameritrade self managed 401k with a more conservative setup.
Regarding the Alpha Competition, this version qualifies with 84% PSR (Alpha score). Peter, you should think about entering it. You did all the work. I'm just playing around with for consideration of using for my own accounts.
Regarding the high results above, that was without any Margin. So if you wanted to go crazy, you could add some margin to it, or simply trade non-Leverage funds but lean more on margin.
Nathan Swenson
Screen shot of the end result.
Nathan Swenson
Sorry for all the posts. Having trouble posting screen shots when working from an IPAD.
Mateusz Pulka
Tien Duy Vo Peter Guenther
I have spotted this bug also, the problem is here (the loop is run outside the if statement):
if not self.be_in:
# Close 'In' holdings
#for asset, weight in self.HLD_IN.items():
# self.SetHoldings(asset, 0)
#for asset, weight in self.HLD_OUT.items():
# self.SetHoldings(asset, weight)
wt[self.STKS] = 0
wt[self.TLT] = .5
wt[self.IEF] = .5
# Thomas's reducing unnecessary trades
for sec, weight in wt.items():
cond1 = (self.Portfolio[sec].Quantity > 0) and (weight == 0)
cond2 = (self.Portfolio[sec].Quantity == 0) and (weight > 0)
if cond1 or cond2:
self.SetHoldings(sec, weight)
The for loop will be fire every time even if we set self.be_in to false. The correct version is:
if not self.be_in:
# Close 'In' holdings
#for asset, weight in self.HLD_IN.items():
# self.SetHoldings(asset, 0)
#for asset, weight in self.HLD_OUT.items():
# self.SetHoldings(asset, weight)
wt[self.STKS] = 0
wt[self.TLT] = .5
wt[self.IEF] = .5
# Thomas's reducing unnecessary trades
for sec, weight in wt.items():
cond1 = (self.Portfolio[sec].Quantity > 0) and (weight == 0)
cond2 = (self.Portfolio[sec].Quantity == 0) and (weight > 0)
if cond1 or cond2:
self.SetHoldings(sec, weight)
The same should be applied in second if statement.
Mateusz Pulka
Sorry some kind of formatting problem. Generally the for loop should be move inside the if statement as Tien Duy Vo pointed out when algo starts and be_in paramter is true we will buy long and short at the same time.
Nathan Swenson
I'm sorry, I don't know Python. I don't see any difference between your code blocks. Is this mistake resulting in inflated results due to margin usage?
Edit: Didn't see your last response. I will wait for a Python coder to update it. I only know C#.
Mateusz Pulka
Sorry for formating problem. The code should look like this:
https://pastebin.com/cnKm9BVYinstead of this:
https://pastebin.com/pPcGFKR0Nathan Swenson
So the issue pointed out by Gpw radar and Tien Duy Vo only occurs if "be_in = true" at the time of start. I don't see any issues with my order when ran from 2008 to 2020. It would seem that the results for mine are correct. I was worried that the results were invalid.
Tien Duy Vo
gpw radar : Thanks for pointing out. Great job. Unfortunately, the backtesting framework on Quantconnect seems to be much slower than on Quantopian. It is quite difficult to debug that way.
There is another issue related to this part of the code:
self.Schedule.On(
self.DateRules.EveryDay(),
self.TimeRules.AfterMarketOpen('SPY', 120),
self.rebalance_when_out_of_the_market
)
self.Schedule.On(
self.DateRules.WeekEnd(),
self.TimeRules.AfterMarketOpen('SPY', 120),
self.rebalance_when_in_the_market
)
Here, the algo is firing the two functions rebalance_when_out_of_the_market and self.rebalance_when_in_the_market, which is responsible to get "in" and "out". However, you can see that one is started every day and the other one at weekend. I wonder, whether this is done on purpose.
Mateusz Pulka
You are right Nathan Swenson it only occures once at the begining when you start algo and when flag in is set to true. For example check out your orders when you set the star date at 1st January 2018. It is not a big deal but worh to fix it.
Mark hatlan
Great work! This market timer does a really nice job.
However TQQQ does do way better than SPXL. SPXL starts on 11/03/2008. UPRO starts on 6/28/2009. TQQQ starts on 2/7/2010. When switching the start date to 2/7/2010 here are the returns:
SPXL +7,552%
UPRO +7,180%
TQQQ +19,859%
I think SPXL only looked better because of the earlier first trade date.
Nathan Swenson
Thanks Mark! Good point!
Aalap Sharma
Relativily new to all this and I would really like to know are these returns realistic in the real markets? Has anyone deployed such algos to the market and seen healthy returns. Just curious...
Nathan Swenson
Aalap, I just turned the algo on and entered TMF. We shall see soon enough. I'm going very aggressive with leveraged products. It should be very realistic as it only trades about 10 times a year with trades just 2 hours after RTH market open. Algo is entirely in treasury bonds at the moment.
Aalap Sharma
Cool! I was thinking the same :)
Mateusz Pulka
Hi Guys,
I have added some improvments to the code and please noticed the result. So first algo has improvment in terms of open the trade at the begning of the cycle when we start the algo. The return for 2010-2020 is: 16 772%
Mateusz Pulka
The second run contains the following improvement. I just want to generate a signal about in/out just right after the open market. But open position just in the same way as the original algo. What is surprising the result is 21 011%. I am a little bit surprised about this, to be honest. Any idea where this difference comes from?
Nathan Swenson
Gpw Radar, I see it takes more trades when you check signal at open. Perhaps it's due to increased volatility at open which is more likely to trigger needed deviation. The 2 hours after close is actually European market close for which there is often a ramp up in index price. I had thought about messing around with that as even 5 minutes makes a difference in that period. I know 2hrs and 5 min is significant. The timing of entry vs exit and asset type all matter. Bonds seem affected more at open, mid day, and close, while 2hr after open seems more significant for equities. Lots of opportunity for improvement I believe with timing alone.
Mateusz Pulka
please notice that I only generate a signal in/out 1min after the market is open and then after 120min I open the position base on the signal. I have noticed that as I used IB with the cash parameter some of the orders were not filled (lack of money) and the order was later sometimes even 5 days later.
Peter Guenther Have you tried to use futures instead of etf to generate the in/out signal?
https://finance.yahoo.com/commodities?.tsrc=fin-srch
Nathan Swenson
Gpw, perhaps the delayed order in due to transaction order. I often see that the buy order is executed before the sell order for prior holdings. This probably needs to be fixed.
Peter Guenther
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 QuantConnect. In addition, the material offers no opinion with respect to the suitability of any security or specific investment. QuantConnect 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. All investments involve risk, including loss of principal. You should consult with an investment professional before making any investment decisions.
To unlock posting to the community forums please complete at least 30% of Boot Camp.
You can continue your Boot Camp training progress from the terminal. We hope to see you in the community soon!