Rob’s Journal

[ScottMcNab]

Rotational systems need more time to give a feel for performance…5 year windows can vary much more dramatically than MRV or MOC as only getting a few data points each month…is the USMOM system you trade any good on ASX Rob ?

[RobGiles]

Scott McNab wrote:

Rotational systems need more time to give a feel for performance…5 year windows can vary much more dramatically than MRV or MOC as only getting a few data points each month…is the USMOM system you trade any good on ASX Rob ?

Hi Scott

Yes I have noticed, and expected, the variance in returns based on which 5 year window was being analysed. So what window would you use for testing a MOM system….10?

If I use the exact same rules and parameter values that my S&P500 system has on the ASX100 I get the following over the last 10 years:
CAR 2.35%
MaxDD -31.40%
MAR Ratio 0.07

vs the S&P500 system with the following metrics:
CAR 14.81%
MaxDD -20.84%
MAR Ratio 0.71

Note that the parameter values were optimised for the S&P500 system, but not for the ASX100 system yet. Are these results an indication of lack of robustness (given that they are materially different across the 2 markets) or would one expect the value of the metrics to be materially different in different markets?

[ScottMcNab]

All good q’s Rob …whether the system should be optimised to each market or work across all markets is one that I have seen different views on…best to ask Nick (my memory from when I did course was to use optimisation sparingly…only for a single key variable once ot twice a year)…and it also relates to your question on backtesting…if you are going to optimise or have a different system for each market then I think maybe you have to keep more OOS data (maybe test on 2005-2013)…if you are in the camp where the same system should work across each market then the other markets can help serve as OOS data ?

[RobGiles]

thanks Scott….you raise some good points. I’d value your insights please Nick? Does the fact that the results are poor on the ASX for my USMOM1 system render that system useless or does it downgrade the robustness score?

I’d also be interested how your MOM systems designed for the US markets perform on the ASX (and / or vice versa)….were they similar or like mine? Anyone else tried this out?

[Nick Radge]

Ideally you want to trade a longer term system across a full investment cycle. Picking a small window may prove misleading, either positively or negatively.

Assume you pick 2007 through 2010? A poor period for long only trend style systems.

[RobGiles]

Thanks Nick. I’ve looked at the USMOM through many different time periods, including the 2007 – 2010 and was happy with the results. I guess what Scott & I are asking is should we be concerned that a system’s performance is acceptable on one market (S&P500) but when applied to another market (ASX100 with exactly the same parameters and parameter values) the results deteriorate markedly?

I would have thought that stock markets in different countries, although correlated, would still exhibit very different personalities due to exchange rate influences, different mix of industries, political influences etc?

USMOM1 Backtest result for the 1/1/07 to 1/12/11 period:
CAR 7.29%
MaxxDD -30.88%
that was using a long Index MA. If I shortned the MA by 80 days it gave much better results:
CAR 11.77%
MaxDD -20.81%

but of course you wouldn’t have known this at the time, although maybe your once a year reoptimization of things like Index MA filters may have got you there?

[ScottMcNab]

FYI Rob I use the same system on all markets (for both Rotn and MRV) but I have no credibility with regards to an opinion as to whether this is a better way to go or not (ie I only have 2 systems)

[Nick Radge]

All markets are different and all markets change over time. So yes, you would use different parameters and you would adjust them on a regular (annual) basis.

[RobGiles]

Great thanks Nick.

Am delving into the ASX 100 system more today.

[RobGiles]

Hi Guys

Last night I ran my CBT exploration, ranked by ROC, and took the top 40 orders and placed them as usual. Today when I ran my backtest to compare actual with B-test fills, I was missing a fill (I got 5 the b-tester got 6 fills). The missing fill however was the 41st ranked stock on the exploration. I thought my b-testing code should only take the top 40 orders into the market but clearly it hasn’t in this case. Would be very appreciative if someone could shed some light on why this would occur.

[Nick Radge]

Just check the ranking decimals. You may have had two stocks with the same rank. You placed one and the backtester picked up the other.

If its only using two decimals, increase to 6.

[RobGiles]

Nick Radge wrote:

Just check the ranking decimals. You may have had two stocks with the same rank. You placed one and the backtester picked up the other.

If its only using two decimals, increase to 6.

Spot on Nick thank you…that was it. I am using 2 decimals & had 3 stocks with a ranking score of 101.45.

[RobGiles]

Just checking something here…..I am trading the ASX Growth Portfolio Blue Signals. I want to add diversification to my overall investments. Would i be achieving that aim by trading a momentum system on the All Ords (i.e. would you expect a lot of duplication of positions here)?

[TrentRothall]

My initial thoughts would be that you could trade the ASX 200 with your rotational system that way you are staying out of the smaller stocks that the blue signals may pick up.
I could be wrong but I wouldn’t expect there to be too many duplicates anyway because from my understanding the growth portfolio is looking for a increase in momentum to initialise a position where a rotational system requires momentum over the longer term.

[RobGiles]

Sept ’18 performance:

USMOM1 +0.42% for the month.
+7.9% since inception
This month I re-balanced my AMD Position which was 53% overweight otherwise I wouldn’t have had any cash to buy the bottom ranked position for the monthly rollover. Any thoughts on this action are welcomed (for or against, although I know there’s already been some discussion on this topic in here before).

USMOC1 +2.48% for the month
– 17.5% since inception.
Thinking of doubling my exposure to this system.

ASX Growth -0.06% for the month.
+39.5% since inception.

System development:
Still back-testing ASX momentum systems. Stating the obvious I guess, but the process has highlighted how important start date is. for e.g. you’d be fairly bitter & twisted if you’d invested all your cash in June 2007 (but less bitter & twisted than your average buy & hope investor) with my current performance stats as follows:
CAR 2.46
Max DD – 27.5%
whereas if you’d invested in this system in June ’98 to June ’07 you’d be a much happier individual:
CAR 22.34%
MaxDD -21.5%

[Author]

Posts