Auto-Pilot Disengaged – August 8, 2011

[ATTACH=CONFIG]9707[/ATTACH][ATTACH=CONFIG]9705[/ATTACH]

[ATTACH]9706[/ATTACH]

The IWM Robot is now totally out of any reasonable and reliable historical statistics samples available. There is no way we can allow to put our capital at risk based on blind following of the contradictory ST/LT signals, especially in presence of a dangerous exponentially expanding volatility.

Consequently, Pascal and I jointly decided to switch-off the auto-pilot and to leave the robot in cash until further notice. Starting on Monday, statistics will be published as usual on the robot page, but the signal will be to stay in cash whatever the apparent edges. Dark clouds and storms abound ahead of the market and the traffic controllers are blocking all passengers on the tarmac for survival and safety reasons.

Not only is the robot out of statistical bounds, but more ominously, the 20 DMF itself is now in unknown territory. Pascal will comment on how one can try to pilot “manually” a plane under such conditions with the various tools from the EV website.

My own view is that it is crazy and pure gambling to even try boarding any plane now. Do you remember the old discussion we had about the “Holy Grail of Trading” actually being patient and taking only the highest probability setups? Now is the time to relax in cash until reliable strong edges are back in play and everybody else end up ruined, depressed and exhausted.

Below are the multi-pivots charts of IWM, SPY, QQQ and GDX for your review. They currently all require no other commentary than that Yearly Pivot (YPP) is the key support/resistance and equilibrium for all of them. With the exception of a neutral SPY, they are all under heavy floor selling pressure from the resistance clusters.
Billy

[ATTACH=CONFIG]9703[/ATTACH]
[ATTACH=CONFIG]9708[/ATTACH]
[ATTACH=CONFIG]9709[/ATTACH]

[QUOTE=Billy;15431][ATTACH=CONFIG]9707[/ATTACH][ATTACH=CONFIG]9705[/ATTACH]

[ATTACH]9706[/ATTACH]

The IWM Robot is now totally out of any reasonable and reliable historical statistics samples available. There is no way we can allow to put our capital at risk based on blind following of the contradictory ST/LT signals, especially in presence of a dangerous exponentially expanding volatility.

Consequently, Pascal and I jointly decided to switch-off the auto-pilot and to leave the robot in cash until further notice. Starting on Monday, statistics will be published as usual on the robot page, but the signal will be to stay in cash whatever the apparent edges. Dark clouds and storms abound ahead of the market and the traffic controllers are blocking all passengers on the tarmac for survival and safety reasons.

Not only is the robot out of statistical bounds, but more ominously, the 20 DMF itself is now in unknown territory. Pascal will comment on how one can try to pilot “manually” a plane under such conditions with the various tools from the EV website.

My own view is that it is crazy and pure gambling to even try boarding any plane now. Do you remember the old discussion we had about the “Holy Grail of Trading” actually being patient and taking only the highest probability setups? Now is the time to relax in cash until reliable strong edges are back in play and everybody else end up ruined, depressed and exhausted.

Below are the multi-pivots charts of IWM, SPY, QQQ and GDX for your review. They currently all require no other commentary than that Yearly Pivot (YPP) is the key support/resistance and equilibrium for all of them. With the exception of a neutral SPY, they are all under heavy floor selling pressure from the resistance clusters.
Billy

[ATTACH=CONFIG]9703[/ATTACH]
[ATTACH=CONFIG]9708[/ATTACH]
[ATTACH=CONFIG]9709[/ATTACH][/QUOTE]

Billy and Pascal,

May I be the first to say thank you for this black and white guidance. Worth every penny of my subscription costs. I am safely in cash and will remain so for however long. (Apart from a very small amount of cash for daytrading to keep me awake and alert) !

Trev

Pascal and Billy,

I would be VERY interested to understand how the trading patterns of 2011 differ statistically from those of 2008. Without any analysis to back this up, my gut feel says the markets were extremely chaotic back then just as they are now. How did the Robots react to price discovery back then and why?

For what it is worth -- I totally agree with you Billy. This is no robot time or even (swing)trading time. Wait on the sideline with a Margarita is the best we can do.
My signal to re-enter is a hourly VIX in a down trend. You will see the vix starting to make lower hourly highs (over the coarse of several days!!!), that for me is the signal to seriously start looking for a long entry and for short vega trades.

Anything till then is done in small size with the mindset of a day trader.

[QUOTE=adam ali;15433]Pascal and Billy,

I would be VERY interested to understand how the trading patterns of 2011 differ statistically from those of 2008. Without any analysis to back this up, my gut feel says the markets were extremely chaotic back then just as they are now. How did the Robots react to price discovery back then and why?[/QUOTE]

Adam,

This is at the source of the statistical reliability problem. The 20 DMF was in confirmed shorting mode during all of September 2008 and had its first market direction signal change with a cover your short/buy signal on October 10, 2008. The robot did manage the trade well because it was looking for short positions durring all of that time Currently, the 20 DMF is already in unprecedented oversold territory and waiting for a long signal. Under such circumstances, the robot decides independently of the 20 DMF, and based on ST/LT statistics, whether to go long or short. But because the database only has a very few ST/LT combinations similar to today's, this is the exception to the rule that should be applied instead.
We are also in a typical volatility expansion environment that can quickly lead to 5-6% daily intraday moves for IWM. Because the robot is an EOD system and the risk management is based on a rising but lagging ATR% of +/-3% daily volatility, any setup coul actually proved to be a winner EOD but would probably be stopped out many times during the day.
Billy

billy

could the Robot be adjusted further to include day trading setups, I mean, the wild swings in this market is a day trader dream (60+ points) ?, or is it just designed with EOD data only and is not capable of intra daily data ??.
thank you

[QUOTE=hmatar;15439]billy

could the Robot be adjusted further to include day trading setups, I mean, the wild swings in this market is a day trader dream (60+ points) ?, or is it just designed with EOD data only and is not capable of intra daily data ??.
thank you[/QUOTE]

Hmatar,
Experienced discretionary day traders are the only ones who can expect to make a good performance and they are the only ones who should be hyperactive instead. I confess that I will try to be in that camp too.
An intraday robot can only be developped with the availibilty of a real-time 20 DMF which is still under development. It is an extraordinary technical challenge to finalize due to the millions of data to process and repeat every minute.
Billiy

thank you billy, looking forward already for intraday Robot, hope you guys can handle the ton of data and able to produce such a gold mine...good luck

[QUOTE=Billy;15438]Adam,

This is at the source of the statistical reliability problem. The 20 DMF was in confirmed shorting mode during all of September 2008 and had its first market direction signal change with a cover your short/buy signal on October 10, 2008. The robot did manage the trade well because it was looking for short positions durring all of that time Currently, the 20 DMF is already in unprecedented oversold territory and waiting for a long signal. Under such circumstances, the robot decides independently of the 20 DMF, and based on ST/LT statistics, whether to go long or short. But because the database only has a very few ST/LT combinations similar to today's, this is the exception to the rule that should be applied instead.
Billy[/QUOTE]

Billy, I'm copying my recent comment to the analogy made by Ivan Hoff on another thread:

[QUOTE=TraderD;15437]I'm somewhat puzzled by the analogy. The robot reportedly cruised fine through the Fall of 2008 and didn't have to go to cash every night. Why is there a manual override now? Is this possibly a symptom of an over-optimized trading system (relative to available backtest/analysis historical data)?
Trader D[/QUOTE]

The rather simple-minded observation I have (admittedly, in complete hindsight) is that if the robot didn't include the ETF confirmation criterion (in its specific incarnation), we would be now in a rather impressive short swing trade and AFAICT a manual override into cash wouldn't happen, is that correct? If that is indeed the case, wouldn't you be inclined to think that the ETF confirmation is an over-optimized component of the robot? Would it make sense to go back and reduce the number of parameters tweaked in the robot setup to achieve greater consistency at the likely expense of lower overall return?

Trader D

Billy and Pascal,

Back in fall of 2008, the 20DMF issued a sell signal. Am I correct in understanding that signal didn't require confirmation from the inverse ETFs, which only came into play when the Fed entered the market through its POMO?

Also, in October 2008, the 20DMF gave a buy signal. In between the time it was short and then long, did the 20DMF fall into the pattern we're experiencing today, i.e., deeply oversold but not yet in buy mode? In other words, was it in cash?

If so, then the Robot backtest would have the Robot seeking a trade based solely on the LT/ST stats. Are those stats quite different than what we're seeing today? Did the Robots seek trades then or was it in cash?

I do understand and agree that relying on relatively few data points to trade the Robot makes no sense. My questions are more to gain a greater perspective on the contrast between 2008 and now in terms of the EV system.

[QUOTE=adam ali;15446]Billy and Pascal,

Back in fall of 2008, the 20DMF issued a sell signal. Am I correct in understanding that signal didn't require confirmation from the inverse ETFs, which only came into play when the Fed entered the market through its POMO?

Also, in October 2008, the 20DMF gave a buy signal. In between the time it was short and then long, did the 20DMF fall into the pattern we're experiencing today, i.e., deeply oversold but not yet in buy mode? In other words, was it in cash?

If so, then the Robot backtest would have the Robot seeking a trade based solely on the LT/ST stats. Are those stats quite different than what we're seeing today? Did the Robots seek trades then or was it in cash?

I do understand and agree that relying on relatively few data points to trade the Robot makes no sense. My questions are more to gain a greater perspective on the contrast between 2008 and now in terms of the EV system.[/QUOTE]

Adam, Pascal may correct me if I'm wrong, but from my backtesting files, the short signal in September2008 was
confirmed very early by the TEV extension of the inversed ETFs even without POMO back then. Thereafter, until October 2008, all ST/LT settings have been SHORT and STRONG SHORT, never NEUTRAL and even less LONG NEUTRAL like today.
There is absolutely nothing comparable between the 20DMF signals and LT/ST settings in September 2008 and today. We can therefore legitimately expect that the outcome could also be very different than 2008.
Billy

[QUOTE=TraderD;15445]Billy,
The rather simple-minded observation I have (admittedly, in complete hindsight) is that if the robot didn't include the ETF confirmation criterion (in its specific incarnation), we would be now in a rather impressive short swing trade and AFAICT a manual override into cash wouldn't happen, is that correct? If that is indeed the case, wouldn't you be inclined to think that the ETF confirmation is an over-optimized component of the robot? Would it make sense to go back and reduce the number of parameters tweaked in the robot setup to achieve greater consistency at the likely expense of lower overall return?

Trader D[/QUOTE]

It is true that not including the confirmation would have made a killing in the recent series of trade, but would have significantly deteriorated the robot performance in previous series of trades. It is only in hindsight that Pascal could make the discovery that confirmation improved performance during POMO periods but hindered it out of POMO periods. This information is obviously now seriously considered for inclusion in the robot rules and very likely will be in the future.

A manual override in cash would have happened anyway for new entries and the robot would already have covered its initial short position.

Now, let me kindly notice that if we change the rules after each losing trade, the robot will lose its objectivity and utility. Pascal is running new mixes of rules in backtests 24/24 with the latest observations mixes since a few days now to make sure of optimal necessary rules adaptations.

Billy

Thanks, Billy, for the great feedback.

I'm no statistician but I do wonder at what point we can truly test a sufficient number of scenarios that we feel comfortable dipping our toe in the water again. Without sounding melodramatic, I think it's fair for me to be concerned that a similar situation to what just occurred (i.e., a 20DMF signal overridden with the outcome being a series of Robot trades that were stopped out), could happen again. In other words, not knowing what I don't know is an uncomfortable position to be in, and I don't know what other series of events could result in the EV system encountering another unknown, so to speak.

In hindsight, I wish I had raised the issue of the 20DMF moving below the 0% line forcefully. However, would that truly have changed anything in terms of your and Pascal's response? I'm not trying to be cheeky, here; I'm merely trying to ascertain whether poking and prodding on my (and everyone's) part is helpful to the goal of improving the system.

It's a difficult problem: we want to trade with statistical probabilities on our side, but at the same time, do we have a sufficiently robust sample set to truly feel comfortable we "have the bases covered"?

[QUOTE=adam ali;15450]
It's a difficult problem: we want to trade with statistical probabilities on our side, but at the same time, do we have a sufficiently robust sample set to truly feel comfortable we "have the bases covered"?[/QUOTE]

Adam, you want HIGH probabilities on your side. None can be found in any direction based on Friday's close however you look at it. I've probably read more than 100 blogs and newsletters this weekend and whatever any indicator they use, they are all amazed how they are in "terra incognita".
I doubt any algorithm from anyone could provide a valid high probability trading plan for more than a few minutes currently.
Cash is King! Cash is a position with a stop once we see high probability trades again.
Billy

[QUOTE=Billy;15448]...It is only in hindsight that Pascal could make the discovery that confirmation improved performance during POMO periods but hindered it out of POMO periods. This information is obviously now seriously considered for inclusion in the robot rules and very likely will be in the future...
Billy[/QUOTE]

Is the "POMO periods / ETF Confirmation" a case of correlation or a case of causation in the process of developing new robot rules ([url]http://stats.org/faq_vs.htm)?[/url] I would feel quite more comfortable with the ETF confirmation rule if the rationale for its use during POMO periods was inferred based on logical grounds prior to a data mining exercise that shows the superior performance it produces.

Trader D

[QUOTE=TraderD;15458]Is the "POMO periods / ETF Confirmation" a case of correlation or a case of causation in the process of developing new robot rules ([url]http://stats.org/faq_vs.htm)?[/url] I would feel quite more comfortable with the ETF confirmation rule if the rationale for its use during POMO periods was inferred based on logical grounds prior to a data mining exercise that shows the superior performance it produces.

Trader D[/QUOTE]

Unfortunately, your link is dead so I'm not sure I understand your question well.
Pascal is the leader in mathematical/statistical expertise and is surely better qualified than me for responding.
Billy

[QUOTE=TraderD;15458]Is the "POMO periods / ETF Confirmation" a case of correlation or a case of causation in the process of developing new robot rules ([url]http://stats.org/faq_vs.htm)?[/url] I would feel quite more comfortable with the ETF confirmation rule if the rationale for its use during POMO periods was inferred based on logical grounds prior to a data mining exercise that shows the superior performance it produces.

Trader D[/QUOTE]

I introduced a confirmed short signal rule when I noticed at some point that large players were selling SDS while the 20DMF was issuing a short signal. I thus concluded that the short might be a false signal and overruled it at that time (early POMO days). It is on that base that I included the SDS confirmation in teh 20DMF rules - that was later on changed by the four inversed ETFs confirmation.

The important issue is not regarding the 20DMF. I think that the issue is to render the robot strong enough to sustain minimal damage in case of market direction error or even to overrule the 20DMF at some point. The solution I believe is in better sorting out the weak and strong robot trading signals. I am working on that. Another item is to revert to cash whenever the LT/ST signals are so completely apart - which indicates that the model has reached its programmed statistical limits. We are in such an exceptional situation right now.


Pascal

Billy, Pascal,

Do I understand correctly that in the future the Robot will have occasional cash positions?

Tim

[QUOTE=Timothy Clontz;15478]Billy, Pascal,

Do I understand correctly that in the future the Robot will have occasional cash positions?

Tim[/QUOTE]

Yes Tim,
This could be a possible new rule at times. We'll know after full backtesting of new suggested rules have been done.
Billy

I've alo been considering a cash option for my sector selections. In my own backtesting the long sector outperforms the short sector (on average) even during drastic market moves. A long XLK hedged against a short XLE would have continued to make money even after being stopped out.

I'll work on my own ruleset to incorporate those kinds of conditions for the sector test. My own "neutral" setting may simply be hedged instead of in cash.

In such a condition a stop loss may only stop out half of the position and enter a stop limit entry point for the hedge.

[QUOTE=Pascal;15464]I introduced a confirmed short signal rule when I noticed at some point that large players were selling SDS while the 20DMF was issuing a short signal. I thus concluded that the short might be a false signal and overruled it at that time (early POMO days). It is on that base that I included the SDS confirmation in teh 20DMF rules - that was later on changed by the four inversed ETFs confirmation.

The important issue is not regarding the 20DMF. I think that the issue is to render the robot strong enough to sustain minimal damage in case of market direction error or even to overrule the 20DMF at some point. The solution I believe is in better sorting out the weak and strong robot trading signals. I am working on that. Another item is to revert to cash whenever the LT/ST signals are so completely apart - which indicates that the model has reached its programmed statistical limits. We are in such an exceptional situation right now.

Pascal[/QUOTE]

Pascal, thanks for the explanation.

My primary concern is the rule derivation methodology. In other words, how an anecdotal observation is validated to be statistically significant for inclusion in the robot's rule set.

From a parametrization standpoint, whatever ends up being selected has to: (a) be based on some apriori rationale, (b) coherently fit into the model and (c) have minimal dimensionality with respect to the available data on which it is intended to be validated. Clustering/segmentation of the LT/ST signals (e.g. weak/strong) seems at first glance to be a reasonable choice for satisfying (a)-(c) above.

Repeat analysis of the signals' distributions may be necessary every so often to re-align the model with changing dynamics of the market (POMO or otherwise). Another option is to utilize "range-adaptive" cluster boundaries that are automatically re-calculated based on a recent history (e.g. past 12 or 24 months) to compensate for the inevitable market drift. The latter often feels more "versatile" than relying on hard-coded thresholds.

Trader D

[QUOTE=Billy;15462]Unfortunately, your link is dead so I'm not sure I understand your question well.
Pascal is the leader in mathematical/statistical expertise and is surely better qualified than me for responding.
Billy[/QUOTE]

Sorry, Billy, the link should be devoid of the question mark: [url]http://stats.org/faq_vs.htm[/url]

HTH,

Trader D