TLC Weekly Update July 31, 2020

image

An interesting week of wild market actions that left many traders puzzling what to expect next. Well, take it one day at a time is probably the best advice I can give. There is no point to engage in trading when you do not have an understanding of the context. Take a break could be a good idea too so that you can clear your mind from fixation of specific narratives of the market.

Rarely do I find CNBC makes meaningful videos. This video is an exception – watch it to understand why Amazon has no competition in the cloud storage arena. The fight is ongoing to be the leader in this field but the second place player Microsoft has a long way to get near Amazon’s market shares.

Good read about Ida Wood, one of the most interesting persons of her time. I like the fact that she was able to handle her husband’s gambling addiction in such subtle way that otherwise the wealth would never have been preserved. As a trader, it is in fact important to learn from this lesson and save our winnings systematically so that we do not lose all our money back to the markets.

Robert Greene has been interviewed by many people but he did not have a Youtube channel until now. His first video, The Crisis Generation, is a good one. It is about 30 minutes though so enjoy it over a long break when you get the chance.

I have re-written a script for my video lesson the third round already. Still not satisfied with the result. So members of DaytradingBias may have to wait a little longer.

The week was so hectic that I did not even know that it is Friday already. Having all these phone calls from Asia to Europe scheduled at odd hours is really messing up my sense of time. My goal to build this trading power house is taking shape though. Exciting time!

Have a great weekend everyone!

TLC Weekly Update July 3, 2020

image

Today is a US market holiday making this a long weekend for me. Many of my friends in Toronto find it odd that I rarely take a break on Canada Day (July 1st) while enjoying my time the weekend after. Well, they are not aware of my trading mainly deal with US markets so my holiday schedule is really the American one.

Just heard the latest podcast Tim Ferriss Show with Hugh Jackman this time. A very interesting podcast packed with a lot of details that is never disclosed before. Tim Ferriss did an amazing job getting his guest to spill his guts. Enjoy the show if you have 2 hours to kill. And in case you prefer to listen to it on Youtube, here is the link for that.

A short clip with Ray Dalio summing up perfectly the kind of financial markets we are dealing with. It is difficult environment to navigate if you do not have a big picture understanding of what is going on. Mr. Dalio summary can help you pay attention to what matters most at this point in the economic cycle.

Long weekend is often a good time to reflect and contemplate what to do next. Many people tend to imagine too much and try too hard to develop a plan that they can never follow. I am a true believer in the accumulation of results. Or as Steve Jobs’ famous speech put it, “You can’t connect the dots looking forward; you can only connect them looking backwards. So you have to trust that the dots will somehow connect in your future.”

Dive deep into one subject or topic at a time and do your best to learn as much as you can is a very empowering experience. Don’t tell yourself you are “trying to learn as much as you can”. That framing of “to try on something” already put you in a state of not learning, or, in a state of rejecting whatever coming out of the experience. Words have power and programming yourself with the wrong words have consequence.

For those of you struggling with trading over the past few months, maybe it is time to dig deep and refine your skills related to trading. 10% better in one area within a month may not do much. But after getting better by 10% (or more) in several areas of your trading can be a game changer to your overall performance. There is always room for more improvement in our line of business, and in life too.

Have a great long weekend all!

My Journey to Fully Automate My Trading: The Extreme Volatility Challenge is Blessing in Disguise

image

It is the end of second quarter of year 2020, I am so busy with so many things I could not really sit down to write something for this series for months. Since this series is a documentary, I guess I should write something so that looking back, I have what happened on record. After contemplating on several ideas, I decided to talk about the impact of extreme volatility on my trading strategies.

There it was, March 2020, the fastest and steepest decline in S&P500 in its history. And then even more amazing, was the miracle rally from that swing low pushing S&P500 back up to almost unchanged for the year. Nasdaq 100 has even made new all time high now.

So many of you have asked whether my trading models are doing fine? I can detect the undertone even though English is not my native language. My guess is that they are wondering if I lost a lot of money during this time.

In short, I am doing fine. If I were trading mostly discretionarily, I will not be. The automated trading strategies saved me from making major trading mistakes many times during this period. I am so glad that I managed to convert about 50% of my trading method to fully mechanical trading models right before the start the extreme trading environment.

What Went Right

The strategies managed to avoid most of the trading days that has extreme swings. Some of you may wonder why avoiding those days. Isn’t it the purpose of day trading to capture the intraday movements?

Yes, day trading strategies are designed to capture the intraday price movements based on the microstructure for which price would move a certain way given certain pre-conditions are met. However, when the volatility is way too high, even if you are on the right side of a move, the strategy will still be stopped out easily thanks to the extreme swings every few minutes.

Of course you can increase the size of the stop losses to participate in the game. But my research shows that is absolutely counter-productive. First, increasing the overall risk taken per contract means you need to reduce the total size of each trade to protect the trading capital from an overall risk management perspective. Second, the equity swings can be nerve wrecking which can disable you from take care of your everyday tasks. In other words, you see extreme swings in your equity and likely ended up doing almost nothing.

One very good thing that stands out is the data and order server stability with all these firms I work with. Comparing to the financial crisis back in year 2008 and 2009, the experience is so much better. Back then we have so many outages making trading nearly impossible. Just the fear of being trapped in an open position was bad enough. Again, the advancement and maturity in technology and infrastructure with these firms are something I greatly appreciated.

What Went Wrong

I was caught off-guard several times when the brokerages made sudden announcement to change the margin requirements. There was once that the change was made in the middle of a trading session. These sudden changes caused me to miss several trades due to the orders being rejected by the brokerage system.

Not happy with these incidents mainly because the missed trades are all winners. LOL

And I learned from this experience that the brokerages are reacting to the situation very differently. For example, Interactive Brokers and Tradestation at times raising their day trading margin requirement to full exchange overnight maintenance margin while some pro shops just double up their promised day trading margin requirement. What the brokerage firms do is not to protect their clients. What they are doing is protecting themselves. This shows that the pro firms understand their clients are professionals so there is no need to exercise extreme caution.

The worst part of the experience so far is the next to none support from many firms as the lock-down due to COVID19 forced many to operate remotely with very limited access to their staff. So anything that requires human intervention or help becomes not available or that the waiting queue is so long that you just have to give up. Can’t complain about that since this will probably become the new normal if the outbreak continues for a prolonged period of time.

What Could Be Improved

Technically, highest priority is the integration of position size into some of my trading strategies so that they can change the order size should there be a sudden margin change. This is not difficult but takes time to develop and test the code. Just one more project on the table that jumped my long queue of other things I need to get done.

I already have remote control of everything setup so that is not a problem. The remaining disaster scenario is that we have some form of global internet outage while I have an open position. For this scenario, I am still working on a way to minimize its impact.

What’s Next

The time I saved from manual trading gave me the freedom over the past few months in completing a few business deals. The main benefit, however, is that I have more time to spend on automating even more of my trading strategies. It is just fun watching these bots going live and doing their things.

It feels like playing Legos when I was very young or playing SimCity as a teenager. The satisfaction coming from the accomplishment is very hard to describe.

As I mentioned in my weekly blog, the success I have achieved so far with the conversion process has given me the confidence to keep going until everything is automated. One fund manager who is a long time friend sum it up nicely – once you have converted to automated trading, you will never go back.

TLC Weekly Update April 3, 2020

image

Another week of roller coaster ride with the stock markets worldwide. When I told the premium members that I expected after end of March S&P would collapse back down to around 2400, many were in disbelieve. Well, S&P tanked hard down to near 2400 on Wednesday. The timing sounds amazing but in fact it is just a simple observation.

What I noticed is that everyone suddenly turned into experts on COVID-19. That, of course, includes all these financial analysts coming out with their fancy projections and forecasts. However, from the medical papers published by the scientists, I’ve learned that we actually know almost nothing about the virus so far. Even the specialists who are studying the virus do not know enough about it to make any sensible projections on when and how the outbreak will be contained.

When we do not even know what we are dealing with, how can we produce meaningful projections?

So all these firms are selling a fast bottom to drum up business, nothing more.

The consequence is more downside once they run out of suckers. Of course, sometimes people get lucky and if this outbreak suddenly disappear for good, I am all for that. It is a nightmare that this world is not ready for.

I am wrapping up several videos this week. The first one is out on youtube already. It is a quick reminder on what to pay attention to when day trading Emini S&P during crisis. Check it out!

I am still working on the full length lessons for Trading Success Blueprint and Emini S&P Day Trading Course. Due to the self isolation rule here, I am working with minimal help from others at the moment. It feels nostalgic in a way that it reminds me of doing research on trading models alone decades ago. I hope that I can put out something within a week or so.

I came across this video with Sadhguru’s explanation on why meditation does not work for many. He summarizes this so well. If you find meditation is not doing anything for you, you probably need to watch this. It also reminded me to produce a lesson on meditation for traders since it is an integral part of TSB.

Will take a break this afternoon and resume working over the weekend.

Have a great weekend all!

My Journey to Fully Automate My Trading: How Did It All Begin

image

In this internet age, people always question the authority of anyone who tries to make a point. That’s especially true when the point of view one has is completely different from what the mainstream beliefs are. Since my beliefs are at odds with the mainstream trading education community, I guess it is time to set the record strict so that you can decide for yourself why you should listen to me on things related to trading.

Interviewing Myself

I have a habit of interviewing traders (if they allow me to) and collecting answers from them if they prefer the questionnaire format. That adds up to several boxes of records over the years. Many of these traders are good traders whose life long trading experience are extremely useful to newcomers. However, my trader friends also prefer not being put in the limelight, so to speak. I can only use the information myself as oppose to publishing volumes of trader interviews.

One of the questions I always ask these traders is, “How it all begin?”

I am going to answer that myself. Right here, right now.

How It All Began

Many people get into trading because they learn about it from a friend or saw on TV how traders are making big money. If you are interested in making money quickly, you will give trading a try. That’s not what happened to me at all.

When I was young, I have no interest in money making. I did not have what they call entrepreneur spirit. I was not interested in the financial markets. My hobbies were reading books, playing chess and making my own electronic devices.

My older brother was completely opposite. He liked creating his own businesses. He had a keen sense about the financial markets since he was young. He was the person who, at the first opportunity he found, became a floor trader in the Toronto Stock Exchange.

As a young trader, being Asian no less, in a place dominated by very aggressive western people, who would have imagine that he can last six months?

He went on to set a record there – as a first time newcomer, he not only survived the game for a full year but also made 4 times his trading capital by the end of the year. He was the hottest new guy.

From there the direction of my life took a sharp turn. My mother believed that my brother’s new found prosperity was the way to go. My brother thought that my intention to become a full time academic was stupid. Without any other option, I had to give trading a try.

So I followed my brother’s footstep to became a floor trader at the Toronto Stock Exchange.

I also set a record there – I was the youngest floor trader they have accepted thanks partly to my brother’s star power and partly for my perfect score in their exam which never happened before. I had an advantage over others in taking the exam – the hardest part of the exam was related to option pricing and strategies which was damn easy for someone who spent most of his life studying math and science.

That’s why I do not think like others who try to beat this game.

I did not even want to play this game, for God’s sake.

That’s how my trading career started some thirty years ago.

TLC Weekly Update February 7, 2020

image

Another totally messed up week with scheduling issues, stuck in traffic thanks to crazy weather here and heat to my place stopped working. Sometimes technologies really test our nerve. Looking at the bright side though, I managed to finish reading another book when my internet was fucked up all evening …

Yes, plain old printed books still rock!

I was working hard to come up with all kinds of ideas for my teaching videos on trading. I ended up with like 20 ideas, each I wrote like 10 pages of script and stopped. It is hard indeed to create something that is both educational and functional. Serious, if I go too negative, people walkaway without learning the lessons they need. If I go real gun ho and downplaying the difficulties of trading, people gets too excited and forget about the main points. Striking a balance is not easy.

I was a good lecturer way back then. I was a good mentor to hundreds if not more pro traders working for firms. But this goal of helping the retail traders is super challenging. How to disrupt people from fantasizing trading as something more than what it is? It is fun taking on a challenge like this.

For some interesting reason, I have to retell how I first get started in trading to quite a number of people this week. Maybe people need to know me better so that they are not that intimidated. I am sure I have written about this way back when somewhere. Maybe it is time to do it once more in one of my new article series for easy reference.

So many random thoughts this week. Next week should be better, I hope.

Have a great weekend all!

TLC Weekly Update December 13, 2019

image

I finally uploaded the first video lesson for DaytradingBias youtube channel. Let me know whether you like it. All inputs are welcome.

I am typing this update in Kuala Lumpur, Malaysia. The weather here is pretty hot. I am hoping to explore some investment ideas here before leaving early next week.

I came across this article while waiting for my flight. If you live in North America, you need to know about this dangerous mushroom. Check it out.

I was asked very often by traders and investors alike about this US-China deal. Well, no deal is good enough. That’s all I can say. How can the stock market be 15-20% higher from a time that there were no trade conflict at all to the current state of getting a partial deal is good enough?

When Card Counting Fails: Learn to Walk Away While You Can

roulette2

When I was in Europe last month, it was inevitable that I had to go out and socialize with my business associates. One such night we ended up going to a club with blackjack tables. One of my friends there knows very well I am an avid card counter and would like to see if I can beat the house. So there I was, sitting at one of the blackjack tables with couple hundreds of euro in chips to play the game.

The Game

I asked the dealer like how many decks are there and started playing.

I did my usual counting and noticed that the cards dealt out were collected and put back into the card dealing machine. I knew something was not right but I could not recall exactly what it was at the time, partly due to all night wine and dine activities.

Needless to say, I got cleaned out.

Whenever I tried to increase my bet size, thinking that it was the right time to do so, I encountered significant losses.

The chance for me to count wrong was very low. So low that I knew something did not add up. After I lost my last chips, I recalled exactly what I should have remembered before I started playing.

My associates asked me to keep on going so that I can win the money back. I told them I don’t want to do that because I was low on cash. In reality I had more than enough cash to keep going but I knew better not to. My friends even tried to pool together more cash for me to do it again because they probably feel bad that I lost money.

I ended up telling them the truth. I pointed out the machine on the table is something I cannot beat. Since I do not like playing blackjack to lose money, I told them we should do something else instead. They were quite upset and were afraid that I was unhappy. I had to assure and reassure them that I am perfectly alright.

I was secretly relieved that I did not need to grind at the table. I was happy because I knew this is the right decision.

The Machine

The issue I pointed out being the card dealing machine was not an excuse. This type of card dealing machines is designed to save time for the dealer, prevent cheating through manual card shuffling and, most important of all, to beat card counting. Cards are consistently redistributed back into the shoe hence the chance of these cards showing up again, say, five hands later, would be the same as all the other cards within the machine. There is no more distribution imbalance that a card counter can rely on. Thus, all card counting strategies based on the cards not being reused until next complete reshuffle would fail.

I should have walked away the moment I sit down at the table and noticed that the machine is in place for dealing cards. But I did not.

I suspect that my inability to recall the important fact about the card dealing machine is my commitment bias. I changed my Euros for chips. I sat down at the table. And most important of all, I have a crowd around me watching. My mind swing from being a careful pro into a casual player.

The Crowd

Emotions ran high when the crowd saw the dealer’s hand busted at the fourth and fifth card. Emotions ran even higher when someone on the table getting 21 on the fifth card.

Of course, emotions swing low when the dealer managed to clean the table with 20 or 21 even though many players had pretty strong hands.

Everyone has been participating in the game, with emotions invested into every card being dealt out.

I could see on the face of everyone that they were emotionally exhausted about an hour into the game.

Isn’t it interesting that we all know this is a game of chance yet we would cheer on wishing the dealer to go bust, or that some players were so anxious that it took them forever to decide whether to hit or to stand?

Maybe this is the very reason some people love gaming.

They enjoy the emotional rides and excitement that these games bring to them.

The Odds

Going a bit technical here, I will explain what the difference is between a normal Las Vegas style blackjack and the one I played with the card dealing machine.

In short, the Las Vegas style dealing will give the house a very slight edge over the players if the player is not counting cards, while exercising all normal cautions like not to hit when you cards already total at 20. With a good card counting strategy, a player can, at times, having a significant edge over the house when many high cards are left in the shoe leading to very uneven distribution.

For the card dealing machine I played, it actually offers the players a very minute edge, as long as the player is exercising the normal cautions. This means, if you have a big enough bank roll, you can win a small percentage of your capital as long as you are betting with the same size. Obviously, the goal of using these machines is not to beat the players. These machines are installed for the purpose of facilitating a service, to keep the guests entertained.

However, if a card counter is not aware of the design, the uneven betting based on the wrong projection of the existence of a bias distribution, will lead to unnecessary losses.

The Lesson

It is a good reminder to us, the professional traders, that we manage to make money in trading because we have good strategies and game plan in place. However, we have to be aware of the changes to the game itself that may completely alter the odds of our trading strategies. Keeping up with the environment change is very much part of our responsibility as a pro trader.

Time to Slack Off 2017

image

As a follow up to my Time to Slack Off series, I like to report my results and what I think going forward I will do with my trading. Many doors opened this year for which I am very grateful for and that I get to try out different ideas in such a short period of time is both exciting and exhausting. It is time for me to reflect and plan for the coming year.

Transformation of My Trading

I have achieved my trading goal for myself and for my clients as a money manager back in early October already. Due to serious pile up of all kinds of tasks, I did not get the time to write about it until now. This year is fundamentally different from the years of trading I have done due to the drastic changes of my trading goals and the new responsibility of managing a completely different kind of funds.

Many readers who follow me for years know that I used to trade through the complete US market open hours. I did take breaks during lunch but I tended to squeeze as much profit from the market as possible back then. Last two years my personal trading goals have changed to a more moderate approach for which I am driving for consistent returns with much reduced stress and effort. That took a lot of work outside of trading to further improve my mechanical trading models. More importantly, I came up with an even better trading framework for handling the current trading environment.

Hence I spent a lot less time in front of the screen and more time outside of it. I now usually sit at the screen to watch the open but I can choose not to because my mechanical models would take care of the orders anyway. Even though I have open positions by 11 am (Eastern Time) I can walk away since the positions are managed automatically. In my opinion, the performance is actually better based on the relatively shorter amount of time spent in front of the screen.

My Experiment on Running a Different Type of Fund

Last year I started to manage in a small scale funds that demand stable return in low-teens percentage with a time window of 3 years (or more) of lock-in period. As oppose to classic fundamental based fund managers who bet on fairy-tale information, or those big swingers with so-called macro view that ignores the market dynamics, my approach is to day trade with mechanical strategies that I know are rock solid concepts working consistently over the past 20 years. By controlling the leverage, I make it possible to produce consistent returns without the so-called volatility swings with those funds that have overnight risk. It is a great idea that worked out very well.

In comparison, the responsibility as a money manager managing client accounts, my objective is often maximizing the return with risk precisely defined. I can assure you that it is not an easy task. Although I have been doing my part for years, it is still challenging as the financial markets evolve rapidly.

The Birth of a Private Fund

Inevitably, after the success of the experiment, I am being asked to reconsider my position to run a fund among close friends and families. It is not even going to be the size of a tiny hedge fund. It is just money that a few close friends can spare for speculation purpose (something I called burnable). Since I am so restrictive on the amount of money they should put into the pool relative to what they have and that I am imposing the same 3 to 5 years lock-in period, I am glad that they choose to keep their individual commitment small. Now that the word is out, I have requests from friends everywhere asking me to do the the same.

This is, kind of, completely deviating from my original plan. My original intention was to run this private fund with just my own money and possibly some from my partner. Once the first year return is booked, I will try to convert the individual accounts that I manage for my long term clients into the same pool so that I can streamline the whole operation. That is a longshot though, because my clients really dislike publicity of any kind. Still, I hope to convert them to believe in my new hands off approach.

Anyhow, I planned to launch this no later than February next year. Just the explanation of the risk involved in my kind of trading can take hours to each individual interested in this. It will keep me very busy until then.

Mix and Match of Trading Signals

So what does all these developments have to do with daytradingbias.com? After all I tagged this post with it.

Well, part of the trading models I developed for my private fund will also be made available at daytradingbias.com thru real-time trading assistant and other means. I have looked into many other ways to delivery the signals. The viable ones will be added one by one.

For those interested in managing their own accounts with a subset of signals picked from the set, documentation / a complete course will be made available so that they can adapt the strategies to create a trading plan that fits their risk tolerance. This is what I am planning so far but I do not know if the plan will change again down the road.

On the Road Again

I am heading to Asia as mentioned in my post back in October coming weekend. Once I have internet access there I will continue to post. I will get the chance to meet with many people from the financial industry there. If anything interesting comes up, I will definitely write about them.

 

Past Time to Slack Off Posts

Time to Slack Off 2014

Time to Slack Off 2013

Time to Slack Off 2012

My Journey to Fully Automate My Trading: AI vs. KISS

Thinker

The latest round of buzz about AI (Artificial Intelligence), particularly the new meme Machine Learning, has triggered many talks on its applications in trading and investing. It is very interesting how it suddenly becomes the latest holy grail in trading. Is it really that much better? Not necessary.

What AI is Good at

AI is very good at picking up patterns from large amount of data based on the framework we have provided them. It also gives AI the advantage to find patterns that human often miss since we are born to identify visual anomalies only. In other words, AI can assist us to uncover useful information from large amount of data. From the game of chess or online games, to industrial design of cars and equipment, AI helps us resolve many difficult problems in much faster and efficient manner comparing to human based discovery approach.

When I use the word “pattern” above, it is not limited to visual or statistics based patterns. It can be patterns of rules that govern a dynamic system. For example, the machine learning process may discover that certain set of rules are failing to produce the expected results, and that they all belongs to the same category of underlying patterns in the data.

By applying this meta logical pattern on the rules, AI can develop new rules itself. This is the technological direction, namely self reprogramming and self refinement, that Elon Musk is so worried about. Think about an AI based program deployed to defend a country that has built-in self management rules to improve itself. What if one day the system produced a new rule that it is better to launch all the missiles to guarantee winning a war, or chose to delete a rule that emphasize on minimizing the casualties of civilians?

AI in Trading

AI has been applied to trading ever since it was introduced many years ago. The earlier approaches are mainly developed to capture patterns in price and related financial data (e.g. PE ratio) to make forecast on individual stock and markets. Later on we have seen successful trading models built for short term trading on indices using patterns recognized from large amount of data including price patterns and market breadth data. The concept behind the development of these models, however, are still very human centric. We were using AI to discover patterns and then we apply the patterns in our trading. In short, we decide what discoveries made by the computer are applied in our trading.

The latest round of AI application in trading, however, is taking on a different direction. Many professional traders and trading firms are now testing fully automated trading models that are managing themselves. What I mean is that human factor is reduced down to the initial feeding of data into the computer with an overall theme specification and subsequent risk management only. In short, we are teaching the computer to trade by themselves instead of teaching human to do the job because we prefer traders to have little or no emotion at all for better performance.

The advantage of these new approach to AI based trading does not stop there. Models will continue to evolve on their own, either in live or simulation environment (which human still have control). This helps proprietary trading firms tremendously with much better control over the consistency in performance.

Context Matters

It is obvious that AI is best fit for trading in short term environment as the amount of data to be processed can be too much for human to analyze. It is also clear that the AI models that self manage can pick up subtle changes in the data much faster than human can. This ability to teach itself to adapt to a changing environment can be a double-edged sword though.

For a changing environment, say, a news driven shock to the markets, can be very short term. Given enough historical examples feed to the AI systems, they will figure out a way to handle these situations. The catch is, however, that certain longer term environment change never repeats themselves, yet they produced all the major characteristic changes that affect the markets for years. As there is never enough historical data on these situations, AI cannot really learn from them nor can they incorporate safety measures to safe guard themselves properly when such tide turning events happen in the future.

In other words, the adaptive AI based trading systems are doing exactly opposite of what many classic (and successful) trading models do. Instead of exploiting one specific bias to extract profit from the market with money management strategies to protect the profits like the classic trading models, the new self learning AI systems keep tuning themselves to outsmart the markets. This approach is not that different from what we called routine re-optimization of deployed trading models. Since we do not know if the set of parameters we use on a trading model would perform best in the future, by optimizing the models based on a subset of the historical data, usually the most recent part, on a regular basis, it gives us a way to tune the model to better fit the current trading environment. The self learning AI systems basically does that themselves.

Human Factor Still Key to Success

Hence, it is important more than ever that the trainer / designer of an AI system to understand the various potential drivers in a market. There are things the AI system would never be able to learn or to adapt to. There are things the AI system should never adapt to. The boundaries necessary to make the AI system safe to trade have to be provided by human.

Seriously, everyone can train their generic AI toolbox to deploy trading models to trade real money. In fact, I am sure every model deployed has a pretty darn good historical performance. But, it is not how good a system perform that matters. As the old saying goes, “If you avoid the losers, the winners take care of themselves”. It is how the system react to adverse situations and not losing too much money in the process that really counts. Only those designers who are well aware of defensive money management principles would do this correctly right from the beginning.

The bottom line is clear – it is still the person behind the machine based trader that matters most.

KISS Still Shines

“Keep It Simple, Stupid!” believe it or not, still holds true even in this heavily bots populated trading environment.

As I explained many times over the years, with more bots trading, the markets evolved into something much more predictable in a very sarcastic sense. Yes, older style of trading no longer produces good performance. And yes again, many trading methods are neutralized by the existence of bots. However, new patterns emerges from the very existence of these bots because they all behave in a very similar way. AI systems are no different. Given the technology are all based on similar toolbox, and that the obvious patterns are picked up by the AI systems one way or another, it is likely the AI systems will all behaviour similarly and go after very similar biases identified by them. In aggregation, they produce consistent footprints just like any other market participants.

So it is not necessary to stay at the forefront of technology or employing the latest trading gadget to make money in the markets. It is your overall approach to the market that matters. KISS still shines in the current trading environment. I know many size traders still focus on a few simple trading setups to make their living. The existence of these smarter AI bots changes the characteristics of many markets in the smallest timeframes only.

A Common Misconception About Day Trading Models

Lots of people spend all their time to discover or fine tuning a strategy so that it trades so many times to give them stellar performance like 300% or even 500% return per year. That may work but it is also dangerous to put all money on such models.

As I explained before in last instalment of this series, it is much better to emulate a good day trader who has multiple trading setups for which each one offers its own independent risk reward profile. It is the combination of these trading setups that produce a balanced approach to trading. With the right combination of these strategies, you get the same spectacular performance with much lower risk of complete melt down in performance like the single strategy approach.

Here is also the main concern with AI based bot traders. Unless you have a way to dissect the trading approach, you do not know the risk profile of each individual decision made by the system. You just know, as a whole, the machine trader you have on hand somehow perform great on the historical data. But we know they their were trained on those data, of course they would perform well on those data. You cannot throw a evolved model back in time to see if they would do well by the same reason.

If you train an AI system with certain part of the historical data, keeping the model not adaptive, it is then just the same old machine assisted discovery method. If you let the system retrain itself from time to time with new data, it is similar to the re-optimization mentioned above with the drawback of not able to gauge the historical performance. I think you get the point – machine learning is not perfect.

Summary

AI based bot traders are sexy for many reasons but they are far from perfect. If you know nothing about the underlying data and its characteristics, using AI to speed up your research is definitely the future as we are going to amass a lot more data going forward. However, it is not going to do you any good if you are an amateur in trading hoping that you can simply train the machine to do the job for you. Your have to be a good trainer (not necessary good trader) to make your trading bot a good trader.

At this point, it should be quite clear where I stand on the subject. I use AI to assist my research. I also use AI based models to warn me of potential changes in the market dynamics. I like the technology as it saves me time on data mining and other tasks in research. But I do not deploy trading models that are based on AI only. I prefer the KISS approach because I need the transparency and consistency with the models so that they are much easier to manage. It is a matter of personal preference. Maybe I have paranoia on AI just like Musk.