kevinkdog 

If the IS profit is positive… 39.4% of cases have profitable OOS performance With a profitable IS test, we are more likely to have a profitable OOS result.

A 39.4% chance of a profitable OOS performance still means a 60% chance the strategy will end negative, even after a positive IS. That is not very promising.

Also the 39.4% is just a little over 35.1%. Even with a negative IS you still have a chance of 35.1% on a positive OOS which is only a minor 4.3% difference.

Because of the minor difference and a chance of less than 40% on profitability I would be inclined to say that back testing has no added value at all or am I missing something?

kevinkdog 

Thanks for the kind words. So to answer "why would I consider turning off an algo?" let's look at this strategy, assuming I traded 1 contract throughout... If I had started real money trading right after development (something I do NOT recommend)... First run up was +$25K per contract Then a drawdown of about $18K Then a 2nd runup of about $45K Then a drawdown of about $25K Finally a current recovery of about $8K In summary, overall had you stuck with the strategy through thick and thin, you would have made $25K. BUT, you had to endure a long drawdown of $18K, and a shorter drawdown of $25K. Could you have handled it emotionally? I bet 99% of people could not. Just imagine yourself in 2 scenarios: 1. You start trading around trade 68, you go on a cruise for years and years, and arrive home today. You never looked at the equity chart since trade 68. You'd probably be happy where you are at, with $25K profit. 2. You start trading around trade 68 and you look at equity curve every week. How would you feel at trade 105, when you have given back most of your profit? Would you be worried that your strategy was broken? I sure would. Nothing like that drawdown had ever happened in the backtest. Is that a fluke, or a warning sign? When people look at hypothetical equity curves, they imagine themselves in scenario #1. But reality is scenario #2 - TOTALLY different feeling, for the same end results. So why turn off a system? Well, remember the backtest is not a prediction of the future. You HOPE it continues, but "past performance is not indicative of future results." And imagine the psychological turmoil you'd experience when reality starts looking worse than the backtest (I love when people say "algo trading is emotionless," these sad souls are so misguided). This performance would have me pulling my hair out! All things considered I think it is wise to plan for a different alternative than you see in backtest. So, you plan for failure, realizing it may never occur. (By the way, this was a really good question. I plan on using this discussion in my next "algo Trading" article for Tech Analysis of Stocks & Commodities magazine).

Good Afternoon Kevin,

Thank you kindly for your detailed response.

I will print out your response, read it and respond shortly.

kevinkdog 

Thanks for the kind words. So to answer "why would I consider turning off an algo?" let's look at this strategy, assuming I traded 1 contract throughout... If I had started real money trading right after development (something I do NOT recommend)... First run up was +$25K per contract Then a drawdown of about $18K Then a 2nd runup of about $45K Then a drawdown of about $25K Finally a current recovery of about $8K In summary, overall had you stuck with the strategy through thick and thin, you would have made $25K. BUT, you had to endure a long drawdown of $18K, and a shorter drawdown of $25K. Could you have handled it emotionally? I bet 99% of people could not. Just imagine yourself in 2 scenarios: 1. You start trading around trade 68, you go on a cruise for years and years, and arrive home today. You never looked at the equity chart since trade 68. You'd probably be happy where you are at, with $25K profit. 2. You start trading around trade 68 and you look at equity curve every week. How would you feel at trade 105, when you have given back most of your profit? Would you be worried that your strategy was broken? I sure would. Nothing like that drawdown had ever happened in the backtest. Is that a fluke, or a warning sign? When people look at hypothetical equity curves, they imagine themselves in scenario #1. But reality is scenario #2 - TOTALLY different feeling, for the same end results. So why turn off a system? Well, remember the backtest is not a prediction of the future. You HOPE it continues, but "past performance is not indicative of future results." And imagine the psychological turmoil you'd experience when reality starts looking worse than the backtest (I love when people say "algo trading is emotionless," these sad souls are so misguided). This performance would have me pulling my hair out! All things considered I think it is wise to plan for a different alternative than you see in backtest. So, you plan for failure, realizing it may never occur. (By the way, this was a really good question. I plan on using this discussion in my next "algo Trading" article for Tech Analysis of Stocks & Commodities magazine).

Thank you Kevin for the detail explanation and examples.

Question please:

1. After you turn the strategy off, what do you do to make money trading, because now you have no strategy to trade? Do you start building a new trading strategy on the ES market?

Thanks

goodoboy 

Thank you Kevin for the detail explanation and examples. Question please: 1. After you turn the strategy off, what do you do to make money trading, because now you have no strategy to trade? Do you start building a new trading strategy on the ES market? Thanks

Good question. I trade a portfolio of strategies, in various futures markets and sectors. In my mind, diversification is the closest thing to the Holy Grail, and I get it by trading many markets with many different strategies. I am continually building new strategies. Right now I trade about 30 strategies, in all 7 market sectors. I choose those 30 from a database of about 200 strategies that have met my criteria.

If I had one strategy that I'd knew for certain would continue making very good risk adjusted money in the future, I'd probably just trade that. But I am not smart enough 1) to develop such a terrific strategy and 2) even if I could develop it, to know for certain it would continue to make money for the foreseeable future. So I do the next best thing - develop and trade lots of decent strategies.

Hope that answers your question.

kevinkdog 

Good question. I trade a portfolio of strategies, in various futures markets and sectors. In my mind, diversification is the closest thing to the Holy Grail, and I get it by trading many markets with many different strategies. I am continually building new strategies. Right now I trade about 30 strategies, in all 7 market sectors. I choose those 30 from a database of about 200 strategies that have met my criteria.

Hello kevinkdog;

Thank you for the response.

1. So instead of investing all your money in one algo, you split your money to invest in 30 strategies in all the futures market? I agree this makes better sense to bet your money on 30 strategies versus 1.

2. What do you mean by 7 market sectors?

3. Why not bet your money on all 30 strategies and let them run forever and scale up size and be rich? I am not seeing the reasoning for working hard creating more strategies when you have 30 already. I would think finding 30 strategies is more than enough work and effort and take you very long time.

Thank you,

Hey @goodoboy, good questions. Be really interesting to see what Kevin says in response to your question about why isn't 30 strategies enough. I would imagine a few strategies stop working every year so he has to build new ones to replace the stale ones constantly so the work never ends.

goodoboy 

Hello kevinkdog; Thank you for the response. 1. So instead of investing all your money in one algo, you split your money to invest in 30 strategies in all the futures market? I agree this makes better sense to bet your money on 30 strategies versus 1. 2. What do you mean by 7 market sectors? 3. Why not bet your money on all 30 strategies and let them run forever and scale up size and be rich? I am not seeing the reasoning for working hard creating more strategies when you have 30 already. I would think finding 30 strategies is more than enough work and effort and take you very long time. Thank you,

1. Yes

2. Stock indices, currencies, metals, energies, interest rates, ags, softs

3. Strategies fail (as seen in the earlier post I made), and the more I develop, the better the strats I create, and the more I like the strategies I create (which is important when drawdowns hit).

kevinkdog 

1. Yes 2. Stock indices, currencies, metals, energies, interest rates, ags, softs 3. Strategies fail (as seen in the earlier post I made), and the more I develop, the better the strats I create, and the more I like the strategies I create (which is important when drawdowns hit).

Good Morning kevinkdog,

Thank you for the response.

How do you know when a strategy fails?

If you have 30 strategies and scale them up, by time one of them fails, you are already rich. All I need is one algo to reach +100 contracts, mission accomplished right?

Sorry, but I just do not understand the point of continuously programming and finding all those algos. That seems like alot of work for no reason.

How much money does one algo take to invest in? I assume about $25K, that is $750,000 to invest in 30 algos. If I bet $750K on 30 algos, my job is done, I sit back and wait for big money. These 30 algos, have one job, make me ALOT of money, millions of dollars. Not sure I understand why I need go back and create more algos.

Sorry but, I am not see or understanding the reward for the investment.

Can you explain better to me please?

blackgrey45 

Hey @goodoboy I would imagine a few strategies stop working every year so he has to build new ones to replace the stale ones constantly so the work never ends.

Good Morning blackgrey45,

Good conversations.

If strategy keep failing eventually, I run out of money to invest in more strategies.

With the extra variable, Strategy May Fail" added to the make money equation of algo trading, it complicates thing, IMO.

The markets have data now about 23 years. For example, ES has about 23 years of minute data somewhere.

My question is this:

1. With all this data, why should a strategy fail? If I create 5 ES strategies with ALL this data and bet my money on it, I should have 100% confidence that 3 out of 5 of these algos making me beyond rich in the next +5 years, maybe longer. This is the questions I have to Kevin or anyone else. I am not understanding this.

goodoboy 

Good Morning kevinkdog, Thank you for the response. How do you know when a strategy fails? If you have 30 strategies and scale them up, by time one of them fails, you are already rich. All I need is one algo to reach +100 contracts, mission accomplished right? Sorry, but I just do not understand the point of continuously programming and finding all those algos. That seems like alot of work for no reason. How much money does one algo take to invest in? I assume about $25K, that is $750,000 to invest in 30 algos. If I bet $750K on 30 algos, my job is done, I sit back and wait for big money. These 30 algos, have one job, make me ALOT of money, millions of dollars. Not sure I understand why I need go back and create more algos. Sorry but, I am not see or understanding the reward for the investment. Can you explain better to me please?

There are various methods to give you guidance on when a strategy was broken or was breaking. For example, maybe if you encountered a drawdown that was beyond the maximum historical drawdown during backtest, that might be an indication of failure.


As far as your last statement, I think you might be underestimating how difficult trading is. I don't know of any real money trader who can just "sit back and wait for big money." And I know a lot of successful (and unsuccessful) traders. I know a lot of fake traders who claim it is easy, who throw out comments like "oh, do you need more money from trading? It is simple to make more money, just trade 10, 20 or 50 contracts instead of 1 or 2."

To me, trading is the hardest way to make easy money.