Jump to content

Welcome to the new Traders Laboratory! Please bear with us as we finish the migration over the next few days. If you find any issues, want to leave feedback, get in touch with us, or offer suggestions please post to the Support forum here.

  • Welcome Guests

    Welcome. You are currently viewing the forum as a guest which does not give you access to all the great features at Traders Laboratory such as interacting with members, access to all forums, downloading attachments, and eligibility to win free giveaways. Registration is fast, simple and absolutely free. Create a FREE Traders Laboratory account here.

cunparis

Avoiding Curve Fitting

Recommended Posts

I have developed 3 indicators that each test profitably. I've determined the optimal parameters by optimization (periods, thresholds, etc.). I do not expect to get the same results in the future, but I prefer to use the optimized values rather than some arbitrary values.

 

My question is this: I'm now working on combining these 3 into one signal (short, flat, long). I've tried two different approaches to do this:

 

1 - I use the optimal parameters that I determined on each indicator individually

 

2 - I re-optimized all parameters together.

 

#1 seems to be more realistic, with the acknowledgment that the performance will not be the same as the backtests, due to the performance of each system not being the same. This I know. So the final results will probably not be as good.

 

#2 - Seems to be more optimal, with an even stronger acknowledgment that the results will not be as good as the backtest. However there is a greater risk of curve fitting due to the increased rules and degrees of freedom. In defense of the optimization I will say that lots of attempts produced unacceptable results so I believe that if optimization finds something good say PF > 3.0 then it's very likely to be positive in forward testing even though the PF will most likely be less.

 

I'm curious what people think about these two approaches. I am currently forward testing both #1 & #2 but since they trade on daily charts and not very often, it will take a while to have something meaningful.

 

I've developed systems that have held up and systems that have fallen apart. I understand the limitations of backtesting and automation. So I prefer not to debate that but focus on which approach would be more optimal (and not necessarily more realistic).

Share this post


Link to post
Share on other sites
I have developed 3 indicators that each test profitably. I've determined the optimal parameters by optimization (periods, thresholds, etc.). I do not expect to get the same results in the future, but I prefer to use the optimized values rather than some arbitrary values.

 

My question is this: I'm now working on combining these 3 into one signal (short, flat, long). I've tried two different approaches to do this:

 

1 - I use the optimal parameters that I determined on each indicator individually

 

2 - I re-optimized all parameters together.

 

#1 seems to be more realistic, with the acknowledgment that the performance will not be the same as the backtests, due to the performance of each system not being the same. This I know. So the final results will probably not be as good.

 

#2 - Seems to be more optimal, with an even stronger acknowledgment that the results will not be as good as the backtest. However there is a greater risk of curve fitting due to the increased rules and degrees of freedom. In defense of the optimization I will say that lots of attempts produced unacceptable results so I believe that if optimization finds something good say PF > 3.0 then it's very likely to be positive in forward testing even though the PF will most likely be less.

 

I'm curious what people think about these two approaches. I am currently forward testing both #1 & #2 but since they trade on daily charts and not very often, it will take a while to have something meaningful.

 

I've developed systems that have held up and systems that have fallen apart. I understand the limitations of backtesting and automation. So I prefer not to debate that but focus on which approach would be more optimal (and not necessarily more realistic).

 

I use step 1. Don't optimize together. I always test different "indicators" or rules in isolation then I bring them together one at time. If one rule does not contribute to making the system better I don't re-optimize it - I dump it.

 

Good systems, in my humble opinion, only need a 2-3 basic rules. Your key trading concept shouldd work well without much, if any optimization.

Share this post


Link to post
Share on other sites
I use step 1. Don't optimize together. I always test different "indicators" or rules in isolation then I bring them together one at time. If one rule does not contribute to making the system better I don't re-optimize it - I dump it.

 

Good systems, in my humble opinion, only need a 2-3 basic rules. Your key trading concept shouldd work well without much, if any optimization.

 

Thanks for the feedback. I did a lot of forward testing this weekend. What I found was that performance going forward was pretty good until the past few years. Then even if I reoptimized it didn't walk forward well. i think it's due to changing from bull to bear and from the increased volatility. At this point I have doubts about the predictive capability. I'm going to give it a few more goes.

 

I'm using a moving average difference for the main signal, so that's 2 rules. Then I added an upper & lower threshold, that's 2 more. I think that's too many. The reason is in some of the optimizations (3-4 years, 100+ trades) I'd have moving averages like 5,6 and other times 7,5. This didn't make sense because having a faster average slower than the slow (inverting them) would effectively inverse all the signals. So I got suspicious.

 

I think I need to find a way to make an indicator without using 2 moving averages. It's too much curve fitting I think.

 

any ideas?

Share this post


Link to post
Share on other sites
Thanks for the feedback. I did a lot of forward testing this weekend. What I found was that performance going forward was pretty good until the past few years. Then even if I reoptimized it didn't walk forward well. i think it's due to changing from bull to bear and from the increased volatility. At this point I have doubts about the predictive capability. I'm going to give it a few more goes.

 

I'm using a moving average difference for the main signal, so that's 2 rules. Then I added an upper & lower threshold, that's 2 more. I think that's too many. The reason is in some of the optimizations (3-4 years, 100+ trades) I'd have moving averages like 5,6 and other times 7,5. This didn't make sense because having a faster average slower than the slow (inverting them) would effectively inverse all the signals. So I got suspicious.

 

I think I need to find a way to make an indicator without using 2 moving averages. It's too much curve fitting I think.

 

any ideas?

 

I do have a lot of ideas. :) I wish I had more time to experiment and build systems. But let me say this…

 

In my limited experience attempting to create a trading system with moving averages is very difficult. You can make strategies from basic indicators, but it's hard to do and can result in curve fitting. Try using common indicators in a different way - ways in which most people don't use them. For example, RSI is often used to highlight overbought and oversold conditions. Try using it as a trend indicator. This is just an example.

 

Price patterns are another way to go. Price breaking out from trading ranges or price behavior around opening day gaps are examples of trading without indicators.

 

In short, to make money in automated systems you are either 1) trend following or 2) trend fading. Decide what you want to do and focus on markets and market sessions that are favorable to those conditions. Your trading system does not need to trade all day or even every day. My best system trades about once a month as it fades extreme moves on a 5-minute chart. So be picky.

 

I think it's interesting to note that you stated " This didn't make sense because having a faster average slower than the slow (inverting them) would effectively inverse all the signals. So I got suspicious. "

 

Sounds like fading your original signal is a better idea. In other words, using your moving averages in a method that is "unusual" may produce better results than your original concept.

Share this post


Link to post
Share on other sites

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.

Guest
Reply to this topic...

×   Pasted as rich text.   Paste as plain text instead

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.


  • Topics

  • Posts

    • How's about other crypto exchanges? Are all they banned in your country or only Binance?
    • Be careful who you blame.   I can tell you one thing for sure.   Effective traders don’t blame others when things start to go wrong.   You can hang onto your tendency to play the victim, or the martyr… but if you want to achieve in trading, you have to be prepared to take responsibility.   People assign reasons to outcomes, whether based on internal or external factors.   When traders face losses, it's common for them to blame bad luck, poor advice, or other external factors, rather than reflecting on their own personal attributes like arrogance, fear, or greed.   This is a challenging lesson to grasp in your trading journey, but one that holds immense value.   This is called attribution theory. Taking responsibility for your actions is the key to improving your trading skills. Pause and ask yourself - What role did I play in my financial decisions?   After all, you were the one who listened to that source, and decided to act on that trade based on the rumour. Attributing results solely to external circumstances is what is known as having an ‘external locus of control’.   It's a concept coined by psychologist Julian Rotter in 1954. A trader with an external locus of control might say, "I made a profit because the markets are currently favourable."   Instead, strive to develop an "internal locus of control" and take ownership of your actions.   Assume that all trading results are within your realm of responsibility and actively seek ways to improve your own behaviour.   This is the fastest route to enhancing your trading abilities. A trader with an internal locus of control might proudly state, "My equity curve is rising because I am a disciplined trader who faithfully follows my trading plan." Author: Louise Bedford Source: https://www.tradinggame.com.au/
    • SELF IMPROVEMENT.   The whole self-help industry began when Dale Carnegie published How to Win Friends and Influence People in 1936. Then came other classics like Think And Grow Rich by Napoleon Hill, Awaken the Giant Within by Tony Robbins toward the end of the century.   Today, teaching people how to improve themselves is a business. A pure ruthless business where some people sell utter bullshit.   There are broke Instagrammers and YouTubers with literally no solid background teaching men how to be attractive to women, how to begin a start-up, how to become successful — most of these guys speaking nothing more than hollow motivational words and cliche stuff. They waste your time. Some of these people who present themselves as hugely successful also give talks and write books.   There are so many books on financial advice, self-improvement, love, etc and some people actually try to read them. They are a waste of time, mostly.   When you start reading a dozen books on finance you realize that they all say the same stuff.   You are not going to live forever in the learning phase. Don't procrastinate by reading bull-shit or the same good knowledge in 10 books. What we ought to do is choose wisely.   Yes. A good book can change your life, given you do what it asks you to do.   All the books I have named up to now are worthy of reading. Tim Ferriss, Simon Sinek, Robert Greene — these guys are worthy of reading. These guys teach what others don't. Their books are unique and actually, come from relevant and successful people.   When Richard Branson writes a book about entrepreneurship, go read it. Every line in that book is said by one of the greatest entrepreneurs of our time.   When a Chinese millionaire( he claims to be) Youtuber who releases a video titled “Why reading books keeps you broke” and a year later another one “My recommendation of books for grand success” you should be wise to tell him to jump from Victoria Falls.   These self-improvement gurus sell you delusions.   They say they have those little tricks that only they know that if you use, everything in your life will be perfect. Those little tricks. We are just “making of a to-do-list before sleeping” away from becoming the next Bill Gates.   There are no little tricks.   There is no success-mantra.   Self-improvement is a trap for 99% of the people. You can't do that unless you are very, very strong.   If you are looking for easy ways, you will only keep wasting your time forgetting that your time on this planet is limited, as alive humans that is.   Also, I feel that people who claim to read like a book a day or promote it are idiots. You retain nothing. When you do read a good book, you read slow, sometimes a whole paragraph, again and again, dwelling on it, trying to internalize its knowledge. You try to understand. You think. It takes time.   It's better to read a good book 10 times than 1000 stupid ones.   So be choosy. Read from the guys who actually know something, not some wannabe ‘influencers’.   Edit: Think And Grow Rich was written as a result of a project assigned to Napoleon Hill by Andrew Carnegie(the 2nd richest man in recent history). He was asked to study the most successful people on the planet and document which characteristics made them great. He did extensive work in studying hundreds of the most successful people of that time. The result was that little book.   Nowadays some people just study Instagram algorithms and think of themselves as a Dale Carnegie or Anthony Robbins. By Nupur Nishant, Quora Profits from free accurate cryptos signals: https://www.predictmag.com/    
    • there is no avoiding loses to be honest, its just how the market is. you win some and hopefully more, but u do lose some. 
    • $CSCO Cisco Systems stock, nice top of range breakout, from Stocks to Watch at https://stockconsultant.com/?CSCOSEPN Septerna stock watch for a bottom breakout, good upside price gap
×
×
  • Create New...

Important Information

By using this site, you agree to our Terms of Use.