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.

UrmaBlume

Make It Adaptive

Recommended Posts

What is present in many commercial automated systems and missing from almost all "retail" developed and operated automated systems is that the retail systems are not adaptive.

 

So many retail traders have done the tremendous amount of work to develop, backtest and optimzie a profitable trading system only to see if work for a while and then fail. This failure is oftentimes not a failure of concept but a failure to make the parameters of the system adaptive/responsive to current/changing market conditions.

 

For us this is basically a 2 step process - first we take our measure of the maket from the most appropriate of many inputs and then the software makes the appropriate adjustments to system parameters. Different inputs from different time frames adjust different paramters.

 

Our read of current market conditions is just about the only place where we use time charts. The chart below is our measure of the percentage of average commercial commitment to the market in 6 different time frames ranging from 2 minutes to 405 minutes.

 

All of our inputs are normalized for time of day. We divide the day into 405 (the length of the day session in minutes) segments for EACH time frame. For example we take a reading of commercial commitment for 60 minutes at 1130 that reading is compared to the average of the 60 minute value at 1130 for the previous 62 trading days. At ll31 we do it again and we do it for each of 12 time frames in at least six different indicators.

 

We display some of these measure of market condition in the HUD.

 

We consider the percentage of commercial commitment shown below as well as total volume, price ranges and certain internals from different exchanges. All of these inputs/measures of current market conditions are normalized for time of day and scaled to percentages of average to facilitate their inputs to certain predictive technologies such as genetically optimized neural networks and MARS (Multivariate Adaptive Regression Splines) from Salford Systems in San Diego. Of note is that after training and development an easily constructed script can auto convert the MARS function to Easy Language for quick and easy deployment and real-time predictions.

 

Different levels of these indicators make adjustments to parameters such as speed and phase adjustments to different data smoothers such as the JMA as well as stop losses, price and volume targets and take profits.

 

If you want it to last - that is, if you want it to Live Long and Prosper then make it adaptive.

 

adaptive1.jpg

Share this post


Link to post
Share on other sites
didn't Darwin say something like that?

 

You are right again Tams and so was Darwin.

 

We have seen a lot of systems and this lack of adaptive parameter settings is a VERY common weakness. Adaptive - not optimized.

Share this post


Link to post
Share on other sites

UB, we struggled with adaptivity via time of day for quite a while… surprised you find it useful… finally went back exclusively with MarketTyping algo’s that are good around the clock and applicable to any instrument… use it to move the weighting of systems around much more than to push parameters though...

Share this post


Link to post
Share on other sites
UB, we struggled with adaptivity via time of day for quite a while… surprised you find it useful… finally went back exclusively with MarketTyping algo’s that are good around the clock and applicable to any instrument… use it to move the weighting of systems around much more than to push parameters though...

 

The efficacy of time of day normalization depends on the input - for some it adds value and others not. As to the weighting of systems within a family of systems all trading the same market we consider that to be just another parameter along with those mentioned.

 

What you said, well DUH ZDO

UrmaBlume, well, DUH... ;)zdo

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

    • Why not to simply connect you account to myfxbook which will collect all this data automatically for you? The process you described looks tedious and a bit obsolete but may work for you though.
    • The big breakthrough with AI right now is “natural language computing.”   Meaning, you can speak in natural language to a computer and it can go through huge data sets, make sense out of them, and speak back to you in natural language.   That alone is a huge breakthrough.   The next leg? AI agents. Where they don’t just speak back to you.   They take action. Here’s the definition I like best: an AI agent is an autonomous system that uses tools, memory, and context to accomplish goals that require multiple steps.   Everything from simple tasks (analyzing web traffic) to more complex goals (building executive briefings or optimizing websites).   They can:   > Reason across multiple steps.   >Use tools like a real assistant (Excel spreadsheets, budgeting apps, search engines, etc.)   > Remember things.   And AI agents are not islands. They talk to other agents.   They can collaborate. Specialized agents that excel at narrow tasks can communicate and amplify one another’s strengths—whether it’s reasoning, data processing, or real-time monitoring.   What it Looks Like You wake up one morning, drink your coffee, and tell your AI agent, “I need to save $500 a month.”   It gets to work.   First, it finds all your recurring subscriptions. Turns out you’re paying $8.99 for a streaming service you forgot you had.   It cancels it. Then it calls your internet provider, negotiates a lower bill, and saves you another $40. Finally, it finds you car insurance that’s $200 cheaper per year.   What used to take you hours—digging through statements, talking to customer service reps on hold for an hour, comparing plans—is done while you’re scrolling Twitter.   Another example: one agent tracks your home maintenance needs and gets information from a local weather-monitoring agent. Result: "Rain forecast next week - should we schedule gutter cleaning now?"   Another: an AI agent will plan your vacations (“Book me a week in Italy for under $2,000”), find the cheapest flights, and sort out hotels with a view.   It’ll remind you to pay bills, schedule doctor’s appointments, and track expenses so you’re not wondering where your paycheck went every month.   The old world gave you tools—Excel spreadsheets, search engines, budgeting apps. The new world gives you agents who do the work for you.   Don’t Get Too Scared (or Excited) Yet William Gibson famously said: "The future is already here – it's just not evenly distributed."   AI agents will distribute it. For decades, the tools that billionaires and corporations used to get ahead—personal assistants, financial advisors, lawyers—were out of reach for regular people.   AI agents could change that.   BUT, remember…   We’re in inning one.   AI agents have a ways to go.   They’re imperfect. They mess up. They need more defenses to get ready for prime time.   To be sure, AI is powerful, but it’s not a miracle worker. It’s great at helping humans solve problems, but it’s not going to replace all jobs overnight.   Instead of fearing AI, think of it as a tool to A.] save you time on boring stuff and B.] amplify what you’re already good at. Right now is the BEST time to start experimenting. It’s also the best time to find investments that will “make AI work for you”. Author: Chris Campbell (AltucherConfidential)   Profits from free accurate cryptos signals: https://www.predictmag.com/     
    • What a wild year.   AI seems to be appearing everywhere you look, Paris hosted a weird Olympics, unrest continues in the Middle East, the US endured a crazy-heated election, and the largest rocket ever to fly successfully landed in a giant pair of robot arms.   Okay, but what about the $money stuff?   Well, this year we've seen a load of uncertainty - inflation is still biting and many businesses have gone down.   Property has been very fractured, with developments becoming prohibitively expensive, while other markets have boomed.   It hasn't been an easy ride, that's for sure.   However, the stock market has had some outstanding results, and for those who know how to trade, some have done VERY well for themselves.   Some have replaced their incomes. Some have set themselves up for the rest of their days on this planet.   How about you? How did you go? Author: Louise Bedford    Profits from free accurate cryptos signals: https://www.predictmag.com/  
    • U Unity Software stock watch, attempting to move higher off the 22.4 triple+ support area at https://stockconsultant.com/?U  
    • TSSI TSS stock, watch for an ascending triangle breakout above 11.49, target 15 area at https://stockconsultant.com/?TSSI
×
×
  • Create New...

Important Information

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