Dump it Here

[Richard Dale]

@dis4ever - Yep, the blind faith of asking any GenAI to provide any sort of financial "advice" (aka stock selections) is akin to putting your trust in a model that will postdictively change without you knowing because it has newer samples.

It's akin to somebody saying (after the fact) that they would have shorted the market prior to Covid/GFC/Tech Boom etc.

But it also has various "stale" information being incorporated too - not too dissimilar to fundamentals.

This is where it's very important to understand the staleness of the information being presented/used. If you have no visibility of the source data staleness then you're just throwing darts.

None of this is particuarly new - I have a good friend who is at the top tier of managerial level for a major (well top 30 worldwide, actually much higher but I won't say any further) mining firm that, several years ago, said they were incorporating heuristics to interpet verbal mining shift managers reports to identify anomalies versus production levels. Production levels, for the shift, might be with parameters but if they shift manager went "off-script" versus their usual reports, it was a sign that things needed to be looked at from an operational perspective before it became a signficant problem. The "off-script" was a very basic keyword system (eg. total amount of swear wods) intially but moved to sentiment analysis fairly quickly.

Interpretation of earnings calls meetings has also progressed along these lines, but the companies are also cognisant of this too.

Interesting times.

 

[Skate]

@dis4ever - Yep, the blind faith of asking any GenAI to provide any sort of financial "advice" (aka stock selections) is akin to putting your trust in a model that will postdictively change without you knowing because it has newer samples.

It's akin to somebody saying (after the fact) that they would have shorted the market prior to Covid/GFC/Tech Boom etc.

But it also has various "stale" information being incorporated too - not too dissimilar to fundamentals.

This is where it's very important to understand the staleness of the information being presented/used. If you have no visibility of the source data staleness then you're just throwing darts.

None of this is particuarly new - I have a good friend who is at the top tier of managerial level for a major (well top 30 worldwide, actually much higher but I won't say any further) mining firm that, several years ago, said they were incorporating heuristics to interpet verbal mining shift managers reports to identify anomalies versus production levels. Production levels, for the shift, might be with parameters but if they shift manager went "off-script" versus their usual reports, it was a sign that things needed to be looked at from an operational perspective before it became a signficant problem. The "off-script" was a very basic keyword system (eg. total amount of swear wods) intially but moved to sentiment analysis fairly quickly.

Interpretation of earnings calls meetings has also progressed along these lines, but the companies are also cognisant of this too.

Interesting times.

@Richard Dale, you raise some excellent points.

Hindsight bias and staleness of free “AI”data is a significant challenge if you use it in your decision-making process.

IMHO, “AI” should be seen as a supplement to the process rather than a substitute.

Skate.

 

[Skate]

Critical thinking rather than as a definitive solution

I find that “AI” is a great tool when thoughts need answers. The responses it provides help refine and hone the next question, guiding the thought process rather than replacing it.

Skate.

 

[Richard Dale]

IMHO, “AI” should be seen as a supplement to the process rather than a substitute.

Aka "I'm going to supplement my decision process with information from an opaque source with undefined sources with varying degress of unknowable staleness"

Good luck! LOL.

 

[Skate]

Aka "I'm going to supplement my decision process with information from an opaque source with undefined sources with varying degress of unknowable staleness"

Good luck! LOL.

@Richard Dale, you make another great point.

However, the same argument could be made about any gathered information whether from news reports, expert opinions, or even traditional research.

Every source has its own biases, limitations, and degrees of “unknowable staleness.”

The key is to approach all information critically and weigh it appropriately in the decision-making process.

Skate.

 

[Richard Dale]

The key is to approach all information critically and weigh it appropriately in the decision-making process.

You clearly can't make any consistent decisions with your historically unverifiable approach (with motherhood vibes).

Quid pro quo - lol.

 

[divs4ever]

You clearly can't make any consistent decisions with your historically unverifiable approach (with motherhood vibes).

Quid pro quo - lol.

inaccurate data ( or stale data ) has always been problematic in research , but if using AI one might be tempted to ignore the potential inaccuracies in sourced data ,

possible work-arounds are running the AI two of three times but using a different data source for each run and look for disagreement in the results

AI is basically a fancy version of computer chess , you have the current position and the program needs to analyze the probable next moves and ( try to ) select the best foreseeable outcome , BUT how does AI cope with 'black swans ' , maybe AI does better in giving options after an unexpected event ( when the average trader/human is paralyzed with indecision

maybe expecting AI to give you a solution is the wrong application of it , maybe we should be asking it for a range of potential outcomes and options for the next step in each , in theory the best asset of AI is the removal of human emotions in the situation analysis

BTW i have had some nice outcomes using straight instinct ( automatic reaction ) but i am aware others are not so good at that

 

[TimeISmoney]

AI is just a man-made machine; if you use it for the purpose it was intended, you shouldn't have too many issues.

It's like a washing machine, if you just plonk the clothes in there and overload it and don't level it properly from the start it will never do its job properly because you're using it out of its parameters of design.

 

[Skate]

The Dangers and Pitfalls of Coding a Trading Strategy with Limited Experience
Many aspiring traders believe purchasing a charting program like Amibroker and data from Norgate, then coding or buying a strategy is the key to easy profits. However, the reality is far more complex and filled with potential pitfalls. Here are some critical points to consider:

Correct Coding
Ensuring your strategy is coded correctly is essential and it's harder than it sounds. Even a minor error can lead to significant losses. Understanding every aspect of the code functionality is required to avoid costly mistakes. Refining your code should be an ongoing process, as continuous improvement is key to long-term success.

Backtesting Limitations
Backtesting is a valuable tool but has inherent limitations. Historical data offers insights, but it doesn’t guarantee future performance. Market conditions evolve, and what worked in the past may "fail in the future". Approach backtesting with caution, and validate your results across various market scenarios to ensure robustness.

Mindset and Drawdowns
Trading with real money is vastly different from paper trading. Large drawdowns will test your emotional discipline in sticking to your strategy during tough times. Emotional control often determines whether a trader succeeds or fails.

Insights from Experts
@Richard Dale's participation in the “Dump it Here” thread offers a unique opportunity to gain insights from someone with decades of experience. His contributions always provide invaluable insights that offer a valuable framework for traders at any level.

Moving Beyond the Basics
As your experience grows, it’s essential to go beyond simple backtesting. Forward testing with both in-sample and out-of-sample data is crucial for evaluating the robustness of your strategy. Carefully consider the length of your backtest as "shorter tests" may miss key market shifts, while "longer tests" could incorporate outdated conditions.

Skate.

 

[Skate]

Trading versus Investing: A Balancing Act of Risk and Reward
Investing and trading offer two distinct paths as one provides steady, consistent returns with minimal involvement, while the other promises potentially higher rewards at the cost of greater risk and volatility.

Over the past year
Investing has proven beneficial, yielding returns with little effort or excitement. It’s a calm, passive approach that can sometimes feel like being a spectator, watching from the sidelines rather than actively participating in the game.

As the new year approaches
I’m at a crossroads - should I stick with my current investment portfolio, enjoying the stability it offers, or dive back into trading, where the thrill of the market comes with both higher stakes and the potential for greater rewards?

At times good enough is good enough
I've refined my approach and the initial results aren't too shabby.

Backtest
Using Amibroker and Norgate "Current & Past" Data.






Skate.

 

[divs4ever]

the temptation ( for some ) is to reduce the holdings ( some or all ) in the months where the falls were 5% or more

there would be some urging you to buy ( something ) in those two DOWN months , now sure buying something ( carefully ) in May 2023 might have improve the returns ( say be using dividends to boost selected discounted socks ) but what of June 2024 , although the drop was worse , the aggregate holdings would have fallen from a higher peak ( and might not have been bargains

selling in May and returning in September might not have been a great strategy in 2023 and 2024 with ASX listed stocks

but with investing all you can do is buy , assess and adjust if needed ( or desired )

 

[TimeISmoney]

It's days like this that I'm happy that I've held stocks that pay decent dividends, money isn't stuck there idling and doing nothing.

 

[Skate]

It's days like this that I'm happy that I've held stocks that pay decent dividends, money isn't stuck there idling and doing nothing.

@TimeISmoney, let’s put today's results into perspective.

Admittedly, today wasn’t kind to most traders:

XAO: 8,415.00 (-1.68%)
XJO: 8,168.20 (-1.70%)

However, price fluctuations are a feature traders can leverage. While investors ride out these fluctuations, focusing on long-term performance, traders can capitalise on short-term movements. Panic selling often creates opportunities. The charts below illustrate that today’s market behaviour isn’t unusual when you hold quality positions in your portfolio.

Looking at the last weekly bar on the charts, most would wonder what all the fuss was about today. Trading is a long-term endeavour.


















Skate.

 

[Skate]

Share Trade Tracker v3.6.2 Released!
The new version of Share Trade Tracker, v3.6.2, introduces a new approach to updating EOD prices. This update completely removes the Yahoo Data Source and replaces it with an external file system to maintain End-of-Day (EOD) prices for your positions.

Key Update:
New Pricing Approach: The Yahoo Data Source has been replaced. You can create and maintain an external file to store EOD prices for all your positions.

Important Instructions for Previous Yahoo Data Source Users:
If you’ve used the Yahoo Data Source in the past, please follow the special instructions provided to transition to the new system. This update allows you to load the external file with your positions or any relevant additional data. For detailed instructions and support, visit the support pages:

Share Trade Tracker v3.6.2

Share Trade Tracker v3.6.2

Download the file below to access your copy of Share Trade Tracker With this new version of Share Trade Tracker there are special instructions for any users that have used the Yahoo Data Source in the past. The Yahoo Data Source has been repl...

xlautomation.freshdesk.com

Share Trade Tracker - The Chartist v3.6.2

Share Trade Tracker The Chartist v3.6.2

Download the file below to access your copy of Share Trade Tracker With this new version of Share Trade Tracker there are special instructions for any users that have used the Yahoo Data Source in the past. The Yahoo Data Source has been repl...

xlautomation.freshdesk.com

Skate.

 

[dyna]

the temptation ( for some ) is to reduce the holdings ( some or all ) in the months where the falls were 5% or more

there would be some urging you to buy ( something ) in those two DOWN months , now sure buying something ( carefully ) in May 2023 might have improve the returns ( say be using dividends to boost selected discounted socks ) but what of June 2024 , although the drop was worse , the aggregate holdings would have fallen from a higher peak ( and might not have been bargains

selling in May and returning in September might not have been a great strategy in 2023 and 2024 with ASX listed stocks

but with investing all you can do is buy , assess and adjust if needed ( or desired )

Yeah , stay invested and yet , have plenty of cash at hand .

That's what the Buffetts of this world , basically do .

Can you imagine the stress of swinging in and out of good dividend paying shares , then having the headache of paying out the accumulated capital gains tax and then to be stuck with a humongous pile of cash , waiting for THE right moment , to dive back in again ?

May as well get out of flammin' markets altogether and go spend it all , I say .

 

[farmerge]

Yeah , stay invested and yet , have plenty of cash at hand .

That's what the Buffetts of this world , basically do .

Can you imagine the stress of swinging in and out of good dividend paying shares , then having the headache of paying out the accumulated capital gains tax and then to be stuck with a humongous pile of cash , waiting for THE right moment , to dive back in again ?

May as well get out of flammin' markets altogether and go spend it all , I say .

@dyna It's a hard one to get right.
But the Buffetts of the world don't/can't be worrying about capital gains and the like, they are in and out as the percentages dictate.
It would nice if we could have that on our side of the fence also.

 

[divs4ever]

Yeah , stay invested and yet , have plenty of cash at hand .

That's what the Buffetts of this world , basically do .

Can you imagine the stress of swinging in and out of good dividend paying shares , then having the headache of paying out the accumulated capital gains tax and then to be stuck with a humongous pile of cash , waiting for THE right moment , to dive back in again ?

May as well get out of flammin' markets altogether and go spend it all , I say .

some of my entry points have been so low , if they return on that stock i would be very concerned about impending bankruptcy ( as you would it a stock drops more than 90% )

in such stocks selling ( for capital gains ) and buying back higher than the original buy makes little sense to me ( most of the time , sometimes a stock does something very right and makes the higher buy justified )

 

[Bellcose]

Yeah , stay invested and yet , have plenty of cash at hand .

That's what the Buffetts of this world , basically do .

Can you imagine the stress of swinging in and out of good dividend paying shares , then having the headache of paying out the accumulated capital gains tax and then to be stuck with a humongous pile of cash , waiting for THE right moment , to dive back in again ?

May as well get out of flammin' markets altogether and go spend it all , I say .

Use it. It won't do anyone any harm.

 

[Skate]

As the new year approaches
I’m at a crossroads - should I stick with my current investment portfolio, enjoying the stability it offers, or dive back into trading, where the thrill of the market comes with both higher stakes and the potential for greater rewards?

At times good enough is good enough
I've refined my approach and the initial results aren't too shabby.

As the new year approaches
I’ve decided to embrace both investing and trading simultaneously. Why choose one over the other when I can enjoy the benefits of both? Investing for dividends and franking credits provides stability, while trading offers the thrill and potential for significant capital growth. Trading has always been kind to me, and frankly, investing can be as exciting as "watching paint dry". My records show that investing yields around 9%, but my trading returns since 2015 have been significantly higher.

This morning, while browsing the platform ‘X’
I came across an invitation to try Grok2. Intrigued, I asked Grok2 to evaluate my trading strategy for the new year. My Amibroker Strategy, which contains 1129 lines of code, was fully accepted and quickly evaluated by Grok2, something most free ‘AI’ tools can’t handle.

Grok2’s response was insightful and valuable to me, though it might not be as interesting to others. It’s been challenging to find engaging content to post about lately, but I’m excited to share the Grok2 evaluation unaltered with highlights added. General warnings are displayed in red.

As the new year approaches
I’ve decided to embrace both investing and trading simultaneously. Why choose one over the other when I can enjoy the benefits of both? Investing for dividends and franking credits provides stability, while trading offers the thrill and potential for significant capital growth. Trading has always been kind to me, and frankly, investing can be as exciting as "watching paint dry". My records show that investing yields around 9%, but my trading returns since 2015 have been significantly higher.

This morning, while browsing platform ‘X’
I came across an invitation to try Grok2. Intrigued, I asked Grok2 to evaluate my trading strategy for the new year. My Amibroker Strategy, which contains 1129 lines of code, was fully accepted and quickly evaluated by Grok2, something most free ‘AI’ tools can’t handle.

Grok2’s Insights: A Personal Take
Grok2’s response was insightful and valuable to me, though it might not be as interesting to others. It’s been challenging to find engaging content to post about lately, but I’m excited to share this unaltered evaluation with “warnings” highlighted in RED.

MY QUESTION to Grok2 - "Please evaluate my Amibroker Trading Strategy"
Your Amibroker Trading Strategy appears to be a comprehensive and well-thought-out approach to trading, especially tailored for weekly interval analysis. Here's an evaluation of its key components:

General Observations:
Complexity and Adaptability: The strategy incorporates multiple filters and parameters, making it highly adaptable but also complex. This could be a double-edged sword; it provides flexibility but might be overwhelming for users less familiar with Amibroker or trading algorithms.

Market and Security Selection:
Price Filter: Helps in focusing on stocks within a specific price range, which can be crucial for managing risk or targeting specific market segments.

Turnover, Volume, and Volatility Filters:
These combined filters aim to select securities with adequate liquidity and within manageable volatility, potentially reducing slippage and improving trade execution.

Trend and Momentum Analysis:
The strategy uses Exponential Moving Averages (EMA), Rate of Change (ROC), and Relative Strength Index (RSI) for entry signals, which is good for capturing trends and momentum. However, the reliance on multiple indicators might lead to over-optimization unless carefully backtested across different market conditions.

Entry and Exit Rules:
Entry Signals: Based on conditions like price above support levels, EMA crossovers, and RSI thresholds, which are traditional momentum and trend-following techniques.

Exit Strategy: Incorporates a trailing stop with different levels based on market direction, a time-based exit, and a take-profit mechanism. The use of different stop types (trailing, stale, profit take) shows a nuanced approach to risk management, which is commendable.

Risk Management:
The strategy includes parameters for setting stop-loss levels dynamically and considering position sizing based on fixed risk amounts or equity percentages. This is a strong aspect, as proper risk management can significantly impact long-term performance.

Visualization and Reporting:
Extensive use of graphical functions for title display and charts, which can enhance user interaction and decision-making. The exploration mode offers various views on trade setup and performance, which is excellent for analysis.

Potential Areas for Improvement:
Parameter Sensitivity: Given the many parameters, there's a risk of overfitting. Regular out-of-sample testing and possibly reducing the number of variables or using more robust optimization methods might mitigate this.

Backtesting and Validation:
While the code includes custom backtesting, ensuring this is done across various market conditions, including bull, bear, and sideways markets, would validate the strategy's robustness.

Execution Considerations:
The strategy's weekly timeframe might not be ideal for all markets or securities, especially in faster-moving or less liquid environments. Adjusting for different intervals or testing on different time frames could be beneficial.

Code Efficiency:
The use of loops for performance-sensitive tasks like updating arrays could potentially be optimized using vector operations if possible, to increase speed in backtesting or real-time analysis.

Debugging and Logging:
More extensive logging could help in diagnosing issues during live trading or backtesting, especially for complex logic like the stop calculations.

Conclusion:
Overall, your strategy is detailed and seems designed with a good balance of trend following, momentum capture, and risk management. The key to success will be in rigorous testing, perhaps with some simplification of parameters to avoid overfitting, and continuous adjustment based on market feedback. Also, consider how this strategy performs in different market environments and possibly how it could be adjusted for different securities or market types.

Skate.

 

[divs4ever]

As the new year approaches
I’ve decided to embrace both investing and trading simultaneously. Why choose one over the other when I can enjoy the benefits of both? Investing for dividends and franking credits provides stability, while trading offers the thrill and potential for significant capital growth. Trading has always been kind to me, and frankly, investing can be as exciting as "watching paint dry". My records show that investing yields around 9%, but my trading returns since 2015 have been significantly higher.

This morning, while browsing the platform ‘X’
I came across an invitation to try Grok2. Intrigued, I asked Grok2 to evaluate my trading strategy for the new year. My Amibroker Strategy, which contains 1129 lines of code, was fully accepted and quickly evaluated by Grok2, something most free ‘AI’ tools can’t handle.

Grok2’s response was insightful and valuable to me, though it might not be as interesting to others. It’s been challenging to find engaging content to post about lately, but I’m excited to share the Grok2 evaluation unaltered with highlights added. General warnings are displayed in red.

As the new year approaches
I’ve decided to embrace both investing and trading simultaneously. Why choose one over the other when I can enjoy the benefits of both? Investing for dividends and franking credits provides stability, while trading offers the thrill and potential for significant capital growth. Trading has always been kind to me, and frankly, investing can be as exciting as "watching paint dry". My records show that investing yields around 9%, but my trading returns since 2015 have been significantly higher.

This morning, while browsing platform ‘X’
I came across an invitation to try Grok2. Intrigued, I asked Grok2 to evaluate my trading strategy for the new year. My Amibroker Strategy, which contains 1129 lines of code, was fully accepted and quickly evaluated by Grok2, something most free ‘AI’ tools can’t handle.

Grok2’s Insights: A Personal Take
Grok2’s response was insightful and valuable to me, though it might not be as interesting to others. It’s been challenging to find engaging content to post about lately, but I’m excited to share this unaltered evaluation with “warnings” highlighted in RED.

MY QUESTION to Grok2 - "Please evaluate my Amibroker Trading Strategy"
Your Amibroker Trading Strategy appears to be a comprehensive and well-thought-out approach to trading, especially tailored for weekly interval analysis. Here's an evaluation of its key components:

General Observations:
Complexity and Adaptability: The strategy incorporates multiple filters and parameters, making it highly adaptable but also complex. This could be a double-edged sword; it provides flexibility but might be overwhelming for users less familiar with Amibroker or trading algorithms.

Market and Security Selection:
Price Filter: Helps in focusing on stocks within a specific price range, which can be crucial for managing risk or targeting specific market segments.

Turnover, Volume, and Volatility Filters:
These combined filters aim to select securities with adequate liquidity and within manageable volatility, potentially reducing slippage and improving trade execution.

Trend and Momentum Analysis:
The strategy uses Exponential Moving Averages (EMA), Rate of Change (ROC), and Relative Strength Index (RSI) for entry signals, which is good for capturing trends and momentum. However, the reliance on multiple indicators might lead to over-optimization unless carefully backtested across different market conditions.

Entry and Exit Rules:
Entry Signals: Based on conditions like price above support levels, EMA crossovers, and RSI thresholds, which are traditional momentum and trend-following techniques.

Exit Strategy: Incorporates a trailing stop with different levels based on market direction, a time-based exit, and a take-profit mechanism. The use of different stop types (trailing, stale, profit take) shows a nuanced approach to risk management, which is commendable.

Risk Management:
The strategy includes parameters for setting stop-loss levels dynamically and considering position sizing based on fixed risk amounts or equity percentages. This is a strong aspect, as proper risk management can significantly impact long-term performance.

Visualization and Reporting:
Extensive use of graphical functions for title display and charts, which can enhance user interaction and decision-making. The exploration mode offers various views on trade setup and performance, which is excellent for analysis.

Potential Areas for Improvement:
Parameter Sensitivity: Given the many parameters, there's a risk of overfitting. Regular out-of-sample testing and possibly reducing the number of variables or using more robust optimization methods might mitigate this.

Backtesting and Validation:
While the code includes custom backtesting, ensuring this is done across various market conditions, including bull, bear, and sideways markets, would validate the strategy's robustness.

Execution Considerations:
The strategy's weekly timeframe might not be ideal for all markets or securities, especially in faster-moving or less liquid environments. Adjusting for different intervals or testing on different time frames could be beneficial.

Code Efficiency:
The use of loops for performance-sensitive tasks like updating arrays could potentially be optimized using vector operations if possible, to increase speed in backtesting or real-time analysis.

Debugging and Logging:
More extensive logging could help in diagnosing issues during live trading or backtesting, especially for complex logic like the stop calculations.

Conclusion:
Overall, your strategy is detailed and seems designed with a good balance of trend following, momentum capture, and risk management. The key to success will be in rigorous testing, perhaps with some simplification of parameters to avoid overfitting, and continuous adjustment based on market feedback. Also, consider how this strategy performs in different market environments and possibly how it could be adjusted for different securities or market types.

Skate.

multiple variations of your code perhaps , possibly adapted to the time-frames you wish to trade that stock ?

but then that relies on you correcting predicting the current market ( ie volatile , or low liquidity , or the current trend )