Dear Esteemed Members, I want to share my trades with you. I trade stocks, crypto, forex, energy, and commodities. What's your convention on the number of journals? Should I open a journal for every market, or should I open one journal for all my trades? Kind regards, Ely
It depends how many strategies you apply. If you trade the same strategies to all instruments then one journal is better, because it can be better compared the performance among different instruments with the same strategy.
If you're looking to sell your TA signals, then the more noise you make to more $$ you earn... (hey, nuet persoenlich, aber i dem forum wirsch du kchei kunde finde, fill zu fill negatevi kundschaft, hat zu fill spammer kha da im forum.... schoen zghoere das es in zueri trader hat, noet nur banke....)
Just one should suffice. Don't try to beat the record number of Journals. @expiated as > 45 journals! We don't like to see redundant, non-value-added new threads.
Hey, Thank you very much. (I ha Erfahrig im Leite vo finanzielle Institutione. ^_^ Aber ich bin idem Forum als Person und für persönlichi Zweck igstiege. Ich schätz dini Einsichte i dä Gemeinschaft.) - I use a large scale of strategies, instruments, and timeframes. If I opened a new journal for the different methods, it would rapidly scale above 45. But I won't beat that. From your replies, I understand the community would like to read about my many strategies in one thread. I could use the AI strategy as a frame because I manage all these methods with AI and then break them down into various techniques within one journal. - But I've got more questions. Do you prefer short journal updates that you can read fast or longer, more detailed explanations?
I think you should describe what is behind this AI, meaning what are the inputs with what is the AI feeded, for your own interests too. Because from my experience only people use AI who do not know much about the markets. Because everyone who has deep knowledge sees no need to use an AI, because the framework within can be tested and optimized easily. Second, everyone with a deeper understanding of the markets, want also the outcome to be analyzed still by a "human", because only if you really understand what is behind the strategy and how it is found and created you can gain trust on this which you need in critical times when the bigger drawdowns of this strategy are happening. I have not seen any serious trader/investor who just trust AI or do not want to understand what is behind all of it. But the matter with AI is, that it cannot be really understood how a solution is found by the AI and how the strategy was really created. Because everything needs to have a meaning when applying something and creating a strategy. If it is not sound from the beginning to the end, the result is very likely not what you want (and not speaking of the realime tracking performance afterwards only). So far I have not seen any good AI applied on financial markets.
You described AI, but I use XAI. It's a different AI. The field of Explainable AI (XAI) encompasses AI systems capable of providing insights into their decision-making processes, bridging the gap between input and output analysis. In my XAI, I use interpretable models. My model cross-checks decision trees, linear regression, and rule-based systems. People might use one or another, but my model exploits all of these methods to correct the errors of one with another. Permutation Importance and Partial Dependence Plots contribute to weighting the different models to create a new model. It's different than using any one of the mentioned techniques. I share your view about the importance of post-hoc explanation techniques, and that's why I trained my XAI to do post-explanation with LIME (Local Interpretable Model-Agnostic Explanations) and SHAP (SHapley Additive exPlanations). You mentioned drawdown. My XAI can explain Maximum Drawdown with two techniques I wrote above: LIME and SHAP. The XAI uses LIME to explain factors contributing to a specific maximum drawdown event, identifying influential features like market volatility or portfolio composition. SHAP quantifies the impact of each feature on the drawdown, revealing those most responsible for the loss. In the end, I didn't burn my CFA certificate, and I didn't suggest it. There's a reason I've got companies with employed portfolio managers, but still, I'm here in person and writing my personal opinion in my free time. I love market analytics, and I'll do it no matter what. But AI helps me solve monotonous tasks. - I can have fun trading.
Okay. Then I would suggest that your reporting in your journal(s) is concentrating on currencies and most liquid futures as there is the most liquidity. You need to consider that you are anticipating what others are doing when you let test your XAI to find something. So here any edge should be last to be vanished which should be also important for you as you want to profit from your findings as long as possible. You should also consider that any found edge can be reengineered when you post too much trade details. So be careful here in your own interest.
We already have one member who has like a dozen different journals. We don't need another. Keep it tidy.
I think you need to have different journals. You might be talented to predict currency pairs based on the news, but it might not work on cryptos! Have different journals.