No, not at all, given the context of stock trading. Stocks do not trade the same way today as they did in 2014. Similarly there is no point in using trading data from the 1850s given that that kind of market with those kinds of traders will never ever exist again. You can only pick a few recent months or weeks to capture current trading sentiment/technique and even then everything could get blown away after the next rate hike or international incident.
Generally I don't think there is any alpha in training transformers to predict the next price point just given historical price data, because the price is determined by humans (and algorithms trained on data generated by humans) that react to news. If you can predict the news, you can probably predict stock prices, but if you could predict the future you'd have AGI and not some dingy time series calculator.
It's complicated; that's why there isn't a one-size-fits-all solution. In the end, you want to have a good execution plan, and there's usually not just one and the same action to achieve that.
>As someone with a good amount of professional experience both as a developer and a designer, I'm consistently surprised by how quick so many developers are to assume their personal usage habits, osmosis-gained knowledge from projects, and folk wisdom about design trumps the expertise of seasoned credentialed professionals in the field.
Exactly! Too many people think that their personal preference is the best. Sometimes, the best solution is to have plain HTML where the user chooses their favorite font and size, like in the early Netscape era. However, that's not always the case.
My background is the opposite; I'm a mediocre software engineer but have quite good people skills. I'm experienced enough to know what takes time and which parts of the system are more critical than others. I have a few senior engineers whom I really listen to carefully and to whom I give a lot of trust and empowerment. I don't make design decisions, they do and I give input. I take responsibility when we fail (and learn from it) and give the team credit when we succeed. In my humble opinion, being a manager is more about people than anything else.
I like to think I'm a good fit, but of course, I need to improve my skills, like anyone else. At the end of the day, we are working with people, and there's no one-size-fits-all solution. Sometimes the most skillful engineer is the best fit for the EM position. However, I truly believe that to get the best output, you want team members to commit as a group and to feel that it's rewarding to achieve goals and have personal development. Unfortunately, not everyone has the luxury of a long-term perspective.
