successful algo strategy

[MarkBrown]

Now I see why you can't make it in trading...

he or rather "it" can't count very well lol

 

[nsnyc]

he can't count very well lol

How do you know it's a he? Did Oddball tell you?

 

[MarkBrown]

How do you know it's a he? Did Oddball tell you?

f#ckin fixed it have a look, lol.

 

[themickey]

...... which generally hints there are mysterious price patterns in random walks everywhere......

Ya, not much price patterns and logic in a maze.

 

[ValeryN]

Hi guys, newbie here. I have been into algo trading for a while now and I'm at the point where I start wondering if it's possible to build something that is profitable over long time.
I have built few models in Python for stocks on several exchanges (US, Europe) and all of them predict the next day's closing price based on the data from the past. The accuracy is fine on the test set etc... but in real life it doesn't work. Another prove of efficient market theory. And if I just think logical it does make sense. Data from the past just doesn't say anything about today because today is already incorporating future.
This made me think about the model features. If there would be no limitations, what features would I choose for the model.
The price at the moment is a reflection of ask and bid. Is there any place where we can get this? Obviously there is the order book, but that is already status from the past, so according to EMT it's already affecting the price. People submitting the orders is the point where future price is being created. This means that brokers have possible advantage. The bigger the broker (market share) the better their data is. I think crypto manipulation by exchanges shows this as well. What do you think? Is this the only possible way to really predict future price correct over a long period?

While I am not a big fan of Van Tharp, but there is one thing he put very well - you experience whatever you believe in, unless you don't, in which case you won't, which means that you do.

Some popular examples - market is efficient / its' zero sum game / those who success are statical flukes / market is rigged / "HTF rob us all anyway" are all believes you can choose to believe in. If you do, that becomes your reality that reinforces itself.

I have built few models in Python for stocks on several exchanges (US, Europe) and all of them predict the next day's closing price based on the data from the past. The accuracy is fine on the test set etc... but in real life it doesn't work

If your model falls apart after launch the reasons for that are pretty finite and fall under two categories - model is no good or your executions are not matching the model.

If you run automated trading operation those are really the only 2 things to look at.
(a) Is your model staying within reasonable boundaries according to your original expectations
(b) Are your life executions matching your model

Most popular reasons for trading systems to fail in live trading are:

1. It was over-optimized and/or never tested out of sample
2. It has a bug (use unknown data at the time, trading outside of data bars etc)
3. Data quality is not good
4. Your cost estimates are incorrect
5. Your execution feasibility assumptions are incorrect (lack of liquidity/not supported orders by broker/slippage etc)
6. Market has fundamentally changed (probably the very last and rare reason for most people)

If you are willing to push forward you need to determine where your problem is exactly and keep iterating.

But realistically, doing something else might provide better return on your time, especially if you don't have sufficient capital to benefit from realistic returns.

PS. My journal about automated stocks trading. Rob Carver writes about automated futures trading.

Val

 

[easymon1]

that becomes your reality that reinforces itself.

...so, rig it in your own favor.
Privatize the Profits, Socialize the Losses.
bailout baby.

 

[Steve Alexander]

That's almost religious. I'm more into facts. Is there anyone who has successfully built a strategy which works over a long period, except hft which obviously falls outside the EMT?
Btw, I'm not new in this. I have been around with data for 20 years. Wouldn't last that long without passion.

I've been trading over 50 years. Two years ago, I started tweeting my live trades the day before I made them. I use a simple algorithm I have never sold to find trades. My profit after one year was 145%. In June, 2020, I started another experiment, still tweeting every trade, the day before I make it. That account is up 76% since June. Bottom line: It can be done. My Twitter handle is @RandomFour in case you want to see the trades.