Jump to content
Search In
  • More options...
Find results that contain...
Find results in...

Training Trading AI

DISCLAIMER : I know almost nothing about ML.

 

Where can I get data to train the AI?

 

Also should I train a different AI for each market ( with the markets data) or train one with data from multiple markets?

Link to post
Share on other sites

If you plan on using this with your own money then don't. You are guaranteed to loose money, even the best of the best human stock traders can only get around 50% of their trade predictions accurate an AI can definitely not. YET.

I will recommend an NHu12s (or an NHd15 (maybe)) for your PC build. Quote or @ me @Prodigy_Smit for me to see your replies.

PSU Teir List | Howdy! A Windows Hello Alternative 

 

 

Laptop :

Legion y520 | i5 7300hq | 1050 4gb (Manual OC) | 16gb 2400Mhz cl18 | 256 GB SSD | 2tb HDD

Server:

Xeon E3 1245 | 16gb ECC ram | 256 GB SSD | 2*2tb HDD

Link to post
Share on other sites
Just now, Prodigy_Smit said:

If you plan on using this with your own money then don't. You are guaranteed to loose money, even the best of the best human stock traders can only get around 50% of their trade predictions accurate an AI can definitely not. YET.

I would guess an AI would do a lot better than humans.

Link to post
Share on other sites
9 minutes ago, Wictorian said:

I would guess an AI would do a lot better than humans.

Human-traders can follow the news, they understand motivations, they can see correlations between events, they can, to an extent, predict government-imposed regulations -- just try training basic NLP to an AI and you'll quickly see that that is a humongous task.

Hand, n. A singular instrument worn at the end of the human arm and commonly thrust into somebody’s pocket.

Link to post
Share on other sites
3 minutes ago, WereCatf said:

Human-traders can follow the news, they understand motivations, they can see correlations between events, they can, to an extent, predict government-imposed regulations -- just try training basic NLP to an AI and you'll quickly see that that is a humongous task.

Yeah, thats the biggest disadvantage, but you can follow them yourseşf and interfere in case of emergency. Besides, manhy traders just analyze the charts. They are two different categories.

Link to post
Share on other sites
Just now, Wictorian said:

I would guess an AI would do a lot better than humans.

An AI is only as good as the humans training it, and as you said yourself...

Just now, Wictorian said:

I know almost nothing about ML.

 

Don't ask to ask, just ask... please 🤨

sudo chmod -R 000 /*

What is scaling and how does it work? Asus PB287Q unboxing! Console alternatives :D Watch Netflix with Kodi on Arch Linux Sharing folders over the internet using SSH Beginner's Guide To LTT (by iamdarkyoshi)

Sauron'stm Product Scores:

Spoiler

Just a list of my personal scores for some products, in no particular order, with brief comments. I just got the idea to do them so they aren't many for now :)

Don't take these as complete reviews or final truths - they are just my personal impressions on products I may or may not have used, summed up in a couple of sentences and a rough score. All scores take into account the unit's price and time of release, heavily so, therefore don't expect absolute performance to be reflected here.

 

-Lenovo Thinkpad X220 - [8/10]

Spoiler

A durable and reliable machine that is relatively lightweight, has all the hardware it needs to never feel sluggish and has a great IPS matte screen. Downsides are mostly due to its age, most notably the screen resolution of 1366x768 and usb 2.0 ports.

 

-Apple Macbook (2015) - [Garbage -/10]

Spoiler

From my perspective, this product has no redeeming factors given its price and the competition. It is underpowered, overpriced, impractical due to its single port and is made redundant even by Apple's own iPad pro line.

 

-OnePlus X - [7/10]

Spoiler

A good phone for the price. It does everything I (and most people) need without being sluggish and has no particularly bad flaws. The lack of recent software updates and relatively barebones feature kit (most notably the lack of 5GHz wifi, biometric sensors and backlight for the capacitive buttons) prevent it from being exceptional.

 

-Microsoft Surface Book 2 - [Garbage - -/10]

Spoiler

Overpriced and rushed, offers nothing notable compared to the competition, doesn't come with an adequate charger despite the premium price. Worse than the Macbook for not even offering the small plus sides of having macOS. Buy a Razer Blade if you want high performance in a (relatively) light package.

 

-Intel Core i7 2600/k - [9/10]

Spoiler

Quite possibly Intel's best product launch ever. It had all the bleeding edge features of the time, it came with a very significant performance improvement over its predecessor and it had a soldered heatspreader, allowing for efficient cooling and great overclocking. Even the "locked" version could be overclocked through the multiplier within (quite reasonable) limits.

 

-Apple iPad Pro - [5/10]

Spoiler

A pretty good product, sunk by its price (plus the extra cost of the physical keyboard and the pencil). Buy it if you don't mind the Apple tax and are looking for a very light office machine with an excellent digitizer. Particularly good for rich students. Bad for cheap tinkerers like myself.

 

 

Link to post
Share on other sites
2 hours ago, Sauron said:

An AI is only as good as the humans training it, and as you said yourself...

 

LOL. 
How many different ways are there to train an AI? I only know anout deep learning and I suppose you give the information (price and time) and it will get the job done?

Link to post
Share on other sites
31 minutes ago, Wictorian said:

How many different ways are there to train an AI?

Practically an unlimited number of ways. See e.g. https://en.wikipedia.org/wiki/Machine_learning#Approaches -- you are completely out of your depth here. An AI isn't a magic box that you can just put numbers in and get a desired result out; you need to choose a training method that suits your needs, then choose a model that suits your needs, then figure out all the data that you need while filtering out any data that might introduce unwanted bias and so on.

Hand, n. A singular instrument worn at the end of the human arm and commonly thrust into somebody’s pocket.

Link to post
Share on other sites
1 hour ago, Wictorian said:

I suppose you give the information (price and time) and it will get the job done?

It's far from an exact science right now, typically successful models are developed by researchers over years of work where they try different techniques to improve their results.

Don't ask to ask, just ask... please 🤨

sudo chmod -R 000 /*

What is scaling and how does it work? Asus PB287Q unboxing! Console alternatives :D Watch Netflix with Kodi on Arch Linux Sharing folders over the internet using SSH Beginner's Guide To LTT (by iamdarkyoshi)

Sauron'stm Product Scores:

Spoiler

Just a list of my personal scores for some products, in no particular order, with brief comments. I just got the idea to do them so they aren't many for now :)

Don't take these as complete reviews or final truths - they are just my personal impressions on products I may or may not have used, summed up in a couple of sentences and a rough score. All scores take into account the unit's price and time of release, heavily so, therefore don't expect absolute performance to be reflected here.

 

-Lenovo Thinkpad X220 - [8/10]

Spoiler

A durable and reliable machine that is relatively lightweight, has all the hardware it needs to never feel sluggish and has a great IPS matte screen. Downsides are mostly due to its age, most notably the screen resolution of 1366x768 and usb 2.0 ports.

 

-Apple Macbook (2015) - [Garbage -/10]

Spoiler

From my perspective, this product has no redeeming factors given its price and the competition. It is underpowered, overpriced, impractical due to its single port and is made redundant even by Apple's own iPad pro line.

 

-OnePlus X - [7/10]

Spoiler

A good phone for the price. It does everything I (and most people) need without being sluggish and has no particularly bad flaws. The lack of recent software updates and relatively barebones feature kit (most notably the lack of 5GHz wifi, biometric sensors and backlight for the capacitive buttons) prevent it from being exceptional.

 

-Microsoft Surface Book 2 - [Garbage - -/10]

Spoiler

Overpriced and rushed, offers nothing notable compared to the competition, doesn't come with an adequate charger despite the premium price. Worse than the Macbook for not even offering the small plus sides of having macOS. Buy a Razer Blade if you want high performance in a (relatively) light package.

 

-Intel Core i7 2600/k - [9/10]

Spoiler

Quite possibly Intel's best product launch ever. It had all the bleeding edge features of the time, it came with a very significant performance improvement over its predecessor and it had a soldered heatspreader, allowing for efficient cooling and great overclocking. Even the "locked" version could be overclocked through the multiplier within (quite reasonable) limits.

 

-Apple iPad Pro - [5/10]

Spoiler

A pretty good product, sunk by its price (plus the extra cost of the physical keyboard and the pencil). Buy it if you don't mind the Apple tax and are looking for a very light office machine with an excellent digitizer. Particularly good for rich students. Bad for cheap tinkerers like myself.

 

 

Link to post
Share on other sites

Don't get discouraged, create a framework which can test your algorithm.  Give it actual market data and a small amount of "virtual" money and let it trade on real wold prices (you might want to include transaction and other fees as well).

This could give you a feel for how well would it perform in the real world.

 

It does not involve risks and It doesn't require any investment other then your time.

ಠ_ಠ  if i said something stupid please let me know

Link to post
Share on other sites
23 hours ago, shadow_ray said:

Don't get discouraged, create a framework which can test your algorithm.  Give it actual market data and a small amount of "virtual" money and let it trade on real wold prices (you might want to include transaction and other fees as well).

This could give you a feel for how well would it perform in the real world.

 

It does not involve risks and It doesn't require any investment other then your time.

Actually I was asking about how I could get the data to feed it.

Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now

×