Join the 80,000 other DTN customers who enjoy the fastest, most reliable data available. There is no better value than DTN!

(Move your cursor to this area to pause scrolling)




"IQ feed is brilliant. The support is mind-bending. What service!" - Comment from Public Forum Post
"Previously I was using *******. IQFeed is WAY more economical, and for my charting needs is just as good, if not better." - Comment from Public Forum Post
"It’s so nice to be working with real professionals!" - Comment from Len
"If you are serious about your trading I would not rely on IB data for serious daytrading. Took me a while to justify the cost of IQ Feed and in the end, it's just a 2 point stop on ES. Better safe than sorry" - Comment from Public Forum
"I've never had DTN go out on me since switching. ******* would go down a couple times every month when I was using them." - Comment from Bryce in AL.
"This beats the pants off CQG, I am definitely switching to the ProphetX 3.0!" - Comment from Stephen
"I'm very glad I switched to IQFeed. It's working perfectly with no lag, even during fast market conditions." - Comment from Andy via Email
"I started a trial a few weeks back before the market went wild. DTN.IQ didn’t miss anything and beat my other provider. I decided to stay with you because of the great service through all the volatility." - Comment from Mike
"You have an excellent product !!!!!!" - Comment from Arely
"I was on the phone with a friend who uses CQG and right after the Fed announcement, CQG was as much as 30 seconds behind DTN.IQ. Some quotes were off by as much as 15-18 cents. Your feed never missed a beat." - Comment from Roger
Home  Search  Register  Login  Recent Posts

Information on DTN's Industries:
DTN Oil & Gas | DTN Trading | DTN Agriculture | DTN Weather
Follow DTNMarkets on Twitter
DTN.IQ/IQFeed on Twitter
DTN News and Analysis on Twitter
»Forums Index »General Discussion »Trading Tips, Tricks and Ideas »Machine learning and tick-by-tick data
Author Topic: Machine learning and tick-by-tick data (2 messages, Page 1 of 1)

keohir808
-Interested User-
Posts: 6
Joined: Sep 16, 2019


Posted: Jan 30, 2022 08:45 PM          Msg. 1 of 2
There seems to be a lack of research regarding the use of tick-by-tick data as input to machine learning models. Has anyone experimented with machine learning and tick-by-tick data? I’ve trained an LSTM with about 2 years worth using tick-by-tick data with DTN which fit a certain criteria such as float, volume, price. The result is a model with around 69.9% accuracy. A naïve model which predicts that the bid price will be the same price as the last tick has an accuracy of around 65%. I’m wondering if I can increase my model’s accuracy through feature engineering. Could anyone share research papers regarding machine learning and tick-by-tick data? Does anyone have any insight regarding data transformations that can be applied to financial data which may result in increased accuracy if used as a feature in machine learning models?


Interests & Tools: Machine Learning, Neural Networks, Deep Learning, Python, Java, Trading, Small Caps, Interactive Brokers.
Edited by keohir808 on Jan 30, 2022 at 08:50 PM

taa_dtn
-DTN Evangelist-
Posts: 141
Joined: May 7, 2004


Posted: Jan 31, 2022 11:10 AM          Msg. 2 of 2
Yes, I experimented with this a few years ago. Your questions are relevant and insightful, but I don't have much useful information to offer in reply.

I haven't seen many published papers on the subject in recent years. Take that with a grain of salt, though, because I'm not looking actively enough. Possibly if the technique has been applied successfully, it hasn't been discussed in public for the obvious reasons. Hopefully someone else will reply with better information.

In general, I hit the same roadblocks you did. It's hard to choose the right network architecture (financial data isn't statistically stationary, so I wasn't able to design either recurrent or convolutional networks that were consistently successful). Raw tick-by-tick data has so much variability along so many dimensions that I suspect feature engineering is necessary, but that's a major research project in its own right. Techniques currently being used for natural language processing are probably where I'd start if I were to look at this again today.

Possibly the most fundamental problem I ran into is that it doesn't seem workable to use a scalar value to measure outcomes, so anything based on simple gradient descent is problematic. I think a practical outcome measurement must be at least three-dimensional -- it needs to include return, risk, and capital management. Arguably more, but the need for those three is easy to understand.
 

 

Time: Mon May 16, 2022 6:02 AM CFBB v1.2.0 31 ms.
© AderSoftware 2002-2003