Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Time Series Prediction Using LSTM Deep Neural Networks

altumintelligence.com

Post reply on HN
Print view View original

21–30 of 72 posts

Re: Time Series Prediction Using LSTM Deep Neural Networks

#21

Post by jarym »

beagle3 wrote: post #17
jarym wrote: post #3

Why does everyone naively try to predict price? No ‘traders’ are interested in predicting it - what traders do is identify good locations to enter or exit the market. I.e. places with defined risk where you will know if you’re wrong if it goes against you by x% while you expect a y% gain if you’re right AND y>x is worth more than the number of times you’re wrong. The types of Algos that work well for this are edge id…

.. because you buy at the price, and sell at the price (spread and fees ignored for now). Which means, regardless of your philosophy, you are predicting a price change - a long signal is a prediction for positive price change; a short signal is a prediction for a negative price change. If that wasn’t true, your system would not be able to profit. Predicting price change and predicting price are semantically equivalen…

Predicting price means you’re predicting one variable with no idea of hot likely you are to be wrong and how wrong you’re likely to be and says nothing of where your expectations are for price to go after.

It is semantically different to say: if price goes to Y then you have odds that it will then go to Target 1 and then slightly lower odds it goes to Target 2.

Re: Time Series Prediction Using LSTM Deep Neural Networks

#22

Post by PeterisP »

foxes wrote: post #20
jkabrg wrote: post #15

Earlier quoted context omitted.

There was a Quanta Magazine article talking about predicting the evolution of a flame-front using ML. The ML algorithm remained accurate for eight Lyapunov intervals; eight times longer than the previous SOTA. https://www.quantamagazine.org/machine-learnings-amazing-abi...

The only real argument I think you can make is that it might be more efficient to have a neural network quickly spit out an approximate solution instead of solving the actual equations. But if you have the time having the actual equations is more valuable?

Assuming that "having the actual equations" is possible, which in market predictions it most likely is not.

Re: Time Series Prediction Using LSTM Deep Neural Networks

#23

Post by ahartmetz »

salty_biscuits wrote: post #18
f00_ wrote: post #16

Earlier quoted context omitted.

exactly, Judea Pearl's The Book of Why opened my eyes to the fact that most of what happens in machine learning is really just curve fitting It connected with what i've heard Chomsky say about trying to develop laws of physics by filming what's happening outside the window. We need to do experiments and interventions to learn the dynamics of a system "What do you think the role is, if any, of other uses of so-called…

I really violently oppose this characterization of ML as "just" curve fitting, as if curve fitting is some simple solved problem. It seems like there is a ignorance about issues relating to model selection, which is an essential part of curve fitting. What complexity of model does the data support? Can you keep a distribution over structures that allows uncertain parts of the model to be interrogated? These are the p…

Not the same kind of experiment. An experiment in the scientific sense tweaks the process that generates the data, not the interpretation of the data. There is an inspiration / hypothesis creation step between old data and new experiment.

Main differences: A hypothesis is sorta kinda like your model's coefficients, but more generally applicable. And you have no feedback loop between model coefficients and input data.

So yeah, you are doing very sophisticated curve fitting. It is useful alright, it's just not very much like science.

Re: Time Series Prediction Using LSTM Deep Neural Networks

#24

Post by djhworld »

I'm currently learning machine learning at the most basic level, this is the sort of stuff I want to work towards though

I deal with time series data a lot at work, I work in broadcasting/media and 99% of the time the data is fairly "predictable" and follows a regular daily pattern, peppered with the odd spikes during big, unpredicatble news events.

Re: Time Series Prediction Using LSTM Deep Neural Networks

#25

Post by salty_biscuits »

ahartmetz wrote: post #23
salty_biscuits wrote: post #18

Earlier quoted context omitted.

I really violently oppose this characterization of ML as "just" curve fitting, as if curve fitting is some simple solved problem. It seems like there is a ignorance about issues relating to model selection, which is an essential part of curve fitting. What complexity of model does the data support? Can you keep a distribution over structures that allows uncertain parts of the model to be interrogated? These are the p…

Not the same kind of experiment. An experiment in the scientific sense tweaks the process that generates the data, not the interpretation of the data. There is an inspiration / hypothesis creation step between old data and new experiment. Main differences: A hypothesis is sorta kinda like your model's coefficients, but more generally applicable. And you have no feedback loop between model coefficients and input data.…

No, it's the same. It is just about having access to control variables.

Re: Time Series Prediction Using LSTM Deep Neural Networks

#26

Post by sgt101 »

f00_ wrote: post #16
fooker wrote: post #5

So, curve fitting?

exactly, Judea Pearl's The Book of Why opened my eyes to the fact that most of what happens in machine learning is really just curve fitting It connected with what i've heard Chomsky say about trying to develop laws of physics by filming what's happening outside the window. We need to do experiments and interventions to learn the dynamics of a system "What do you think the role is, if any, of other uses of so-called…

There are a lot of subtle points to make here. There is a tendency to throw data at models that don't capture parts of a distribution, and it is definitely true that many of the tail events in a challenging domain will not occur again no matter how long we observe the domain. Successful machine learning systems are able to predict these outcomes without having seen the data previously because they have captured the theory that creates them. Unfortunately it is very difficult to determine when a model is capturing the domain theory and when it is just modelling a distribution - often the only way is to "know" that it's a bit fishy. In many domains this difference doesn't matter, vision in animals seems to work in this way - it's all approximations and sameasis, and we and machines get tricked by optical illusions and so on. Other domains (many in physics) are modelled by observing data and inferring a higher level theory. Early days physics didn't work this way - Chomsky is right, but the method of Galileo is not the only method. Modern scientists do organise data and do look for exceptions and regularities which then drives the search for explanatory systems with predictive power.

Re: Time Series Prediction Using LSTM Deep Neural Networks

#27

Post by dafrie »

djhworld wrote: post #24

I'm currently learning machine learning at the most basic level, this is the sort of stuff I want to work towards though I deal with time series data a lot at work, I work in broadcasting/media and 99% of the time the data is fairly "predictable" and follows a regular daily pattern, peppered with the odd spikes during big, unpredicatble news events.

A year ago, the original blog post [1] (it was just recently updated, which is now the one linked here on HN) helped me on a semester thesis, where I quite successfully used LSTM for short-term electricity load forecasting, which also has very strong daily, weekly and seasonal patterns. I used multiple features/variables such as calendar and weather data and found the LSTM models to easily beat ARIMA/TBATS forecasts.

You can find the code repo on my Github link [2], but please bear with the code quality. I only have an economics background, so my coding experience is fairly limited :)

[1] http://www.jakob-aungiers.com/articles/a/LSTM-Neural-Network...

[2] https://github.com/dafrie/lstm-load-forecasting

Re: Time Series Prediction Using LSTM Deep Neural Networks

#28

Post by zwaps »

I find it interesting that Computer Scientists are basically rediscovering statistics.

Now when predicting time series, an issue is that most model (like ARIMA, GARCH etc.) are short-memory processes. When you look at the full-series prediction of LSTMs, you observe the same thing.

So in terms of Time Series, Machine Learning is currently in the mid to late 80's compared to Financial Econometrics.

So if you are a CS, you should now probably take a look at fractional GARCH models and incorporate this into the LSTM logic. If the statistic issues are the same, then this may give you that hot new paper.

Re: Time Series Prediction Using LSTM Deep Neural Networks

#29

Post by mr_toad »

f00_ wrote: post #16
fooker wrote: post #5

So, curve fitting?

exactly, Judea Pearl's The Book of Why opened my eyes to the fact that most of what happens in machine learning is really just curve fitting It connected with what i've heard Chomsky say about trying to develop laws of physics by filming what's happening outside the window. We need to do experiments and interventions to learn the dynamics of a system "What do you think the role is, if any, of other uses of so-called…

> Galileo

Nobody is interested in having a machine discover the theory behind parabolic trajectories. That was solved science 400 years ago.

What is interesting, is having a machine that can estimate a parabolic trajectory, not deductively, but inductively, based only on visual observation, for a variety of different shaped and sized objects. The way a human does.

Galileo was a great scientist, and discovered many natural laws relating to motion, but that wouldn’t have made him a great dodgeball player.

Re: Time Series Prediction Using LSTM Deep Neural Networks

#30

Post by leeuwnhawk »

cmroanirgo wrote: post #13
jarym wrote: post #3

Why does everyone naively try to predict price? No ‘traders’ are interested in predicting it - what traders do is identify good locations to enter or exit the market. I.e. places with defined risk where you will know if you’re wrong if it goes against you by x% while you expect a y% gain if you’re right AND y>x is worth more than the number of times you’re wrong. The types of Algos that work well for this are edge id…

> Why does everyone naively try to predict price? No ‘traders’ are interested in predicting it - what traders do is identify good locations to enter or exit the market. I agree. I've built many systems in this area, but it wasn't until I started working in the Indian market (>10 yrs ago) that it became abundantly clear that trying to calculate the long/shorts signals using historical (/time series) data was a waste o…

> I've built many systems in this area, but it wasn't until I started working in the Indian market (>10 yrs ago) that it became abundantly clear that trying to calculate the long/shorts signals using historical (/time series) data was a waste of time. (And yet my primary role was to provide tools that did exactly that).

I'm currently working on building similar tools in my area of work for the Indian market and would really appreciate if you could shed some more light into the things you learned from your experience in working in this domain.

Post reply on HN