Recommendations on time-series price prediction models?

[userque]

I ran some longer-term (20 years of data or to start date) tests with EEM (iShares MSCI Emerging Markets ETF), GLD (SPDR Gold Trust), IWM (iShares Russell 2000 ETF), and SPY (SPDR S&P 500 ETF). The tests were simulating trades entering on the close when the next predicted inflection point in the detrended curve was the next day. The simulated exit was on the following predicted inflection point. About 60% of the tests were profitable.

On the surface, the method could be robust because it's basically predicting trend retracements. And the amount of fitting is limited because of the relatively small number of terms in the fitted functions. This is visible in the fitted curve images because the curve is often not that close to the data the curve was fitted to.


I have tried genetic programming.
https://www.elitetrader.com/et/thre...your-edge-for-2019.329802/page-8#post-4809209
https://www.elitetrader.com/et/thre...ine-learning-for-astronomical-profits.334373/
https://www.elitetrader.com/et/threads/oscillators.337471/page-23#post-4960785
https://www.elitetrader.com/et/threads/machine-learning-for-price-wave-analysis.339646/#post-4997882
And you even liked some of the posts! Those models tended to overfit and were not very good on unseen data -- except strangely for the astrology-based one.
https://www.elitetrader.com/et/thre...tronomical-profits.334373/page-2#post-4896025

It might be an interesting exercise to see if genetic programming just based on time could fit a time series and make a good prediction.

60% is about what I recall getting too.

I'm sure I did like some of your past post. My memory is selective ... at least that's what I'm told sometimes. I'll check out those links, but I'm sure I'm probably already subscribed to them.

I've found forecasting 'time' (time of low/high of the day), to be less consistent than forecasting price change. But again, I was doing anything robust at the time.

 

[userque]

Of course is that algorithm "recursive". Each one is. You can just include the point prediction in your source data for inferencing and obtain the next prediction.

Yeah, that's what 'I' would think it would mean.

But smarter people have learned to just ask, rather than assume others share our same understandings.

 

[DiceAreCast]

Perhaps you are right if I understand your meaning correctly and if you can confirm that my understanding is right. Then and only then shall we approach OP and assume he asked an intelligent and well thought out question and query for elaboration.

Na,just kidding, you have a point. Better to ask than assume. Though like above that can be tedious and a good grasp at averages can help someone to infer meaning.

Yeah, that's what 'I' would think it would mean.

But smarter people have learned to just ask, rather than assume others share our same understandings.

 

[ajensen]

hi everyone, I'm new to the field of price prediction modeling and currently I'm experimenting the LSTM model. I found a few posts online, like this one : https://towardsdatascience.com/lstm...stock-prices-using-an-lstm-model-6223e9644a2f . They however all suffer from the problem that their predictions are not recursive. I took the trained model from the above mentioned post and ran a recursive prediction; the results are wrong and not usable.

Wonder if anyone can recommend a few time-series price prediction models?

Thanks!

Have you looked at ARMA (autoregressive moving average) models, perhaps supplemented by GARCH to model conditional volatility? Those are the classical time series models. There is a book from 2000, Non-Linear Time Series Models in Empirical Finance
by Philip Hans Franses and Dick van Dijk.

 

[SunTrader]

Looking for cycles = attempting to catch smoke.

 

[longandshort]

I worked briefly at a quant fund (I'm a trader and not a quant, but I worked closely with them to design and implement strategies they were developing) and they were spending a lot of time and money on:
1. Using volume to predict volatility
2. Using volatility to predict price change

Based on the research we had conducted, there was very little (if any) signal in prices themselves. They were looking to trade intra-day momentum, reversals, and sniff out larger orders.

 

[murray t turtle]

If the first forecast shows to be 80% accurate, for example,
then the next bar will be 64% accurate, so on and so forth.

It won't be that the model is 'bad,' it could be that the model is not used in the best way possible.
About how many iterations/cycles/hours/minutes did you train the model; and with how much data?

%%
Sounds like your math is right;
seldom would anybody call any of that[80,64%]a prediction] Weather forecast maybe 80% accurate, but 1 week forcast tends to be more accurate than day 10 /of 10day forecast

 

[jublin]

The model is not created from a Fourier transform, and Fourier transforms (at least the common Fast Fourier Transform) are not good choices for modeling prices according to John Ehlers' "Rocket Science for Traders: Digital Signal Processing Applications."

This suggests going long tomorrow 20210406 and exiting on 20210416 to capture the next cyclic segment predicted to rise.

I haven't been using this method very long. And like everything else, it works -- sometimes.

Hi thanks, this is great. Indeed, the mentioned ETF increased from 4/6 to 4/12 and then went down. I didn't expect such a simple model to be able to predict with reasonable accuracy. Wonder if there is any article I can read about this in more depth? Is it mostly a frequentist model based on observation or there is a Bayesian explanation on why there are such long-term oscillations?

 

[jublin]

If the first forecast shows to be 80% accurate, for example,
then the next bar will be 64% accurate, so on and so forth.

It won't be that the model is 'bad,' it could be that the model is not used in the best way possible.

In the above example, I'd suggest only utilizing the first forecast, then updating the data in order to use actual data rather than forecasted data, for making the next forecast. In this case, you'd only be able to forecast one bar ahead at a time, but you'd have the greatest accuracy.

I've found that it better to not use a 'recursive' approach; rather, I'd use a new model instead.

One model to forecast one bar ahead. A separate model to forecast two days ahead. Etc.

Or, one model to forecast all days ahead that are desired.

Hence, I don't use a time-series approach.

About how many iterations/cycles/hours/minutes did you train the model; and with how much data?

Hi I agree that using a "recursive" approach is dicy and it amplifies error over time. For sure, the one-step model can be applied "recursively" in prediction. By "being not recursive", I mean that the training phase didn't take into account any supervision from more than one day ahead. This resulted in an easy "local optimum" --- simply, more or less, use today's price as the prediction of tomorrow's price. Using this setup, the training phase is not forced to dig any deeper. (By applying the trained model recursively in prediction, it indeed quickly converges to a constant price.)

What I meant to ask is are there any better practices that can force the model to try to predict multiple days, or even months ahead? By "forcing" I mean that the time frame is taken into account in the training phase. I'm not sure how hard it is, this is my first training. Maybe I should try an easier problem formulation, like classification instead of predicting.

I trained for 100 epochs but it cleared converged after about 5 and stayed there. It took less than a hour. I used 15 years of hourly data.

 

[jublin]

Have you looked at ARMA (autoregressive moving average) models, perhaps supplemented by GARCH to model conditional volatility? Those are the classical time series models. There is a book from 2000, Non-Linear Time Series Models in Empirical Finance
by Philip Hans Franses and Dick van Dijk.

Thanks for the recommendation, I saw a post about it (https://towardsdatascience.com/time...tock-prices-using-an-arima-model-2e3b3080bd70) but haven't followed it. I followed a similar post about using Facebook's Prophet: https://towardsdatascience.com/time...es-using-facebooks-prophet-model-9ee1657132b5. The results are ok but I don't like I'd be comfortable to let it drive a trading strategy. Do you think that these two would be comparable?