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.
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.
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.
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.
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.
%% 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
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?
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.
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?