# [WIS22] Cryptocurrency price prediction with recurrent neural networks

Posted 1 year ago
5098 Views
|
5 Replies
|
5 Total Likes
|
5 Replies
Sort By:
Posted 1 year ago
 -- you have earned Featured Contributor Badge Your exceptional post has been selected for our editorial column Staff Picks http://wolfr.am/StaffPicks and Your Profile is now distinguished by a Featured Contributor Badge and is displayed on the Featured Contributor Board. Thank you!
Posted 1 year ago
 I think the 109 values you call "tests" are usually called the validation set, but this is a matter of nomenclature.In any case, I am surprised this can work at all. I've always thought market prices are more or less random walks. In fact, I'm skeptical about the very possibility to predict them from a theoretical point of view, based on the following reasoning.What would happen if such models turned out to be really efficient at predicting the price and if such model was made public? Wouldn't everyone eventually use it, making the prediction self-fulfilling?In fact, there could be a positive feedback happening. The model would predict prices fluctuations that would be amplified by speculators. In the end the model itself would direct the market and the price would become a loose degree of freedom.
Posted 11 months ago
 He's predicting log-price levels, not returns (log-price differences). It is the returns that are random, not the prices. The price series themselves are highly autocorrelated so you could get similarly good-looking results with the naïve forecast function LogPrice(t+1) = LogPrice(t). The real test would be to use the models to try to predict returns (by differencing the forecast log-prices). But the results would be disappointing, just as they would be if you had used, say, an ARIMA model to predict the prices. The returns, which are actually what you are interested in, as just unforecastable "residuals" as far as such price models are concerned.
Posted 1 year ago
 Can you add mathematica code for plots: "Visualising the predicted market values against the real data" in "Neural Net Model trained with one cryptocurrency"I mean for "Predicted" and "Actual" ?  predictedbtctransformed1=Exp/@predictedbtc1 ListLinePlot[...] Thanks.
Posted 1 month ago
 What led you to choose to focus on Bitcoin, Ethereum, and Litecoin, and what motivated you to use the Wolfram Language in your analysis? I'm also curious to know more about how you determined that the third model with the multi-input architecture consistently outperformed the other models in terms of forecasting accuracy. I'm interested in the potential for applying the insights from this project to other areas of finance. Have you considered combining your work with the resources available on the website https://www.moonbitcoins.com/dashboard, which is a platform for buying and selling bitcoins?