• Corpus ID: 113405119

Seq 2 Seq RNNs and ARIMA models for Cryptocurrency Prediction : A Comparative Study

  title={Seq 2 Seq RNNs and ARIMA models for Cryptocurrency Prediction : A Comparative Study},
  author={Jonathan Rebane},
Cyrptocurrency price prediction has recently become an alluring topic, attracting massive media and investor interest. Traditional models, such as Autoregressive Integrated Moving Average models (ARIMA) and models with more modern popularity, such as Recurrent Neural Networks (RNN’s) can be considered candidates for such financial prediction problems, with RNN’s being capable of utilizing various endogenous and exogenous input sources. This study compares the model performance of ARIMA to that… 

Figures and Tables from this paper

Stock Price Prediction With ARIMA and Deep Learning Models
  • Zihao Gao
  • Computer Science
    2021 IEEE 6th International Conference on Big Data Analytics (ICBDA)
  • 2021
Comparing the performance of different time–series models in predicting close price movement for 30 listed stocks from the Dow Johns Industrial Average suggests that LSTM and sequence to sequence (Seq2Seq) model with attention estimates fit the price movement pattern well with relatively low latency.
A Comparative Study of Bitcoin Price Prediction Using Deep Learning
Experimental results showed that although LSTM-based prediction models slightly outperformed the other prediction models for Bitcoin price prediction (regression), DNN-based models performed the best for price ups and downs prediction (classification).
A Novel Cryptocurrency Price Prediction Model Using GRU, LSTM and bi-LSTM Machine Learning Algorithms
Three types of recurrent neural network (RNN) algorithms used to predict the prices of three types of cryptocurrencies, namely Bitcoin (BTC), Litecoin (LTC), and Ethereum (ETH), show excellent predictions depending on the mean absolute percentage error (MAPE).
Bitcoin Price Prediction: An ARIMA Approach
This work aims at revealing the usefulness of traditional autoregressive integrative moving average (ARIMA) model in predicting the future value of bitcoin by analyzing the price time series in a 3-years-long time period.
Stochastic Neural Networks for Cryptocurrency Price Prediction
A stochastic neural network model based on the random walk theory is proposed for Cryptocurrency price prediction that induces layer-wise randomness into the observed feature activations of neural networks to simulate market volatility.
Bitcoin closing price movement prediction with optimal functional link neural networks
  • S. Nayak
  • Computer Science
    Evol. Intell.
  • 2022
Optimal FLN models are used to predict the daily, weekly, and monthly closing prices of Bitcoin and a comparative study among optimal FLNs is carried out using evaluation metrics.
Using Machine Learning ARIMA to Predict the Price of Cryptocurrencies
  • S. A. Alahmari
  • Computer Science, Mathematics
    ISC Int. J. Inf. Secur.
  • 2019
The results demonstrated that ARIMA outperforms most other methods in predicting cryptocurrency prices on a daily time series basis in terms of mean absolute error (MAE), mean squared error (MSE) and root mean squarederror (RMSE).
Comparing the Prediction Accuracy of LSTM and ARIMA Models for Time-Series with Permanent Fluctuation
Long Short-Term Memory (LSTM) from ANN chooses and outputs compared with the autoregressive integrated moving average (ARIMA) model and, although, in long term prediction, the forecast accuracy of both models reduce, LSTM outperforms ARIMA in terms of error of accuracy, significantly.
Improved Recurrent Neural Networks (RNN) Based Intelligent Fund Transaction Model
An encoder-decoder model combined with the attention mechanism--Improved RNN model is used, which can select specific feature inputs and previous time step outputs, both of which are highly correlated with the current output, making system predictions more efficient.
Forecasting Cryptocurrency Prices Time Series Using Machine Learning
This paper describes the construction of the short-term forecasting model of cryptocurrencies’ prices using machine learning approach and found that the proposed approach was more accurate than the ARIMA-ARFIMA models in forecasting cryptocurrencies time series both in the periods of slow rising (falling) and in the period of transition dynamics (change of trend).


Using artificial neural network models in stock market index prediction
Stock Price Prediction Using the ARIMA Model
Results obtained revealed that the ARIMA model has a strong potential for short-term prediction and can compete favourably with existing techniques for stock price prediction.
Recurrent neural network and a hybrid model for prediction of stock returns
An Empirical Study on Modeling and Prediction of Bitcoin Prices With Bayesian Neural Networks Based on Blockchain Information
The empirical studies show that BNN performs well in predicting Bitcoin price time series and explaining the high volatility of the recent Bitcoin price.
Sequence to Sequence Learning with Neural Networks
This paper presents a general end-to-end approach to sequence learning that makes minimal assumptions on the sequence structure, and finds that reversing the order of the words in all source sentences improved the LSTM's performance markedly, because doing so introduced many short term dependencies between the source and the target sentence which made the optimization problem easier.
What Are the Main Drivers of the Bitcoin Price? Evidence from Wavelet Coherence Analysis
It is found that the Bitcoin forms a unique asset possessing properties of both a standard financial asset and a speculative one.
Virtual currency, tangible return: Portfolio diversification with bitcoin
Bitcoin (BTC) is a major virtual currency. Using weekly data over the 2010–2013 period, we analyze a BTC investment from the standpoint of a US investor with a diversified portfolio including both
Autoregressive Integrated Moving Average with Explanatory Variable (ARIMAX) Model for Thailand Export
This paper considers a univariate time series model to forecast Thailand exports to major trade partners. The main question is whether the explanatory variable, i.e. trade partners’ leading
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Qualitatively, the proposed RNN Encoder‐Decoder model learns a semantically and syntactically meaningful representation of linguistic phrases.
Predicting Fluctuations in Cryptocurrency Transactions Based on User Comments and Replies
This paper analyzes user comments in online cryptocurrency communities to predict fluctuations in the prices of cryptocurrencies and the number of transactions by using a simple and efficient method.