Cryptocurrency price forecasting method using long short-term memory with time-varying parameters
نویسندگان
چکیده
Numerous research have been done to predict cryptocurrency prices since affect global economic and monetary systems. However, investigations using linear connection approaches technical analysis indicators frequently fall short of providing an explanation for changes in the pattern BitCoin pricing. This paper is proposed study time-varying parameters with long short-term memory (LSTM). The investigated on a dataset retrieved from Binance March 2022 April 2022. LSTM used variety hyperparameter settings, particularly time parameters, price (BTC/USDT) dataset. Additionally, it evaluated terms mean absolute percentage error (MAPE) comparison smooth moving average (SMA), weighted (WMA), exponential averages (EMA). From investigation, previous 3 days prediction gives lowest MAPE values outperformed other models. When considering last three days' value pricing, indicated offers best accurate prediction, 0.0927%.
منابع مشابه
Time Series Forecasting Based on Augmented Long Short-Term Memory
In this paper, we use variational recurrent model to investigate the time series forecasting problem. Combining recurrent neural network (RNN) and variational inference (VI), this model has both deterministic hidden states and stochastic latent variables while previous RNN methods only consider deterministic states. Based on comprehensive experiments, we show that the proposed methods significa...
متن کاملForecasting Temperature Indices with Time-varying Long-memory Models
The hedging of weather risks has become extremely relevant in recent years, promoting the diffusion of weather derivative contracts. The pricing of such contracts require the development of appropriate models for the prediction of the underlying weather variables. Within this framework, we present a modification of the double long memory ARFIMA-FIGARCH model introducing time-varying memory coef...
متن کاملForecasting Across Time Series Databases using Long Short-Term Memory Networks on Groups of Similar Series
With the advent of Big Data, nowadays in many applications databases containing large quantities of similar time series are available. Forecasting time series in these domains with traditional univariate forecasting procedures leaves great potentials for producing accurate forecasts untapped. Recurrent neural networks, and in particular Long Short Term Memory (LSTM) networks, have proven recent...
متن کاملLong-term Iran's inflation analysis using varying coefficient model
Varying coefficient Models are among the most important tools for discovering the dynamic patterns when a fixed pattern does not fit adequately well on the data, due to existing diverse temporal or local patterns. These models are natural extensions of classical parametric models that have achieved great popularity in data analysis with good interpretability.The high flexibility and interpretab...
متن کاملShort-term Load Forecasting Method
Based on Wavelet and Reconstructed Phase Space Zunxiong Liu, Zhijun Kuang, Deyun Zhang 1.Dept. of Information and Communication Eng, Xi’an Jiaotong University. Xi’an, Shanxi, China. 2.Dept. of Information Eng, East China Jiaotong University. Nanchang, Jiangxi, China Abstract: This paper proposed wavelet combination method for short-term forecasting, which makes merit of wavelet decomposition an...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Indonesian Journal of Electrical Engineering and Computer Science
سال: 2023
ISSN: ['2502-4752', '2502-4760']
DOI: https://doi.org/10.11591/ijeecs.v30.i1.pp435-443