ARIMA for Short-Term and LSTM for Long-Term in Daily Bitcoin Price Prediction

Toai, Tran Kim; Šenkeřík, Roman; Plucar, Jan; Ulrich, Adam; Hanh, Vo Thi; Huan, Vo Minh

doi:10.1007/978-3-031-23492-7_12

Cited by 5 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ARIMA model is more accurate and effective than the complex neural network model in short-term prediction (Ying et al, 2013). However, some scholars have mentioned that ARIMA's assumption is based on a linear situation, and most problems in the real world are highly nonlinear (Toai et al, 2023). It is easy to conclude that the effectiveness of the ARIMA model depends mainly on the strength of the correlation of the data.…”

Section: Related Work Regarding Stock Price Predictionmentioning

confidence: 99%

Time-Sensitive Index Future Trading Trend Prediction with Deep Learning methods

ZHENG,

Tang,

Wang

et al. 2023

Preprint

View full text Add to dashboard Cite

Purpose- As the stock price’s fluctuation is nonlinear and greatly affected by environmental and industrial factors, stock prediction is extremely complicated and has various methods. This paper aims to find the optimal prediction model for predicting the Hang Seng stock market data from six main forecasting methods: ARIMA (Auto Regressive Integrated Moving Average), Artificial Neural Network (ANN), Convolutional Neural Network (CNN), Long short-term memory (LSTM), Gated Circulation Unit (GRU) and Conv1D-LSTM. Design/methodology/approach- In this project, the authors apply the open data of Hang Seng stock’s hour-by-hour closing prices to the above methods to establish forecasting models. Among them, hourly technical indicators (such as MA, EMA, and Momentum) are used in training neural network models as features. MSE and MAE methods are utilized to evaluate the discrepancy between the predicted and actual values. Finally, the accuracy of the buying decision (purchase or sell) is tested by the yield calculated by the actual closing price and the predicted closing price, respectively. Findings- The data collected from open data of the Hang Seng dataset from September 2019 to September 2020 contained hourly stock indexes, including closing price, opening price, high price, low price, volume, and other fundamental indicators. The total amount of data was 4608 (hours)× 26 (indexes) samples. The contribution of this paper to the existing knowledge is the evidence that the LSTM model has more advantages in forecasting and purchasing decisions compared with other models limited to the Hang Seng stock market. On this basis, the in-depth analysis demonstrates that the datasets multi-dimensionality and timeliness should be considered in the prediction model design. And the proposed architecture of deep learning models in this study could be modified to an expert system coupled with several models to explore the best approach to predicting a stock market's trading trend. Originality/value- The contribution of this paper to the existing knowledge is the evidence that the LSTM model has more advantages in forecasting and purchasing decisions compared with other models limited to the Hang Seng stock market. On this basis, the in-depth analysis demonstrates that the datasets multi-dimensionality and timeliness should be considered in the prediction model design. And the proposed architecture of deep learning models in this study could be modified to an expert system coupled with several models to explore the best approach to predicting a stock market's trading trend.

show abstract

Section: Related Work Regarding Stock Price Predictionmentioning

confidence: 99%

Time-Sensitive Index Future Trading Trend Prediction with Deep Learning methods

ZHENG,

Tang,

Wang

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Figure 5 illustrates the prediction results of temperature by the ARIMA model. When new data is available, the ARIMA model is re-trained [40]. As a result, the accuracy is generally quite good, only deviating at certain times.…”

Section: Arima Modelmentioning

confidence: 99%

Exploring Hybrid Models For Short-Term Local Weather Forecasting in IoT Environment

Tran,

Senkerik,

et al. 2023

mendel

View full text Add to dashboard Cite

This paper explores using and hybridizing simple prediction models to maximize the accuracy of local weather prediction while maintaining low computational effort and the need to process and acquire large volumes of data. A hybrid RF-LSTM model is proposed and evaluated in this research paper for the task of short-term local weather forecasting. The local weather stations are built within an acceptable radius of the measured area and are designed to provide a short period of forecasting - usually within one hour. The lack of local weather data might be problematic for an accurate short-term valuable prediction in sustainable applications like agriculture, transportation, energy management, and daily life. Weather forecasting is not trivial because of the non-linear nature of time series. Thus, traditional forecasting methods cannot predict the weather accurately. The advantage of the ARIMA model lies in forecasting the linear part, while the SVR model indicates the non-linear characteristic of the weather data. Both non-linear and linear approaches can represent the combined model. The hybrid ARIMA-SVR model strengthens the matched points of the ARIMA model and the SVR model in weather forecasting. The LSTM and random forest are both popular algorithms used for regression problems. LSTM is more suitable for tasks involving sequential data with long-term dependencies. Random Forest leverages the wisdom of crowds by combining multiple decision trees, providing robust predictions, and reducing overfitting. Hybrid Random forest-LSTM potentially leverages the robustness and feature importance of Random Forest along with the ability of LSTM to capture sequential dependencies. The comparison results show that the hybrid RF-LSTM model reduces the forecasting errors in metrics of MAE, R-squared, and RMSE. The proposed hybrid model can also capture the actual temperature trend in its prediction performance, which makes it even more relevant for many other possible decision-making steps in sustainable applications. Furthermore, this paper also proposes the design of a weather station based on a real-time edge IoT system. The RF-LSTM leverages the parallelized characteristics of each decision tree in the forest to accelerate the training process and faster inferences. Thus, the hybrid RF-LSTM model offers advantages in terms of faster execution speed and computational efficiency in both PC and Raspberry Pi boards. However, the RF-LSTM consumes the highest peak memory usage due to being a combination of two different models.

show abstract