scholarly journals Recurrent Neural Networks and ARIMA Models for Euro/Dollar Exchange Rate Forecasting

2021 ◽  
Vol 11 (12) ◽  
pp. 5658
Author(s):  
Pedro Escudero ◽  
Willian Alcocer ◽  
Jenny Paredes
Keyword(s):  
Time Series ◽  
Exchange Rate ◽  
Short Term Memory ◽  
Moving Average ◽  
Validation Dataset ◽  
Short Term ◽  
Random Behavior ◽  
Forecasting Performance ◽  
Using Data

Analyzing the future behaviors of currency pairs represents a priority for governments, financial institutions, and investors, who use this type of analysis to understand the economic situation of a country and determine when to sell and buy goods or services from a particular location. Several models are used to forecast this type of time series with reasonable accuracy. However, due to the random behavior of these time series, achieving good forecasting performance represents a significant challenge. In this paper, we compare forecasting models to evaluate their accuracy in the short term using data on the EUR/USD exchange rate. For this purpose, we used three methods: Autoregressive Integrated Moving Average (ARIMA), Recurrent Neural Network (RNN) of the Elman type, and Long Short-Term Memory (LSTM). The analyzed period spanned from 2 January 1998, to 31 December 2019, and was divided into training and validation datasets. We performed forecasting calculations to predict windows with six different forecasting horizons. We found that the window of one month with 22 observations better matched the validation dataset in the short term compared to the other windows. Theil’s U coefficients calculated for this window were 0.04743, 0.002625, and 0.001808 for the ARIMA, Elman, and LSTM networks, respectively. LSTM provided the best forecast in the short term, while Elman provided the best forecast in the long term.

Forecasting container throughput with long short-term memory networks

2019 ◽  
Vol 120 (3) ◽  
pp. 425-441 ◽  
Author(s):  
Sonali Shankar ◽  
P. Vigneswara Ilavarasan ◽  
Sushil Punia ◽  
Surya Prakash Singh
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Short Term Memory ◽  
Moving Average ◽  
Short Term ◽  
Error Matrix ◽  
Term Memory ◽  
Content Type ◽  
Forecasting Performance ◽  
Long Short Term Memory

Purpose Better forecasting always leads to better management and planning of the operations. The container throughput data are complex and often have multiple seasonality. This makes it difficult to forecast accurately. The purpose of this paper is to forecast container throughput using deep learning methods and benchmark its performance over other traditional time-series methods. Design/methodology/approach In this study, long short-term memory (LSTM) networks are implemented to forecast container throughput. The container throughput data of the Port of Singapore are used for empirical analysis. The forecasting performance of the LSTM model is compared with seven different time-series forecasting methods, namely, autoregressive integrated moving average (ARIMA), simple exponential smoothing, Holt–Winter’s, error-trend-seasonality, trigonometric regressors (TBATS), neural network (NN) and ARIMA + NN. The relative error matrix is used to analyze the performance of the different models with respect to bias, accuracy and uncertainty. Findings The results showed that LSTM outperformed all other benchmark methods. From a statistical perspective, the Diebold–Mariano test is also conducted to further substantiate better forecasting performance of LSTM over other counterpart methods. Originality/value The proposed study is a contribution to the literature on the container throughput forecasting and adds value to the supply chain theory of forecasting. Second, this study explained the architecture of the deep-learning-based LSTM method and discussed in detail the steps to implement it.

scholarly journals Long Short Term Memory Recurrent Network for Standard and Poor’s 500 Index Modelling

2018 ◽  
Vol 7 (4.15) ◽  
pp. 25 ◽  
Author(s):  
Said Jadid Abdulkadir ◽  
Hitham Alhussian ◽  
Muhammad Nazmi ◽  
Asim A Elsheikh
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Recurrent Neural Network ◽  
Time Series Data ◽  
Short Term Memory ◽  
Series Data ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory

Forecasting time-series data are imperative especially when planning is required through modelling using uncertain knowledge of future events. Recurrent neural network models have been applied in the industry and outperform standard artificial neural networks in forecasting, but fail in long term time-series forecasting due to the vanishing gradient problem. This study offers a robust solution that can be implemented for long-term forecasting using a special architecture of recurrent neural network known as Long Short Term Memory (LSTM) model to overcome the vanishing gradient problem. LSTM is specially designed to avoid the long-term dependency problem as their default behavior. Empirical analysis is performed using quantitative forecasting metrics and comparative model performance on the forecasted outputs. An evaluation analysis is performed to validate that the LSTM model provides better forecasted outputs on Standard & Poor’s 500 Index (S&P 500) in terms of error metrics as compared to other forecasting models.  

Time Series Forecasting in Retail Sales Using LSTM and Prophet

2021 ◽  
pp. 241-262
Author(s):  
Clony Junior ◽  
Pedro Gusmão ◽  
José Moreira ◽  
Ana Maria M. Tome
Keyword(s):  
Time Series ◽  
Data Science ◽  
Short Term Memory ◽  
Special Kind ◽  
Time Series Forecasting ◽  
Short Term ◽  
Term Memory ◽  
Use Of Time

Data science highlights fields of study and research such as time series, which, although widely explored in the past, gain new perspectives in the context of this discipline. This chapter presents two approaches to time series forecasting, long short-term memory (LSTM), a special kind of recurrent neural network (RNN), and Prophet, an open-source library developed by Facebook for time series forecasting. With a focus on developing forecasting processes by data mining or machine learning experts, LSTM uses gating mechanisms to deal with long-term dependencies, reducing the short-term memory effect inherent to the traditional RNN. On the other hand, Prophet encapsulates statistical and computational complexity to allow broad use of time series forecasting, prioritizing the expert's business knowledge through exploration and experimentation. Both approaches were applied to a retail time series. This case study comprises daily and half-hourly forecasts, and the performance of both methods was measured using the standard metrics.

scholarly journals LINEAR AND NONLINEAR CORRELATIONS IN THE ORDER AGGRESSIVENESS OF CHINESE STOCKS

Fractals ◽  
2017 ◽  
Vol 25 (05) ◽  
pp. 1750041 ◽  
Author(s):  
PENG YUE ◽  
HAI-CHUAN XU ◽  
WEI CHEN ◽  
XIONG XIONG ◽  
WEI-XING ZHOU
Keyword(s):  
Time Series ◽  
Moving Average ◽  
Strong Correlations ◽  
Flow Data ◽  
Short Term ◽  
Long Range Correlations ◽  
Average Analysis ◽  
Linear And Nonlinear ◽  
Nonlinear Correlations

The diagonal effect of orders is well documented in different markets, which states that the orders are more likely to be followed by the orders of the same aggressiveness and implies the presence of short-term correlations in order flows. Based on the order flow data of 43 Chinese stocks, we investigate if there are long-range correlations in the time series of order aggressiveness. The detrending moving average analysis shows that there are crossovers in the scaling behaviors of overall fluctuations and order aggressiveness exhibits linear long-term correlations. We design an objective procedure to determine the two Hurst indexes delimited by the crossover scale. We find no correlations in the short term and strong correlations in the long term for all stocks except for an outlier stock. The long-term correlation is found to depend on several firm specific characteristics. We also find that there are nonlinear long-term correlations in the order aggressiveness when we perform the multifractal detrending moving average analysis.

scholarly journals Wavelet based deseasonalization for modelling and forecasting of daily discharge series considering long range dependence

2014 ◽  
Vol 62 (1) ◽  
pp. 24-32 ◽  
Author(s):  
Elena Szolgayová ◽  
Josef Arlt ◽  
Günter Blöschl ◽  
Ján Szolgay
Keyword(s):  
Time Series ◽  
Long Range ◽  
Moving Average ◽  
The Other ◽  
Long Range Dependence ◽  
Short Term ◽  
Forecasting Performance ◽  
Daily Discharge ◽  
Arfima Model ◽  
The Impact

Abstract Short term streamflow forecasting is important for operational control and risk management in hydrology. Despite a wide range of models available, the impact of long range dependence is often neglected when considering short term forecasting. In this paper, the forecasting performance of a new model combining a long range dependent autoregressive fractionally integrated moving average (ARFIMA) model with a wavelet transform used as a method of deseasonalization is examined. It is analysed, whether applying wavelets in order to model the seasonal component in a hydrological time series, is an alternative to moving average deseasonalization in combination with an ARFIMA model. The one-to-ten-steps-ahead forecasting performance of this model is compared with two other models, an ARFIMA model with moving average deseasonalization, and a multiresolution wavelet based model. All models are applied to a time series of mean daily discharge exhibiting long range dependence. For one and two day forecasting horizons, the combined wavelet - ARFIMA approach shows a similar performance as the other models tested. However, for longer forecasting horizons, the wavelet deseasonalization - ARFIMA combination outperforms the other two models. The results show that the wavelets provide an attractive alternative to the moving average deseasonalization.

scholarly journals A Comparative Assessment of Gap-filling Techniques for Ocean Carbon Time Series

2021 ◽  
Author(s):  
Jesse M. Vance ◽  
Kim Currie ◽  
John Zeldis ◽  
Peter Dillingham ◽  
Cliff S. Law
Keyword(s):  
Time Series ◽  
Spline Interpolation ◽  
Moving Average ◽  
Field Measurements ◽  
Linear Interpolation ◽  
Comparative Assessment ◽  
Mean Imputation ◽  
Ocean Carbon ◽  
Using Data

Abstract. Regularized time series of ocean carbon data are necessary for assessing seasonal dynamics, annual budgets, interannual variability and long-term trends. There are, however, no standardized methods for imputing gaps in ocean carbon time series, and only limited evaluation of the numerous methods available for constructing uninterrupted time series. A comparative assessment of eight imputation models was performed using data from seven long-term monitoring sites. Multivariate linear regression (MLR), mean imputation, linear interpolation, spline interpolation, Stineman interpolation, Kalman filtering, weighted moving average and multiple imputation by chained equation (MICE) models were compared using cross-validation to determine error and bias. A bootstrapping approach was employed to determine model sensitivity to varied degrees of data gaps and secondary time series with artificial gaps were used to evaluate impacts on seasonality and annual summations and to estimate uncertainty. All models were fit to DIC time series, with MLR and MICE models also applied to field measurements of temperature, salinity and remotely sensed chlorophyll, with model coefficients fit for monthly mean conditions. MLR estimated DIC with a mean error of 8.8 umol kg−1 among 5 oceanic sites and 20.0 ummol kg−1 among 2 coastal sites. The empirical methods of MLR, MICE and mean imputation retained observed seasonal cycles over greater amounts and durations of gaps resulting in lower error in annual budgets, outperforming the other statistical methods. MLR had lower bias and sampling sensitivity than MICE and mean imputation and provided the most robust option for imputing time series with gaps of various duration.

Analisis Data Time Series Menggunakan LSTM (Long Short Term Memory) Dan ARIMA (Autocorrelation Integrated Moving Average) Dalam Bahasa Python.

2020 ◽  
Vol 11 (1) ◽  
pp. 1-7
Author(s):  
Adhitio Satyo Bayangkari Karno
Keyword(s):  
Time Series ◽  
Short Term Memory ◽  
Moving Average ◽  
Average Model ◽  
Short Term ◽  
Term Memory ◽  
Moving Average Model ◽  
Long Short Term Memory

Abstrak - Penelitian ini bertujuan untuk memprediksi data deret waktu dengan menggunakan dua metode, metode pertama yang umum digunakan adalah statistik Autocorrelation Integrated Moving Average (model ARIMA) dan metode kedua yang relatif baru, yaitu pembelajaran mesin Long Short Term Memory (LSTM). Sebelum data diproses dengan kedua metode, pembersihan data dan pengoptimalan data dilakukan. Optimalisasi data adalah proses transformasi untuk menghilangkan elemen tren dan variasi dari data. Transformasi terdiri dari 7 hasil kombinasi dari proses Log, Moving Average (MA), Exponential Weigh Moving Average (EWMA), dan Differencing (Diff). Tujuh proses masing-masing digunakan dalam proses ARIMA dan LSTM. Sehingga 14 prediksi akan diperoleh (7 dari proses ARIMA dan 7 dari proses LSTM). Dari 14 hasil prediksi diperoleh nilai RMSE terkecil untuk ARIMA adalah 2% dan nilai RMSE terkecil untuk LSTM adalah 1%. Hasil penelitian ini menggunakan 7 kombinasi proses transformasi, dapat meningkatkan tingkat akurasi prediksi dari ARIMA dan LSTM. Dimana akurasi mesin pembelajaran LSTM dengan menggunakan data stok Telkom memiliki akurasi lebih tinggi dari ARIMA.

scholarly journals PENGARUH SERTIFIKAT BANK INDONESIA SYARIAH (SBIS), JUMLAH UANG BEREDAR (JUB), DAN TINGKAT INFLASI TERHADAP NILAI TUKAR RUPIAH ATAS DOLLAR AS PERIODE 2012-2017 DI INDONESIA

2020 ◽  
Vol 6 (6) ◽  
pp. 1196
Author(s):  
Lailatul Isfa Maghfiroh ◽  
Tika Widiastuti
Keyword(s):  
Exchange Rate ◽  
Quantitative Research ◽  
Inflation Rate ◽  
Short Term ◽  
Monthly Data ◽  
Time Series Method ◽  
Us Dollar ◽  
The Exchange Rate ◽  
Using Data

The Purpose of this research is to Find out the effect of macro economics factor including syaria economics like SBIS, JUB, and Inflation Rare in effect to Exchange rate Agaisnt US Dollar, in Long Term or Short Term in 2012-2017. This Research is a quantitative research using data time series. method used in this research is multiple linear regression with monthly data in 2012-2017 period. this research use data gained from the Central Statistic Agency (BPS) and Indonesia Economic Finance Statistic (SEKI). Result of this Research showed partialy, Bank of Indonesia Syaria Certificate and Total Issued Money are positively and significantly effecting exchange rate against US Dollar in 2012-2017 Period, in the other hand Inflation Rate are negatively and not significantly effecting the exchange rate against US Dollar in 2012-2017 Period. Simultaniously, Bank of Indonesia syaria Ceritificate (SBIS), Total Issued Money (JUB), and Inflation Rate are significantly effecting the exchange rate against US Dollar in 2012-2017 Period.Key Words : Exchange Rate, SBIS, JUB, Inflation

scholarly journals PERAMALAN JUMLAH PENUMPANG KERETA API MENGGUNAKAN METODE ARIMA, INTERVENSI DAN ARFIMA (Studi Kasus : Penumpang Kereta Api Kelas Lokal EkonomiDAOP IV Semarang)

2018 ◽  
Vol 7 (1) ◽  
pp. 96-109
Author(s):  
Helmi Panjaitan ◽  
Alan Prahutama ◽  
Sudarno Sudarno
Keyword(s):  
Time Series ◽  
Long Memory ◽  
Time Series Data ◽  
Moving Average ◽  
Step Function ◽  
Local Economy ◽  
Stationary Time Series ◽  
Series Data ◽  
Short Term

Autoregressive Integrated Moving Average (ARIMA) is stationary time series model after differentiation. Differentiation value of ARIMA method is an integer so it is only able to model in the short term. The best model using ARIMA method is ARIMA([13]; 1; 0) with an MSE value of 1,870844. The Intervention method is a model for time series data which in practice has extreme fluctuations both up and down. In the data plot the number of train passengers was found to be extreme fluctuation. The data used was from January 2009 to June 2017 where fluctuation up significantly in January 2016 (T=85 to T=102) so the intervention model that was suspected was a step function. The best model uses the Intervention step function is ARIMA ([13]; 1; 1) (b=0; s=18; r=0) with MSE of 1124. Autoregressive Fractionally Integrated Moving Average (ARFIMA) method is a development of the ARIMA method. The advantage of the ARFIMA method is the non-integer differentiation value so that it can overcome long memory effect that can not be solve with the ARIMA method. ARFIMA model is capable of modeling high changes in the long term (long term persistence) and explain long-term and short-term correlation structures at the same time. The number of local economy class train passengers in DAOP IV Semarang contains long memory effects, so the ARFIMA method is used to obtain the best model. The best model obtained is the ARMA(0; [1,13]) model with the differential value is 0,367546, then the model can be written into ARFIMA (0; d; [1,13]) with an MSE value of 0,00964. Based on the analysis of the three methods, the best method of analyzing the number of local economy class train passengers in DAOP IV Semarang is the ARFIMA method with the model is ARFIMA (0; 0,367546; [1,13]). Keywords: Train Passengers, ARIMA, Intervention, ARFIMA, Forecasting

Sign in / Sign up

Export Citation Format

Share Document