International Gold Price Forecast Based on CEEMDAN and Support Vector Regression with Grey Wolf Algorithm

Lu, Wanbo; Qiu, Tingting; Shi, Wenhui; Sun, Xiaojun

doi:10.1155/2022/1511479

Cited by 9 publications

(3 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Researchers reported that Bi-LSTM Network outperformed other networks such as LSTM, CNN-LSTM, and CNN-Bi-LSTM. Lu et al [ 25 ] predicted the gold price using a hybrid model called complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN)- grey wolf optimizer (GWO)- SVR and high-frequency intrinsic mode functions subsequence (IMFH), low-frequency intrinsic mode functions subsequence (IMFL), and the residual as input data. The IMFL and the residual have higher correlations compared to IMFH.…”

Section: Related Workmentioning

confidence: 99%

Gold price prediction by a CNN-Bi-LSTM model along with automatic parameter tuning

Amini,

Kalantari

2024

PLoS ONE

View full text Add to dashboard Cite

Banking and stock markets consider gold to be an important component of their economic and financial status. There are various factors that influence the gold price trend and its fluctuations. Accurate and reliable prediction of the gold price is an essential part of financial and portfolio management. Moreover, it could provide insights about potential buy and sell points in order to prevent financial damages and reduce the risk of investment. In this paper, different architectures of deep neural network (DNN) have been proposed based on long short-term memory (LSTM) and convolutional-based neural networks (CNN) as a hybrid model, along with automatic parameter tuning to increase the accuracy, coefficient of determination, of the forecasting results. An illustrative dataset from the closing gold prices for 44 years, from 1978 to 2021, is provided to demonstrate the effectiveness and feasibility of this method. The grid search technique finds the optimal set of DNNs’ parameters. Furthermore, to assess the efficiency of DNN models, three statistical indices of RMSE, RMAE, and coefficient of determination (R2), were calculated for the test set. Results indicate that the proposed hybrid model (CNN-Bi-LSTM) outperforms other models in total bias, capturing extreme values and obtaining promising results. In this model, CNN is used to extract features of input dataset. Furthermore, Bi-LSTM uses CNN’s outputs to predict the daily closing gold price.

show abstract

Section: Related Workmentioning

confidence: 99%

Gold price prediction by a CNN-Bi-LSTM model along with automatic parameter tuning

Amini,

Kalantari

2024

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…The forecasting performance of SVR is mainly affected by C and gamma (Ngo N et al, 2022), so we used optimization algorithms to optimize these two parameters. Based on previous literature and the performance of the three optimization algorithms in this paper, for fairness, we have the same settings for all three algorithms (Lu et al, 2022;Mohammed S et al, 2022;Sharma and Shekhawat et al, 2022;Su X et al, 2022): iterations: 30; population: 20; and lower and upper bound [0.1,1]. In the Bagging algorithm, the main factors that affect its performance include base learners and data samples (Mohammed and Kora et al, 2023).…”

Section: Parameter Settingmentioning

confidence: 99%

Henry Hub monthly natural gas price forecasting using CEEMDAN–Bagging–HHO–SVR

Duan,

Zhang,

Wang

2023

Front. Energy Res.

View full text Add to dashboard Cite

As a clean fossil energy source, natural gas plays a crucial role in the global energy transition. Forecasting natural gas prices is an important area of research. This paper aims at developing a novel hybrid model that contributes to the prediction of natural gas prices. We develop a novel hybrid model that combines the “Decomposition Algorithm” (CEEMDAN), “Ensemble Algorithm” (Bagging), “Optimization Algorithm” (HHO), and “Forecasting model” (SVR). The hybrid model is used for monthly Henry Hub natural gas forecasting. To avoid the problem of data leakage caused by decomposing the whole time series, we propose a rolling decomposition algorithm. In addition, we analyzed the factors affecting Henry Hub natural gas prices for multivariate forecasting. Experimental results indicate that the proposed model is more effective than the traditional model at predicting natural gas prices.

show abstract

“…Additionally, accurate forecasting of gold prices can benefit commodity markets and the global economy. Predicting gold prices' volatility more precisely allows market participants to make better-informed decisions regarding their investments in gold [20][21][22][23].…”

Section: Introductionmentioning

confidence: 99%

The Importance of Gold’s Effect on Investment and Predicting the World Gold Price Using the ARIMA and ARIMA-GARCH Model

Bunnag

2024

Ekon. J. Econ.

View full text Add to dashboard Cite

This paper studies the importance of gold's effect on investment and the fact that gold is often seen as a safe-haven asset during economic uncertainty. When inflation rates rise, investors may turn to gold to preserve their wealth; the government will reserve gold to reduce the exchange rate risk. To provide a comprehensive analysis, the study incorporates forecasting the price of gold using both the Autoregressive Integrated Moving Average (ARIMA) and ARIMA-Generalized Autoregressive Conditional Heteroskedasticity (ARIMA-GARCH) models. The gold price data is daily from 1/01/2021 to 3/01/2024. We perform model comparisons that the ARIMA (2,1,3) and the ARIMA (2,1,3)-GARCH (1,1), which model gives lower mean absolute error (MAE) and root mean squared error (RMSE) values. The results show that the MAE and RMSE predictions of the ARIMA (2,1,3)-GARCH (1,1) model are 80.1371 and 96.8299, better than those of the other model. Therefore, the ARIMA (2,1,3)-GARCH (1,1) model forecast results are better precise. It gives a forecast value for gold prices in the world market at the end of 2024 of 1942.094 USD per troy ounce. Hence, the recommendation for investors and policymakers is that if the price is higher than 1942.094 USD per troy ounce in 2024, investors and policymakers should slow down to buy and wait for it to adjust first, or investors and policymakers with gold should gradually sell to make some profit. Moreover, good portfolio management will reduce the exchange rate risk by including an optimized amount of gold in currency portfolios. However, holding gold is risky; its prices may fluctuate due to factors beyond our control, such as war, uncertainty about world economic growth, and inflation. Therefore, investors and policymakers should consider the abovementioned factors and be careful when hedging in gold.

show abstract

International Gold Price Forecast Based on CEEMDAN and Support Vector Regression with Grey Wolf Algorithm

Cited by 9 publications

References 50 publications

Gold price prediction by a CNN-Bi-LSTM model along with automatic parameter tuning

Gold price prediction by a CNN-Bi-LSTM model along with automatic parameter tuning

Henry Hub monthly natural gas price forecasting using CEEMDAN–Bagging–HHO–SVR

The Importance of Gold’s Effect on Investment and Predicting the World Gold Price Using the ARIMA and ARIMA-GARCH Model

Contact Info

Product

Resources

About