Application research on variation analysis model for exchange rate based lasso-BP

Accurate exchange rate forecasting is crucial for investment decisions, multinational corporations, and national policies. The nonlinear nature and volatility of the foreign exchange market hinder traditional forecasting methods in capturing exchange rate fluctuations. Despite advancements in machine learning and signal decomposition, challenges remain in high-dimensional data handling and parameter optimization. This study mitigates these constraints by introducing an innovative enhanced prediction framework that integrates the optimal complete ensemble empirical mode decomposition with adaptive noise (OCEEMDAN) method and a strategically optimized combination weight prediction model. The grey wolf optimizer (GWO) is employed to autonomously modify the noise parameters of OCEEMDAN, while the zebra optimization algorithm (ZOA) dynamically fine-tunes the weights of predictive models—Bi-LSTM, GRU, and FNN. The proposed methodology exhibits enhanced prediction accuracy and robustness through simulation experiments on exchange rate data (EUR/USD, GBP/USD, and USD/JPY). This research improves the precision of exchange rate forecasts and introduces an innovative approach to enhancing model efficacy in volatile financial markets.

In order to improve the feasibility and accuracy of explosive speed prediction, a combination of factor analysis and BP neural network method is proposed to propose an improved BP neural network prediction method. According to the raw data of the main influencing factors related to the explosion speed of explosives, the factor analysis method was used to process the dimensional data of the factors affecting the explosive speed of 20 explosives, and three common factors were obtained. The explosion rate of the original 13 explosives was replaced by three common factors. Influencing factors are used as the input layer parameters of BP neural network. The explosive explosion velocity prediction model combined with factor analysis and BP neural network method is established to predict the explosion velocity of explosives. The improved BP neural network prediction method is verified by the example data. The final verification result is that the relative average error between the predicted and actual values of the 15 training samples is 1.05%, which proves that the improved BP neural network model with training has a good fitting effect. The relative errors of the five predicted samples were 1.44%, 2.14%, 3.49%, 0.78%, and 1.95%, respectively, which were less than 10%, which proved that the improved BP neural network prediction model has better prediction accuracy.

The prediction of exchange rate is very important for both countries and enterprises. At present, the latest prediction technology is training BP neural network through the recent exchange rate data, and it takes effect in some degree. In view of the limitations of the existing BP neural network, an improved hierarchical network model based on Long Short-Term Memory (LSTM) is proposed. The model increases the time depth of the data, and uses attention mechanism to process the historical data of different time levels, which makes the prediction ability of the model stronger. Taking the exchange rate of US dollar / rupee as an example, by comparing with the basic LSTM model and BP neural network, it is proved that the proposed model has a better effect.

BP neural network has a good effect on data prediction. Using BP neural network to predict polymer fire risk index (IFHI) is a cross research method based on computer intelligent learning model and traditional fire risk assessment. In order to solve the defect of low precision of BP neural network in IFHI prediction, a solution to standardize the initial data processing is proposed to optimize the BP neural network simulation model. In the construction of BP neural network model, the range, threshold, and weight of the initial data need to be processed globally, and then the BP neural network is simulated and trained. Finally, the data is simulated and predicted by using MATLAB. The output results of the neural network with different data standardization processing methods are compared to verify the simulation accuracy. The results show that the input node parameters of BP neural network are processed by Z-score normalization method, which improves the learning ability of the model, improves the accuracy of the prediction effect, and reduces the IFHI error of prediction.

We propose to utilize the band spectral regression for out-of-sample forecasts of exchange rates. When one period ahead forecast is considered, there is some evidence that the band spectral regression improves its accuracy, especially when the Taylor rule fundamentals model is employed. However, when the forecasting horizon increases, the purchasing power parity (PPP) fundamentals model is found to be powerful, and we can improve the out-of-sample forecast by selecting appropriate frequency bands. Bayesian model averaging shows that placing a large weight on the business cycle frequency improves the accuracy of the out-of-sample forecasting of the PPP model (as well as the monetary fundamentals model) when a longer forecasting horizon is our focus. Without specifying the frequency bands prior to applying the regression, LASSO can provide better out-of-sample exchange rate forecasts for many cases – most patently for the PPP fundamentals model – and provide information about the dynamic relationship between forecasting variables and exchange rates. The frequency domain approach not only improves the accuracy of exchange rate forecast but provides insights for understanding why the PPP fundamentals act as a powerful predictor when the forecasting horizon increases and there is a possible improvement in the time domain regression forecast.

The risk evaluation of empty mine mined-out area is of great significance to the security and stability of the power facilities. But influence evaluation of empty mine mined-out area factor multitudinous, this paper selected seven factors associated with the system. Based on the principle of BP neural network, we build a 3 layer BP neural network model suitable for grid risk evaluation. The BP neural network model was trained by collected samples of empty mine mined-out area and the logical parameters of BP neural network were acquired and tested by the testing samples for accuracy, and finally we proposes preventive measures based on the evaluation.

PurposeThis study constructs time series model, artificial neural networks (ANNs) and statistical topologies to examine the volatility and forecast foreign exchange rates. The Mauritian forex market has been utilized as a case study, and daily data for nominal spot rate (during a time period of five years spanning from 2014 to 2018) for EUR/MUR, GBP/MUR, CAD/MUR and AUD/MUR have been applied for the predictions.Design/methodology/approachAutoregressive integrated moving average (ARIMA) and generalized autoregressive conditional heteroskedasticity (GARCH) models are used as a basis for time series modelling for the analysis, along with the non-linear autoregressive network with exogenous inputs (NARX) neural network backpropagation algorithm utilizing different training functions, namely, Levenberg–Marquardt (LM), Bayesian regularization and scaled conjugate gradient (SCG) algorithms. The study also features a hybrid kernel principal component analysis (KPCA) using the support vector regression (SVR) algorithm as an additional statistical tool to conduct financial market forecasting modelling. Mean squared error (MSE) and root mean square error (RMSE) are employed as indicators for the performance of the models.FindingsThe results demonstrated that the GARCH model performed better in terms of volatility clustering and prediction compared to the ARIMA model. On the other hand, the NARX model indicated that LM and Bayesian regularization training algorithms are the most appropriate method of forecasting the different currency exchange rates as the MSE and RMSE seemed to be the lowest error compared to the other training functions. Meanwhile, the results reported that NARX and KPCA–SVR topologies outperformed the linear time series models due to the theory based on the structural risk minimization principle. Finally, the comparison between the NARX model and KPCA–SVR illustrated that the NARX model outperformed the statistical prediction model. Overall, the study deduced that the NARX topology achieves better prediction performance results compared to time series and statistical parameters.Research limitations/implicationsThe foreign exchange market is considered to be instable owing to uncertainties in the economic environment of any country and thus, accurate forecasting of foreign exchange rates is crucial for any foreign exchange activity. The study has an important economic implication as it will help researchers, investors, traders, speculators and financial analysts, users of financial news in banking and financial institutions, money changers, non-banking financial companies and stock exchange institutions in Mauritius to take investment decisions in terms of international portfolios. Moreover, currency rates instability might raise transaction costs and diminish the returns in terms of international trade. Exchange rate volatility raises the need to implement a highly organized risk management measures so as to disclose future trend and movement of the foreign currencies which could act as an essential guidance for foreign exchange participants. By this way, they will be more alert before conducting any forex transactions including hedging, asset pricing or any speculation activity, take corrective actions, thus preventing them from making any potential losses in the future and gain more profit.Originality/valueThis is one of the first studies applying artificial intelligence (AI) while making use of time series modelling, the NARX neural network backpropagation algorithm and hybrid KPCA–SVR to predict forex using multiple currencies in the foreign exchange market in Mauritius.

Why use Markov-switching models in exchange rate prediction?

RELATIONSHIP BETWEEN OIL PRICES, EXCHANGE RATES AND MAIZE PRICES IN KENYA

This study aims to predict the exchange rat based on radial basis function neural network (RBFNN). Concerning the selected sample point, it only responds to the inputs of neighboring samples and hence has better approximation performance and overall optimization than other forwarding networks, in addition to being simple in structure and fast in training speed. RBFNN in empirical risk minimization methods has been studied, their adaptability to exchange rate prediction has been explored, and these methods have been verified by exchange rate data. The contributions are proposing an exchange rate prediction algorithm based on RBFNN and more accurately predicting short-term and long-term exchange rate variation trends.

Introduction: Macroeconomic problems such as inflation and exchange rates are often highlighted as benchmarks for achieving economic progress. The stability of both must be monitored by the government in order to control the inflation rate and exchange rate. This instability is a phenomenon of fluctuation, namely the phenomenon of the rise and fall of the exchange rate of a currency based on demand and supply. Given the large impact of exchange rate fluctuations on the economy, the prediction of the wage exchange rate against the US dollar is considered necessary because it is useful to anticipate and minimize bad possibilities that arise. Method: Methods that can be used to analyze fluctuating currency exchange rate data are nonparametric regression, Nadaraya-Watson estimator, Gaussian kernel function, and Local Polynomial Regression. Results and Discussion: The results of a nonparametric regression comparison between the Nadaraya-Watson estimator, Gaussian kernel function, and local polynomial regression were obtained by MAPE of 2.508% and 0.179%, respectively. This shows that the best model uses the local polynomial regression method and predicted USD exchange rate data against IDR using the best model, namely Local polynomial Regression where the MAPE value is less than 10%, which means the prediction rate is very good. Conclusion: The nonparametric regression method of the Nadaraya-Watrson estimator, Gaussian kernel function, and local polynomial regression shows that the best model uses the local polynomial regression method.

Vessel traffic flow forecasting is indispensable for the development of national shipping industry and the coordinated development of regional economy. In this paper, an improved PSO-BP (particle swarm optimization-back propagation) prediction model is established for the prediction of the total vessel traffic flow in a designated port area. The presented prediction model is referred to as SAPSO-BP neural network which utilizes the SAPSO (self-adaptive particle swarm optimization) algorithm to adjust the structure parameters of BP neural network. Facilitated by the establishment of foundation networks and satellite communication of Automatic Identification System (AIS) receivers, the detailed information of vessel is becoming increasingly obtainable. Therefore, a large number of real-observed vessel traffic flow data based on AIS records of Port area of Los Angeles (LA) has been chosen as the testing database to validate the effectiveness of the SAPSO-BP prediction model in vessel traffic flow forecasting. The grey correlation analysis (GCA) is employed to confirm the input dimension of the prediction model. Finally, simulation results demonstrate that the presented prediction approach can achieve vessel traffic flow trend predictions with reasonable, satisfactory convergence and stability.

In this study, the author focus on the exchange rate forecasting. Exchange rates fluctuation is extremely complex, not only contains the linear part but also includes non-linear elements, In this paper, Simulated Annealing Algorithm is introduced to overcome the neural network easy fall into local minimum defects in BP neural network basis, in order to optimize the network weights and thresholds, and thus improve the prediction accuracy. Through several forecast experiments about the major currencies against, the result show that compare to the single use of BP neural network, after introduced Simulated Annealing Algorithm, the prediction accuracy and stability has been further improved, meanwhile time-consuming less than genetic algorithms and other optimization algorithms.

Professional forecasts of interest rates and exchange rates: Evidence from the Wall Street Journal’s panel of economists

In this paper, three different versions of bivariate GARCH in mean models were considered to explain the relationship between uncertainty and average outcomes of the stock index and exchange rate. From the empirical results, the bivariate EGARCH-M is the best model to explain the volatility in the two markets. This paper revealed four important conclusions. First, there is a negative relationship between the exchange rates return and stock prices return, but the current exchange rates return is positively affected by the lagged stock prices return at 5% significance level. Second, the results provide strong empirical confirmation of the first hypothesis (that uncertainty in foreign exchange market has an effect on average stock prices) and third hypothesis (that uncertainty in stock market has an effect on average stock prices), implying a negative effect of stock index uncertainty and a positive effect of exchange rates uncertainty on average stock index. On the other hand, for the exchange rates equation, the GARCH-in-mean variables in AR modeling are significant. This shows that there is a positive effect of exchange rates uncertainty and a negative effect of stock index uncertainty on average exchange rates. Third, the coefficient on the lagged residual variance is greater for stock index than for exchange rates, implying that stock index shocks have longer lived effects on uncertainty in the stock market than exchange rates shock have on uncertainty in the foreign exchange market. Finally, from the magnitude of coefficient that shows the effect of the last period’s shock, volatility is more sensitive to its own lagged values than it is to new surprises in the foreign exchange market.