Good Forecasting Ability Research Articles

Can U.S. macroeconomic indicators forecast cryptocurrency volatility?

This research examines the ability of 28 U.S. macroeconomic variables to forecast the volatility of six cryptocurrencies. In- and out-of-sample analyses are performed to validate their forecasting ability. Our analysis shows that during the full-sample period, 15 variables display forecasting ability, while post-COVID-19 period, this number is 17. Among these variables, the most influential include the consumer confidence index, leading economic index, consumer price index, U.S. exports and U.S. imports. Importantly, the predictive ability of these variables appears to have strengthened during the post-COVID-19 period. The out-of-sample results confirm the effectiveness of those macroeconomic variables in the in-sample tests. Furthermore, the robustness test reveals that incorporating these U.S. macroeconomic variables can enhance the performance of the GARCH volatility model. In this study, combination methods are used to enhance forecasting stability and are proven to have good forecasting ability. Our research also indicates that integrating global macroeconomic variables can enhance forecasting ability while recognizing the valuable information provided by U.S. macroeconomic variables. Additionally, we find that variables such as the short-term government bond yield and the M1 money supply emerge as important predictors of cryptocurrency bubbles.

Seasonality of influenza-like illness and short-term forecasting model in Chongqing from 2010 to 2022

BackgroundInfluenza-like illness (ILI) imposes a significant burden on patients, employers and society. However, there is no analysis and prediction at the hospital level in Chongqing. We aimed to characterize the seasonality of ILI, examine age heterogeneity in visits, and predict ILI peaks and assess whether they affect hospital operations.MethodsThe multiplicative decomposition model was employed to decompose the trend and seasonality of ILI, and the Seasonal Auto-Regressive Integrated Moving Average with exogenous factors (SARIMAX) model was used for the trend and short-term prediction of ILI. We used Grid Search and Akaike information criterion (AIC) to calibrate and verify the optimal hyperparameters, and verified the residuals of the multiplicative decomposition and SARIMAX model, which are both white noise.ResultsDuring the 12-year study period, ILI showed a continuous upward trend, peaking in winter (Dec. - Jan.) and a small spike in May-June in the 2–4-year-old high-risk group for severe disease. The mean length of stay (LOS) in ILI peaked around summer (about Aug.), and the LOS in the 0–1 and ≥ 65 years old severely high-risk group was more irregular than the others. We found some anomalies in the predictive analysis of the test set, which were basically consistent with the dynamic zero-COVID policy at the time.ConclusionThe ILI patient visits showed a clear cyclical and seasonal pattern. ILI prevention and control activities can be conducted seasonally on an annual basis, and age heterogeneity should be considered in the health resource planning. Targeted immunization policies are essential to mitigate potential pandemic threats. The SARIMAX model has good short-term forecasting ability and accuracy. It can help explore the epidemiological characteristics of ILI and provide an early warning and decision-making basis for the allocation of medical resources related to ILI visits.

Decision Tree-Based Modeling of the Aeration Effectiveness of Circular Plunging Jets.

Since soft computing has gained a lot of attention in hydrological studies, this study focuses on predicting aeration efficiency (E20) using circular plunging jets employing soft computing techniques such as reduced error pruning tree (REPTree), random forest (RF), and M5P. The study undertaken required the development and validation of models, which were achieved using 63 experimental data values with input variables, such as angle of inclination of tilt channel (α), number of plunging jets (JN), discharge of each jet (Q), hydraulic radius of each jet (HR), and Froude number (Fr. No), to evaluate the aeration efficiency (E20), which served as the output variable. To evaluate the effectiveness of the developed models, three different statistical indices were used such as the coefficient of correlation (CC), root-mean-square error (RMSE), and mean absolute error (MAE), and it was found that all of the applied techniques possessed good forecasting ability since their correlation coefficient values were greater than 0.8. Upon testing, it was discovered that the M5P model outperformed other soft computing-based models in its ability to predict E20, as demonstrated by its correlation coefficient value of 0.9564 and notably low values of MAE (0.0143) and RMSE (0.0193).

Large-scale Mapping of Landslide and Debris Flow using Flowr Model with Statistical and Machine Learning Methods

The main purpose of this article is to establish a susceptibility zonation map of the landslides and debris flows in Phin Ngan commune, Bat Xat district, Lao Cai province on a large scale using statistical methods and machine learning combined with the FlowR model. First, the five Landslide Susceptibility Index (LSI) maps were established from two statistical models (Logistic Regression - LR, Discriminant Analysis – DA) and three machine learning models (Bayesian Network – BN, Artificial Neural Network – ANN, Support Vector Machine – SVM) were generated based on seven maps of landslide conditioning factors (slope, curvature, stream power index-SPI, topographic wetness index-TWI, sediment transportation index-STI, land use/land cover and weathering crust). Next, the five LSI maps will be evaluated for performance with the value of Area Under the Curve (AUC) according to the Receiver Operating Characteristic (ROC) curve. After that, a susceptibility map of debris flow established with FlowR software was combined with the five LSI maps created from five statistical and machine learning methods to generate a susceptibility zonation map of landslides and debris flows in the study area. The area percentage of the locations with ​​landslides and debris flows located in the zones of susceptibility (very low, low, medium, high, very high), which were created from five combined methods: BN-FlowR, LR-FlowR, DA-FlowR, ANN-FlowR, and SVM-FlowR, were compared and evaluated. The results indicate that the integrated models have given outputs with good forecasting ability. They are also very useful in land-use planning as well as the prevention and mitigation of risks due to landslides and debris flows in the research area and other similar mountainous areas.

Different Forecasting Horizons Based Performance Analysis of Electricity Load Forecasting Using Multilayer Perceptron Neural Network

With an uninterrupted power supply to the consumer, it is obligatory to balance the electricity generated by the electricity load. The effective planning of economic dispatch, reserve requirements, and quality power provision for accurate consumer information concerning the electricity load is needed. The burden on the power system engineers eased electricity load forecasting is essential to ensure the enhanced power system operation and planning for reliable power provision. Fickle nature, atmospheric parameters influence makes electricity load forecasting a very complex and challenging task. This paper proposed a multilayer perceptron neural network (MLPNN) with an association of recursive fine-tuning strategy-based different forecasting horizons model for electricity load forecasting. We consider the atmospheric parameters as the inputs to the proposed model, overcoming the atmospheric effect on electricity load forecasting. Hidden layers and hidden neurons based on performance investigation performed. Analyzed performance of the proposed model with other existing models; the comparative performance investigation reveals that the proposed forecasting model performs rigorous with a minimal evaluation index (mean square error (MSE) of 1.1506 × 10−05 for Dataset 1 and MSE of 4.0142 × 10−07 for Dataset 2 concern to the single hidden layer and MSE of 2.9962 × 10−07 for Dataset 1, and MSE of 1.0425 × 10−08 for Dataset 2 concern to two hidden layers based proposed model) and compared to the considered existing models. The proposed neural network possesses a good forecasting ability because we develop based on various atmospheric parameters as the input variables, which overcomes the variance. It has a generic performance capability for electricity load forecasting. The proposed model is robust and more reliable.

The Economy and Policy Incorporated Computing System for Social Energy and Power Consumption Analysis

Human activities, such as energy consumption and economic development, will significantly affect the natural environment, while changes in the natural environment will also affect the sustainability of human society. Studying the energy consumption changes of human society and forecasting medium and long-term electricity demand will help realize the sustainable development of energy in future society. However, current medium- and long-term electricity consumption forecasts have insufficient data samples and the inability to consider policy impacts. Here, we develop an Economy and Policy Incorporated Computing System (EPICS), which can use artificial intelligence technology to extract the summaries of energy policy texts automatically and calculate the importance index of energy policy. It can also process economic data of different lengths to expand samples of medium- and long-term electricity consumption forecasting effectively. A forecasting method that considers policy factors and mixed-frequency economic data is introduced to estimate future social energy and power consumption. This method has shown good forecasting ability in 27 months. The effect of EPICS can be demonstrated by predicting the medium- and long-term electricity demand.

A combination forecasting model of wind speed based on decomposition

Due to the intermittent, fluctuating and random characteristics of wind system, the output of wind power will become unstable with the change of wind, which brings severe challenges to the safe and stable operation of the power system. An effective way to solve this problem is to accurately forecast the wind speed. This paper presents a novel wind speed combination forecasting model based on decomposition. The innovation of the forecasting model is as follows. (a) In view of the unstable characteristics of wind speed, variational mode decomposition algorithm is introduced to decompose the historical wind speed data to obtain a series of stable components with different frequencies. (b) Echo state network with good forecasting ability is selected as the forecasting model of each component. (c) To solve the problem that the forecasting performance of echo state network is greatly affected by the parameters of the reservoir, an improved whale optimization algorithm is proposed to optimize these parameters. The optimized echo state network improves the forecasting effect. (d) The final forecasting results are obtained by adding the forecasting values of each component. (e) The performance of the developed forecasting model is verified by using two actual collected data sets of ultra-short-term wind speed and short-term wind speed. Compared with some state-of-the-art forecasting models, the comparison result curve between the forecasting value and actual value of wind speed, the forecasting error distribution, the histogram of the forecasting error distribution, the performance indicators, related statistical indicators, and Taylor diagram show that the developed forecasting model has higher prediction accuracy and is able to reflect the change laws of wind speed correctly.

Big Data Credit Report in Credit Risk Management of Consumer Finance

Traditional consumer finance is a modern financial service method that provides consumer loans to consumers of all classes. With the gradual improvement of China’s credit reporting system, big data credit reporting has effectively made up for the lack of traditional credit reporting and has been widely used in the consumer finance industry. In this context, the in‐depth analysis of the specific application of big data credit reporting in the credit risk management of consumer finance and the strengthening of the research on the application of big data credit reporting in the credit risk management of consumer finance are urgently needed to be resolved in the economic and financial theoretical and practical circles’ problem. This article mainly studies the research on credit risk management of consumer finance by big data. The experimental results of this paper show that the model has a good forecasting ability, can distinguish between normal loan customers and default loan customers, and is suitable for practical personal credit risk control business. The prediction accuracy of the default model of the fusion model is 97.14%, and the default rate corresponding to the actual business is 2.86%. By combining the risk items such as the blacklist and gray list in the Internet finance industry, the bad debt rate and illegal usury can be well controlled to meet industry supervision.

The application of vector autoregressive integrated with exogenous variable to model the relationship between covid-19 positive numbers with population growth rate

The Vector Autoregressive Integrated with Exogenous Variable (VARIX) model can be used to examine the relationship between covid-19 positive case numbers (as endogenous variables) and population growth rate (as exogenous variables) while predicting covid-19 positive case numbers. In this paper, we apply the VARIX model to covid-19 phenomena in two regencies/cities in West Java Province, Bandung and Purwakarta. The results of the analysis show that the VARIX model is a suitable model used to describe the intended relationship. The VARIX model has a good forecasting ability characterized by a relatively small MAPE value. The exogenous variables show positive results, so it can be concluded that the positive covid-19 numbers in Bandung City and Purwakarta Regency have a positive correlation with the population growth rate in West Java Province.

Reservoir characterization and production optimization using the ensemble-based optimization method and multi-layer capacitance-resistive models

Multi-Layer Capacitance-Resistive Models (ML-CRMs), unlike the Capacitance-Resistive Model (CRM), can be applied for water flooding performance prediction in a layered reservoir. The ensemble Kalman filter (EnKF) method is applied to match the parameters in ML-CRMs based on a historical production process for each layer. A methodology for maximizing production and financial gain is presented that bases the ensemble-based optimization (EnOpt) method upon the ML-CRMs as the underlying dynamical system. This allows the utilization of historical observation data to characterize and predict the layered reservoir response and further use them to control the injection and production wells to maximize financial gain from the reservoir. The EnOpt method enables the incorporation of nonlinear effects in the ML-CRMs description. Combining the EnOpt method with ML-CRMs (an approximate model), rather than reservoir simulations, is computationally efficient. This can be helpful in cases with scarce geological data or a reservoir that involves a large number of active wells. Synthetic examples of a layered reservoir are performed to validate how EnOpt/ML-CRMs can successfully match observation data with good forecasting and optimization ability.

Single-hidden layer neural networks for forecasting intermittent demand

Managing intermittent demand is a vital task in several industrial contexts, and good forecasting ability is a fundamental prerequisite for an efficient inventory control system in stochastic environments. In recent years, research has been conducted on single-hidden layer feedforward neural networks, with promising results. In particular, back-propagation has been adopted as a gradient descent-based algorithm for training networks. However, when managing a large number of items, it is not feasible to optimize networks at item level, due to the effort required for tuning the parameters during the training stage. A simpler and faster learning algorithm, called the extreme learning machine, has been therefore proposed in the literature to address this issue, but it has never been tried for forecasting intermittent demand. On the one hand, an extensive comparison of single-hidden layer networks trained by back-propagation is required to improve our understanding of them as predictors of intermittent demand. On the other hand, it is also worth testing extreme learning machines in this context, because of their lower computational complexity and good generalisation ability.In this paper, neural networks trained by back-propagation and extreme learning machines are compared with benchmark neural networks, as well as standard forecasting methods for intermittent demand on real-time series, by combining different input patterns and architectures. A statistical analysis is then conducted to validate the best performance through different aggregation levels. Finally, some insights for practitioners are presented to improve the potential of neural networks for implementation in real environments.

Molecular dynamics simulation of wetting behaviors of Li on W surfaces

A modified analytic embedded atom potential has been developed for the Li-W system. The potential has been fitted to physical quantities derived from density functional theory calculations. It is shown that the new potential is capable of reproducing the solubility of solid solution for Li-W systems. The wetting behaviors between solid tungsten and liquid Li are examined by using molecular dynamics simulations. The MD simulation results for the Li droplet wetting on the W surface illustrated that our MAEAM potential model has a good forecasting ability for the contact angle of liquid Li on W the cleaning surface above the wetting temperature. And the results of Li film dewetting from the W surfaces are consistent with relative experimental results. It is believed that the potential can be used to investigate the surfaces wettability of liquid Li on W substrate. We also simulated the lithium droplet on grooved surface. It is shown that the grooving W surfaces can obviously improve the wetting of liquid Li on W surfaces.

Nonlinear modeling and identification of proton exchange membrane fuel cell (PEMFC)

The nonlinear autoregressive moving average model with exogenous inputs (NARMAX) approach is employed to analyze time-frequency domains for the proton exchange membrane fuel cell (PEMFC) system. The time-domain nonlinear NARMAX model of PEMFC system is modeled from measured experimental input and output data. The outputs obtained by using the time-domain NARMAX model were confirmed by model validation tests which compare the model's predictive outputs with actual system outputs, in an interactive environment. This provides a potentially nondestructive tool for the modeling of a nonlinear PEMFC system. Then, the generalized frequency response function (GFRF) is employed in the frequency-domain, which is computed directly from the time-domain NARMAX model, to provide information about the types of nonlinearities in a PEMFC. The analysis revealed that the time-domain model provides better parameter estimation and a good forecasting ability. The frequency-domain response function is consistent with actual reaction mechanisms. The results illustrate that the time-frequency domain NARMAX approach can be effectively employed in modeling and identifying of PEMFC system.

The forecasting ability of world mutual funds

Purpose – The paper aims to empirically examine the forecasting ability of US-based world mutual funds during the 2001-2007 time period. Design/methodology/approach – World mutual funds are treated as portfolios composed of two sets of securities, i.e. domestic and foreign and two methodologies are used to measure forecasting ability: domestic differential exposure and assertion rates. Domestic differential exposure is based on the difference between each fund exposure to the domestic market when it is the outperforming market and the portfolio exposure to the domestic market when the foreign market is outperforming. Similar to the differential exposure, assertion rates measure the ability of fund managers to pick, on a monthly basis, an outperforming market. Findings – Although changing economic conditions in both domestic and foreign markets provided plenty of opportunities to outperform market benchmarks, the results of two empirical tests reveal that fund managers fail to effectively manage their exposure to both markets. Some evidence of good forecasting ability is found when funds are examined on a yearly basis. Originality/value – This study provides the first implementation of both methodologies: domestic differential exposure and assertion rates, to examine global funds.

Global real estate mutual funds: regional exposure and forecasting skill

Purpose – The purpose of this paper is to examine the risk-adjusted performance of US-based global real estate mutual funds (GREMFs) with emphasis on their ability to manage their domestic and foreign portfolios exposures. Design/methodology/approach – The paper applies common econometric measures of portfolio performance and implements a non-traditional methodology called attribution returns to measure forecasting ability. In this setting the paper compares the actual monthly fund return to what would have been earned by the set of indices that best reflects the fund's investment strategy during the previous month. Performance and forecasting ability is examined during two different time periods: 2001-2005 and 2006-2010. Findings – It is found that global real estate fund managers outperform the market and show good forecasting ability during the 2001-2005 time period. Good forecasting ability translates to positive risk-adjusted performance, as attribution returns are positively correlated with α. Originality/value – Despite the significant growth in the number of US-based GREMFs and the ample coverage these funds receive in the popular press, few studies are solely devoted to the examination of these funds. In this study the paper empirically examines the ability of fund managers to successfully forecast country/regional political and economic conditions as well as fluctuations in currency exchanges rates brought about by the changes they made to their portfolios’ domestic and foreign exposures.

Modeling and forecasting MODIS-based Fire Potential Index on a pixel basis using time series models

The aim of this research was to model and forecast MODIS-based Fire Potential Index (FPI), implemented with Normalized Difference Water Index (NDWI), as a proxy of forest fire risk, in Navarre (Spain) on a pixel basis using time series models with a forecasting horizon of one year.We forecast FPINDWI for 2009 based on time series from 2001 to 2008. In the modeling process, the Box and Jenkins methodology was applied in two consecutive stages. First, several generic models based on average FPINDWI time series from different “fuel type-ecoregion” combinations were developed. In a second stage, the generic models were implemented at the pixel level for the entire study region. The usefulness of the proposed autoregressive (AR) model, using the original data and introducing significant seasonal AR parameters, was demonstrated.Results show that 93.18% of the estimated models (EMs) are highly accurate and present good forecasting ability, precisely reproducing the original FPINDWI dynamics. Best results were found in the Mediterranean areas dominated by grasslands; slightly lower accuracies were found in the temperate and alpine regions, and especially in the transition areas between them and the Mediterranean region.

QSTR Studies on the Mutagenicity of Anilines

Quantitative structuretoxicity relationship (QSTR) studies play an important role in toxicity predicting, and is widely used in the study of modern compounds. Anilines represent one of the most important classes of environmental chemicals. Most of them may cause serious public health and environmental problems. The present work is to develop an effective QSTR model for mutagenicity, a toxicological endpoint which has a significant determinant of cancers, of Anilines. We calculated various descriptors and used linear regression way to select relevant parameters, and built a QSTR model that was correlation with Log P, ELUMO and heat of formation (R2=0.87, SE=0.78, Rcv2=0.867585, F=89.034). The model showed a good forecasting ability. Based on the descriptors, a further discussion was presented for the toxic mechanism. The results show that Log P value has the most important effect on anilines toxicity.

New method for reservoir characterization and optimization using CRM–EnOpt approach

A new methodology for efficiently modeling, updating, and optimizing large waterflooding operations is presented that bases the ensemble closed-loop production optimization (EnOpt) upon the capacitance resistive model (CRM) as the underlying dynamical system. This allows us to use observation data from the production wells to characterize and forecast the reservoir response and further use them to control the injection wells to maximize the reservoir production and sweep efficiency (percentage of oil in-place replaced by the injection fluid). Using an ensemble based method allows us to incorporate nonlinear effects in the CRM description and allows a real-time estimation that may incorporate a variation of reservoir parameters in the CRM model with time. Basing the EnOpt method on CRM (an approximate model) as opposed to (first principles based) the reservoir simulations allows a much quicker computational response and ultimately can be helpful in cases where geological data is scarce and/or the operation involves a large number of wells. Synthetic examples are used to demonstrate how EnOpt/CRM can successfully match for the oil and water production rates with a good forecasting ability. Final optimized injection rates lead to a significantly higher oil production and a much improved reservoir sweep efficiency.

Electromechanical equipment state forecasting based on genetic algorithm – support vector regression

Prediction of electromechanical equipments state nonlinear and non-stationary condition effectively is significant to forecast the lifetime of electromechanical equipments. In order to forecast electromechanical equipments state exactly, support vector regression optimized by genetic algorithm is proposed to forecast electromechanical equipments state. In the model, genetic algorithm is employed to choose the training parameters of support vector machine, and the SVR forecasting model of electromechanical equipments state with good forecasting ability is obtained. The proposed forecasting model is applied to the state forecasting for industrial smokes and gas turbine. The experimental results demonstrate that the proposed GA-SVR model provides better prediction capability. Therefore, the method is considered as a promising alternative method for forecasting electromechanical equipments state.

Management Insights

Management Insights