Forecasting Ability Research Articles

Influences of teleconnections on climate variables in northern and northeastern Thailand

Abstract Teleconnection events can influence normal regional weather patterns and affect weather forecast accuracy. To improve the forecast ability, the relationship between main teleconnections such as El Niño–Southern Oscillation (ENSO), Indian Ocean Dipole (IOD), Madden–Julian Oscillation (MJO), and climate variables (rainfall, maximum and minimum surface temperature, vertical mixing ratio, and vertical maximum temperature) was established using lag correlation coefficient and t-test methods. The results reveal moderately significant correlations between El Niño, positive IOD and rainfall, and vertical mixing ratio, which can be associated with lower-than-usual rainfall. The coincidence between El Niño and positive IOD events can worsen drought. Even though the MJO and regional weather correlations were significant, the magnitude of correlation coefficients was negligible. In addition, the spatiotemporal distribution of ENSO shows that the strong El Niño has more influence on rainfall anomalies in the post-1980s. Since there are insufficient studies on the association between teleconnections and climate variables, especially vertical mixing ratio, our findings can benefit prediction development for teleconnection-induced regional climate anomalies for extreme events and water management preparations in northern and northeastern Thailand.

Forecasting the Volatility of Real Residential Property Prices in Malaysia: A Comparison of Garch Models

Abstract The presence of volatility in residential property market prices helps investors generate substantial profit while also causing fear among investors since high volatility implies a high return with a high risk. In a financial time series, volatility refers to the degree to which the residential property market price increases or decreases during a particular period. The present study aims to forecast the volatility returns of real residential property prices (RRPP) in Malaysia using three different families of generalized autoregressive conditional heteroskedasticity (GARCH) models. The study compared the standard GARCH, EGARCH, and GJR-GARCH models to determine which model offers a better volatility forecasting ability. The results revealed that the GJR-GARCH (1,1) model is the most suitable to forecast the volatility of the Malaysian RRPP index based on the goodness-of-fit metric. Finally, the volatility forecast using the rolling window shows that the volatility of the quarterly index decreased in the third quarter (Q3) of 2021 and stabilized at the beginning of the first quarter (Q1) of 2023. Therefore, the best time to start investing in the purchase of real residential property in Malaysia would be the first quarter of 2023. The findings of this study can help Malaysian policymakers, developers, and investors understand the high and low volatility periods in the prices of residential properties to make better investment decisions.

Algal bloom ties: Systemic biogeochemical stress and Chlorophyll-a shift forecasting

Algae are deemed to be the highest carbon drawdown contributors in the world. Almost half of the world’s organic carbon is fixed by marine phytoplankton, especially during algal blooms, despite accounting for less than one percent of the total photosynthetic biomass on Earth. Nonetheless, there are growing concerns about the rise of harmful algal blooms in terms of their persistence and distribution that is a fingerprint of both global climate and local anthropogenic pressure.A novel forecasting model – combining transfer entropy network inference and a forecasting convolution neural-network – is used to predict bloom and non-bloom epidemic regimes, and their environmental determinants to define bloom sources, causes and systemic risk. The model shows high forecasting skills by extracting salient ecosystem features even without spatial dependencies. We defined a 2D entropic ecosystem mandala where the ecological impact, manifested by the distribution’s randomness of Cyanobacteria-driven chlorophyll-a (CHL-a), is proportional to the systemic environmental pressure/stress determined by a set of erratic ocean/climate and coastal/nutrient factors. Originally, a spatial risk was defined based on CHL-a magnitude, persistence and shifts. Considering the temporal variability of CHL-a in Florida Bay (FL Bay) as a case-study, we show how shifts in algal blooms are becoming more persistent in shallow areas with higher dinoflagellate/diatom ratio. This emphasizes the likely key role of cyanobacteria disorganization into phytoplankton organization, and thus the role of land discharge into the marine microbiome balance. This presents major challenges considering the increasing potential causality of green–blue algal blooms (river-dominated) for harmful red-tides with cascading socio-ecological effects, including carbon cycling alteration and ingrained eutrophication in coastal ecosystems. A universal threshold on the top 20% Pareto CHL-a extremes clearly defines bloom and non-bloom regimes independently of being endemic or epidemic, underpinned by distinct eco-environmental interactions, where the largest biogeochemical stress is structurally scale-free with CHL-a as the hub.Forecasting algal bloom in short- and long-term is indispensable for quantifying ecosystem health considering coastal-marine habitats, species and humans, as well as impacts into environmental processes such as carbon sequestration capacity. However, the increasing disorganization of biogeochemical stress decreases our forecasting ability of algal blooms except during outbreaks when is too late for prevention. This has impacts for investigating and controlling eco-environmental determinants of undesired algal bloom emergence and spread.

Time‐varying partial‐directed coherence approach to forecast global energy prices with stochastic volatility model

AbstractFor investors and policymakers, forecasting energy prices with accuracy is essential and plays a major role in the global bulk commodity markets. The current study proposes a novel hybrid forecasting model to predict global energy prices, namely, time‐varying partial‐directed coherence with stochastic volatility. The proposed method combines partial‐directed coherence analysis and stochastic volatility models. Accordingly, this study attempts to provide an in‐depth understanding of the relationship between energy markets and global economic conditions as well as the causality pathway between the underlined markets. Monthly data from January 1982 to July 2022 is used in this study. The results show a strong causality between global economic conditions, European oil, and natural gas prices and have profound implications for policymakers. For completeness, we extend the analysis to the forecasting ability of global economic conditions for oil and natural gas prices. The out‐of‐sample results show that the autoregressive model incorporating the global economic conditions index can significantly improve the accuracy of oil and gas price forecasts. In addition, our results are strongly robust over a variety of time horizons for forecasting, and they provide valuable insights into the forecasting choices to guide investment strategies in the energy and financial market.

Is tail risk priced in the cross-section of international stock index returns?

This study examines the predictive power of tail risk measures in stock indices returns using a comprehensive dataset covering 50 countries from 1926 to 2021. Our findings reveal that tail risk measures exhibit predictive power when considered independently. However, their forecasting abilities disappear when other risk and return factors are incorporated. This suggests that tail risk measures do not contain incremental information about the cross-section of stock returns beyond the commonly used global factors. Our findings are robust across various considerations, holding for alternative tail risk measure types, estimation periods, and different control variables subsets.

Identification of Immuno-Inflammation-Related Biomarkers for Acute Myocardial Infarction Based on Bioinformatics.

Previous studies have confirmed that inflammation and immunity are involved in the pathogenesis of acute myocardial infarction (AMI). However, only few related genes are identified as biomarkers for the diagnosis and treatment of AMI. GSE48060 and GSE60993 datasets were retrieved from Gene Expression Omnibus. The differentially expressed immuno-inflammation-related genes (DEIIRGs) were obtained from GSE48060, and the biomarkers for AMI were screened and validated using the "Neuralnet" package and GSE60993 dataset. Further, the biomarker-based nomogram was constructed, and miRNAs, transcription factors (TFs), and potential drugs targeting the biomarkers were explored. Furthermore, immune infiltration analysis was analyzed in AMI. Finally, the biomarkers were verified by assessing their mRNA levels using real-time quantitative PCR (RT-qPCR). First, eight biomarkers were screened via bioinformatics, and the artificial neural network model indicated a higher prediction accuracy for AMI even in the validation dataset. Nomogram had accurate forecasting ability for AMI as well. The TFs GTF2I, PHOX2B, RUNX1, and FOS targeting hsa-miR-1297 could regulate the expressions of ADM and CBLB, and RORA could effectively interact with melatonin and citalopram. RT-qPCR results for ADM, PI3, MMP9, NRG1 and CBLB were consistent with those of bioinformatic analysis. In conclusion, eight key immuno-inflammation-related genes, namely, SH2D1B, ADM, PI3, MMP9, NRG1, CBLB, RORA, and FASLG, may serve as the potential biomarkers for AMI, in which the downregulation of CBLB and upregulation of ADM, PI3, and NRG1 in AMI was detected for the first time, providing a new strategy for the diagnosis and treatment of AMI.

PEMODELAN PRODUK DOMESTIK BRUTO DI INDONESIA DENGAN PENDEKATAN SEMIPARAMETRIK POLINOMIAL LOKAL DILENGKAPI GUI-R

Gross domestic product is a measuring tool for a country's economy that needs to be known so that the country is able to consider decisions taken regarding future economic policies. The local polynomial semiparametric method that combines parametric regression and local polynomial nonparametric can be one way of predicting a country's GDP. This method is used because in GDP modeling there is one independent variable that has a linear relationship while the other variables have a pattern that tends to cluster. The modeling aims to obtain a semiparametric local polynomial model on GDP in Indonesia with the influence of coal export volume as a parametric independent variable and world oil prices as a nonparametric independent variable from the first quarter of 2005 to the second quarter of 2021 which is equipped with a GUI to simplify calculations. Based on experiments on several types of kernels, bandwidth and model degrees, the best model is local polynomial semiparametric model with Gaussian kernel weighting at degree 2 which has the smallest GCV. This model also has an R-Square value of 89.2% where the value of GDP is strongly influenced by world oil prices and coal export volumes together. The forecasting ability of this best model is said to be good because it has a MAPE of 17.127%.

Coupled data assimilation in climate research: A brief review of applications in ocean and land

Regions of the cryosphere, including the poles, that are currently unmonitored are expanding, therefore increasing the importance of satellite observations for such regions. With the increasing availability of satellite data in recent years, data assimilation research that combines forecasting models with observational data has begun to flourish. Coupled land/ice-atmosphere/ocean models generally improve the forecasting ability of models. Data assimilation plays an important role in such coupled models, by providing initial conditions and/or empirical parameter estimation. Coupled data assimilation can generally be divided into three types: uncoupled, weakly coupled, or strongly coupled. This review provides an overview of coupled data assimilation, introduces examples of its use in research on sea ice-ocean interactions and the land, and discusses its future outlook. Assimilation of coupled data constitutes an effective method for monitoring cold regions for which observational data are scarce and should prove useful for climate change research and the design of efficient monitoring networks in the future.

Combining varying training data-based artificial intelligence models for energy price forecasting

ABSTRACT In this work, the price-forecasting accuracy of an ensemble of seasonal auto-regressive integrated moving average (SARIMA), multiple linear regression (MLR), feed-forward neural network (FFNN), and radial basis function (RBF) network models has been assessed in a single series modeling framework. The methodology involved training the individual models using past data windows of varying sizes and making the forecast for the next five days on a daily rolling basis. The hourly spot price data of the Iberian Electricity Market (MIBEL) is selected as the test case system. All the models have been tested on high and low-volatile data sets to assess their forecasting abilities. The forecast performance has also been assessed by participating in a real-time forecasting competition and comparing it with the earlier models proposed in the literature. The results show that the ensemble model is effective in producing better forecasts. But its forecast accuracy is greatly affected by the size of the training window and the combination of various models. The ensemble of the FFNN and RBF network models performs best when conditions are volatile. Moreover, during volatile periods it is better to use a small window size for training as compared to a large window size.

Performance Evaluation of Technical Analysis in the Nepalese Stock Market: Implications for Investment Strategies

Purpose: This study aims to examine the performance of five widely used technical indicators on Nepal Stock Exchange (NEPSE) indexes. Specifically, the study evaluates indicators such as the simple moving average, moving average convergence and divergence, relative strength index, stochastic oscillator, and Bollinger Band. Design/methodology/approach: The study utilizes a descriptive and quantitative research design. Daily closing index data of NEPSE and its six sub-indices are analyzed for a substantial period, ranging from 1st September 2012 to 31st August 2022. The performance of the technical indicators is examined through modeling, backtesting, and statistical analysis. The technical trading rules of each indicator are incorporated into the modeling process, and the results are analyzed using different performance metrics. Furthermore, the predictability of the indicators is tested through standard statistical analysis and bootstrap techniques utilizing a random walk model. Findings: The results of the study reveal that the technical strategies, as represented by the analyzed indicators, generally support the effectiveness of technical analysis in the NEPSE. However, the relative strength index stands out as an exception, generating negative returns. The second stage of the analysis indicates that the simple moving average, relative strength, and Bollinger band fail to generate significant returns in certain indices. The findings from the bootstrap techniques further contradict the forecasting ability of technical strategies in the NEPSE, raising questions about their real performance in the Nepalese stock market. Practical Implications: This research provides valuable insights for investors, traders, and market participants in understanding the nuances and limitations of technical analysis in the context of the NEPSE. The findings suggest that technical indicators, notably the relative strength index, should be interpreted cautiously and that investing decisions should take into account additional factors. The study contributes to the ongoing discussion on the effectiveness of technical analysis in the Nepalese stock market, assisting practitioners to make informed decisions and better understand market dynamics.

Predicting Stock Market Volatility Using MODWT with HyFIS and FS.HGD Models

We enhance the precision of predicting daily stock market price volatility using the maximum overlapping discrete wavelet transform (MODWT) spectral model and two learning approaches: the heuristic gradient descent (FS.HGD) and hybrid neural fuzzy inference system (HyFIS). The FS.HGD approach iteratively updates the model’s parameters based on the error function gradient, while the HyFIS approach combines the advantages of neural networks and fuzzy logic systems to create a more robust and accurate learning model. The MODWT uses five mathematical functions to form a discrete wavelet basis. The dataset used includes the daily closing prices of the Tadawul stock market from August 2011 to December 2019. Inputs were selected based on multiple regression, tolerance, and variance inflation factor tests, and the oil price (Loil) and repo rate (Repo) were identified as input variables. The output variable is represented by the logarithm of the Tadawul stock market price (LSCS). MODWT-LA8 (ARIMA(1,1,0) with drift) outperforms other WT functions on the 80% dataset, with an ME of (0.00000532), MAE of (0.003214182), and MAPE of (0.06449683). The addition of WT functions to the FS.HGD and HyFIS models increases their forecasting ability. Based on the reduced RMSE (0.048), MAE (0.038), and MAPE (0.538), the MODWT-LA8-FS.HGD outperforms traditional models in predicting the remaining 20% of datasets.

Deep neural networks of solar flare forecasting for complex active regions

Solar flare forecasting is one of major components of operational space weather forecasting. Complex active regions (ARs) are the main source producing major flares, but only a few studies are carried out to establish flare forecasting models for these ARs. In this study, four deep learning models, called Complex Active Region Flare Forecasting Model (CARFFM)-1, −2, −3, and −4, are established. They take AR longitudinal magnetic fields, AR vector magnetic fields, AR longitudinal magnetic fields and the total unsigned magnetic flux in the neutral line region, AR vector magnetic fields and the total unsigned magnetic flux in the neutral region as input, respectively. These four models can predict the production of M-class or above flares in the complex ARs for the next 48 h. Through comparing the performance of the models, CARFFM-4 has the best forecasting ability, which has the most abundant input information. It is suggested that more valuable and rich input can improve the model performance.

APSO-TA-LSTM: a long and short term memory model combining time attention and adaptive particle swarm optimization for stock forecasting

A new stock forecasting model that combines time attention and adaptive particle swarm optimization with LSTM (APSO-TA-LSTM) is proposed to improve the forecasting ability of neural networks for financial time series. The model uses a two-layer LSTM network to encode stock information within the time window and employs time attention to strategically focus on dependencies among time series features for more accurate feature representations. Additionally, the proposed adaptive particle swarm optimization algorithm is used to pick out the key parameters of the network structure and enhance the overall prediction performance. Finally, the experimental results on three stock datasets validate the innovation and effectiveness of our method, and this work will have a broad application prospect in the study of financial time series.

Optimal Asset Allocation Model during the Economic Recession

Due to the impact of the COVID-19 pandemic, the economic situation of various industries around the world has been affected to varying degrees. Different asset types are affected in different ways. As most non-institutional investors lack sufficient professional skills, investors tend to invest in low-risk assets. Some investors only invest in a single asset without a reasonable portfolio allocation of multiple assets, resulting in the risk of one asset being equal to or higher than the portfolio investment of multiple assets. This report mainly uses the CAPM model, based on financial data from China and America from 2020 to 2022, to analyze the correlation coefficients, alpha, beta, and excess returns between different time series and different variables to get a Sharpe ratio, aiming to find the optimal model in various asset allocation combinations (stock indexes, bonds, commodity futures, and cryptocurrency). This paper mainly analyzes the forecasting ability of future returns of different asset types through a time series model and risk premium scatter diagram.

A Short-Term Forecast Method of Maximum Usable Frequency for HF Communication

To further improve the quantitative forecasting ability of high-frequency (HF) communication frequency, we propose a maximum usable frequency (MUF) adaptive forecasting method. This method has four new features: 1) The Volterra filter is introduced to this method, which is easy to implement due to the simple structure. 2) This method can forecast M(3000)F2 based on past measurements without using any previous or forecast data of geomagnetic and solar activity parameters. 3) The spatial characteristics of the M(3000)F2 can be obtained by the improved reconstruction method based on geomagnetic coordinates. 4)The high prediction accuracy can be obtained by the training data set on the 27-day (one solar rotation period). Through the statistical analysis of the measurements and predictions, the results show that the forecast values are in good agreement consistent with the measurement during the geomagnetic quiet or the disturbance periods. This method is proven to have good adaptability and usability and has a further performance improvement compared with ITU and long-term forecast models. And the root-mean-square error of MUF forecasts decreased by 1.9MHz and 0.9MHz on average, and the relative root-mean-square error decreased by 12.6% and 2.9% on average.

Risk factors for hepatic hydrothorax in patients with cirrhosis: a clinical retrospective study.

Hepatic hydrothorax, which presents as an unexplained pleural effusion, is one of the important complications in patients with end-stage cirrhosis. It has a significant correlation with prognosis and mortality. The aim of this clinical study was to detect the risk factors for hepatic hydrothorax in patients with cirrhosis and to better understand potentially life-threatening complications. Retrospectively, 978 cirrhotic patients who were hospitalized at the Shandong Public Health Clinical Center from 2013 to 2021 were involved in this study. They were divided into the observation group and the control group based on the presence of hepatic hydrothorax. The epidemiological, clinical, laboratory, and radiological characteristics of the patients were collected and analyzed. ROC curves were used to evaluate the forecasting ability of the candidate model. Furthermore, 487 cases in the experimental group were divided into left, right, and bilateral groups, and the data were analyzed. The patients in the observation group had a higher proportion of upper gastrointestinal bleeding (UGIB), a history of spleen surgery, and a higher model for end-stage liver disease (MELD) scores compared with the control group. The width of the portal vein (PVW) (P = 0.022), prothrombin activity (PTA) (P = 0.012), D-dimer (P = 0.010), immunoglobulin G (IgG) (P = 0.007), high-density lipoprotein cholesterol (HDL) (P = 0.022), and the MELD score were significantly associated with the occurrence of the hepatic hydrothorax. The AUC of the candidate model was 0.805 (P < 0.001, 95% CI = 0.758-0.851). Portal vein thrombosis was more common in bilateral pleural effusion compared with the left and right sides (P = 0.018). The occurrence of hepatic hydrothorax has a close relationship with lower HDL, PTA, and higher PVW, D-dimer, IgG, and MELD scores. Portal vein thrombosis is more common in cirrhotic patients with bilateral pleural effusion compared to those with unilateral pleural effusion.

Recent increase in the potential threat of western North Pacific tropical cyclones

Conventionally, the threat of tropical cyclones (TCs) is often described by TC intensity. However, the damage caused by TCs is also strongly related to our forecasting ability, which is usually low for TCs with high intensification rates. Here, we challenge this intensity-only criterion and propose a concept of TC potential threat (PT) for the western North Pacific TCs by jointly clustering the TC lifetime maximum intensity and intensification rate. We show that TCs can be separated via an objective algorithm, and approximately 10% of all TCs pose a great PT and feature high forecast errors. Furthermore, the annual number of TCs with high PT has increased by 22% per decade over the past 41 years, and this trend is attributed to the rise in subsurface ocean temperatures. Our study provides a perspective on the TC threat and reveals its increase due to global warming and internal climate variability.

Stock market volatility prediction: Evidence from a new bagging model

The purpose of this study is to investigate which model can improve the precision of the categorical economic policy uncertainty indices in predicting volatility in the U.S. stock market. In this study, a new model is constructed by combining autoregressive model and bagging method. The empirical outcomes indicate that machine learning models outperform traditional forecasting models and that the new model constructed in this study has the best forecasting ability. We perform robustness tests using an alternative stock index, alternative forecasting windows, and different economic cycles. The results show that these findings are robust. We hope to provide new insights into the application of the bagging method in stock market volatility forecasting.

Forecasting Taiwan stock returns via crude oil and gold futures

This study aims to predict Taiwan stock returns through gold and crude oil futures prices using monthly data from TAIEX and 19 stock sector indexes from January 1996 to December 2020. By using a 60-month rolling window horizon, we compare the forecast performances of various regression models, where the forecast performances are measured by MAE (mean absolute error) and ROS2 (out-of-sample R-square). In addition to using spot returns and the first principal component of futures returns on gold and crude oil, five traditional financial variables (dividend to price ratio, earnings to price ratio, market price to book value ratio, long-term yield, and short-term yield) are added to the regression model to explain and predict stock returns. Given that the regression models have included these traditional financial variables, the empirical results reveal that adding gold or crude oil price information to the model substantially improves its explanatory ability. Additionally, except during periods of high stock returns, the forecast ability of crude oil price information on stock returns is significantly better than traditional forecast variables. Furthermore, although gold prices are not as accurate as crude oil prices in predicting stock returns, their predictive capabilities are often better than the traditional financial variables.

Trade Integration and Economic Well-being: Evidence from Generalised Methods of Moments (GMM) in the D-8 Countries

This paper contributes to the trade–development nexus by investigating the link between trade integration and economic well-being in the developing eight (D-8) countries comprising Bangladesh, Egypt, Indonesia, Iran, Malaysia, Nigeria, Pakistan, and Turkiye. Essentially, this paper examined how trade openness, financial openness, and the exchange rate contributed to gross national income (GNI) per capita (a proxy for economic well-being). The panel data obtained from the United Nations Conference on Trade and Development (UNCTAD), the World Bank’s World Development Indicator (WDI), and the Chinn-Ito index between 2005 and 2021 were analysed using the two-step generalized method of moments (GMM), panel unit root, and Rao cointegration, among others. Evidence of a long-run relationship among the variables was established from the Kao cointegration test results at the 5 per cent significance level. This suggests that trade integration has a forecasting ability for economic well-being in the D-8 countries. The results of the two-step GMM revealed that trade openness significantly enhanced the economic well-being of the D-8 countries. This finding explains that cross-border trade among the members of the D-8 countries plays a substantial role in improving the standard of living of the population. Similarly, the results showed that as the degree of financial openness grew, economic well-being improved significantly. However, the results further revealed that exchange rate depreciation had an insignificant negative effect on economic well-being. Given the findings, this paper recommends that policymakers in the D-8 countries should synergise to implement a non-restrictive trade policy, gradually collapse the barriers to financial openness, and promote exchange rate stability to create more opportunities for economic development.