Improvement In Forecast Accuracy Research Articles

Sustainability and Dividends: Complements or Substitutes?

We examine the relationship between environmental, social, and governance commitment levels (ESG) and firm dividend-payer status. Given that larger and more profitable firms are positively associated with both payer status and ESG, it could be that ESG and dividends are complements. However, given that both dividends and ESG relate to firm spending decisions, it may be that the choice is “either/or”, and that ESG and dividends are substitutes. We document a positive relationship between ESG and dividend-payer status in U.S. firms over the period 1991–2016. In particular, we find that the proportion of dividend-payers is roughly 13% higher for firms with positive ESG compared to those with negative ESG. Including ESG in the models used to predict payer status provides, on average, a nearly 26% improvement in relative forecast accuracy. Our results are robust in regards to estimation techniques and the inclusion of variables known to be determinants of payer status. The results indicate that, on average, firms are not forced to sacrifice dividends in favor of ESG spending.

A Short-Term Forecasting Method for High-Frequency Broadcast MUF Based on LSTM

This paper proposes a short-term forecasting method for high-frequency broadcast Maximum Usable Frequency (MUF) based on Long Short-Term Memory (LSTM) to meet the demand for refined and precise high-frequency broadcast coverage. Based on the existing infrastructure of broadcast and television stations, we established an experimental verification system to collect data for approximately three years. Two links were selected based on data quality: Urumqi to Lhasa and Lanzhou to Lhasa. A short-term forecast of MUF was conducted using the data from these two links. Comparison and analysis were conducted between the forecasting results of our model and those of the REC533 model. Our proposed method outperforms the REC533 forecasting results overall, with a reduction in root mean square error (RMSE) of 0.66 MHz and an improvement in forecast accuracy of 14.77%. The comparison result demonstrates the feasibility and accuracy of our model.

Quantitative improvement of streamflow forecasting accuracy in the Atlantic zones of Canada based on hydro-meteorological signals: A multi-level advanced intelligent expert framework

Developing reliable streamflow forecasting models is critical for hydrological tasks such as improving water resource management, analyzing river patterns, and flood forecasting. In this research, for the first time, an emerging multi-level TOPSIS (technique for order preference by similarity to the ideal solution) -based hybridization comprised of the Boruta classification and regression tree (Boruta-CART) feature selection, multivariate variational mode decomposition (MVMD), and a hybrid Convolutional Neural Network (CNN) Bidirectional Gated Recurrent Unit (CNN-BiGRU) deep learning was adopted to multi-temporal (one and three days ahead) forecast the daily streamflow in the Rivers of Prince Edward Island, Canada. For this aim, in the first step, the Boruta-CART feature selection technique determines the most effective lagged components among all the antecedent two-day information (i.e., t-1 and t-2) of hydro-meteorological features (from 2015 to 2020), including the water level, mean air temperature, heat degree days, total precipitation, dew point temperature, and relative humidity in the Bear and Winter Rivers of Prince Edward Island, Canada. Afterwards, a multivariate variational mode decomposition (MVMD) decomposes the input time series to decrease the complexity and non-linearity of the non-stationary ones before feeding the deep learning (DL) models. Here, the CNN-GRU was employed as the primary DL model, along with the kernel extreme machine method (KELM), random variational function link (RVFL), and hybrid CNN bidirectional recurrent neural network (CNN-BiRNN) as the comparative models. A TOPSIS scheme applying several performance measures like the correlation coefficient (R), root mean square error (RMSE), and reliability was designed for the robustness assessment of the hybrid (MVM-CNN-BiGRU, MVM-CNN-BiRNN, MVM-RVFL, and MVM-KELM) and standalone models. The computational outcomes revealed that in the Bear River, the MVM-CNN-BiGRU, owing to its best forecasting performance (one day ahead: TOPSIS score 1, R = 0.960, RMSE = 0.098, and reliability = 65.082; three days ahead: TOPSIS score = 0.999, R = 0.924, and RMSE = 0.33) outperformed the other hybrid models, followed by the MVM-CNN-BiRNN, MVM-RVFL, and MVM-KELM, respectively. Moreover, in the Winter River, the MVM-CNN-BiGRU in terms of (one-day ahead: TOPSIS score = 0.890, R = 0.955, RMSE = 0.274, and reliability = 34.004; three-days ahead: TOPSIS score = 0.686, R = 0.924, and RMSE = 0.330) was superior to the other models. The provided expert system could be vital in the local flood decision-making process, in the absence of streamflow information as input modeling, during the flood seasons to reduce flood damage in residential areas.

Cloud type classification using deep learning with cloud images.

Clouds play a pivotal role in determining the weather, impacting the daily lives of everyone. The cloud type can offer insights into whether the weather will be sunny or rainy and even serve as a warning for severe and stormy conditions. Classified into ten distinct classes, clouds provide valuable information about both typical and exceptional weather patterns, whether they are short or long-term in nature. This study aims to anticipate cloud formations and classify them based on their shapes and colors, allowing for preemptive measures against potentially hazardous situations. To address this challenge, a solution is proposed using image processing and deep learning technologies to classify cloud images. Several models, including MobileNet V2, Inception V3, EfficientNetV2L, VGG-16, Xception, ConvNeXtSmall, and ResNet-152 V2, were employed for the classification computations. Among them, Xception yielded the best outcome with an impressive accuracy of 97.66%. By integrating artificial intelligence technologies that can accurately detect and classify cloud types into weather forecasting systems, significant improvements in forecast accuracy can be achieved. This research presents an innovative approach to studying clouds, harnessing the power of image processing and deep learning. The ability to classify clouds based on their visual characteristics opens new avenues for enhanced weather prediction and preparedness, ultimately contributing to the overall accuracy and reliability of weather forecasts.

Improving categorical and continuous accuracy of precipitation forecasts by integrating Empirical Quantile Mapping and Bernoulli-Gamma-Gaussian distribution

Statistical post-processing is a pivotal approach in enhancing the statistical accuracy and applicability of precipitation forecasts from numerical weather prediction models. The existing methods primarily focus on correcting errors in either categorical or quantitative aspects individually, failing to address both simultaneously. Furthermore, the benefits of post-processing in extending the effective lead time (ELT) have not been quantitatively examined. In this study, an integrated statistical post-processing method by combining the Empirical Quantile Mapping (EQM) and the Bernoulli-Gamma-Gaussian model (BGG) (EQM-BGG for short) is constructed, and a comprehensive accuracy metric for evaluating the ELT is also proposed. Taking the Bengbu Basin located in the upper and middle reaches of the Huai River Basin as the study area, the statistical post-processing using the three methods (EQM, BGG, EQM-BGG) is performed on the multi-model weighted integration forecast precipitation (MWIFP), which are derived from three numerical models, namely ECMWF, NCEP and CMA. The results demonstrate that the integration of EQM-BGG capitalizes on the combined strengths of EQM and BGG, facilitating a dual correction of categorical and quantitative errors. The forecast accuracy (FA) and mean absolute error (MAE) of the post-processed basin-average forecasts are enhanced by more than 10%, and the ELTs for both the entire basin and sub-basins are extended by 12–78 h. At the grid scale, EQM-BGG significantly reduces the decay rate of forecast accuracy and the expansion speed of low-accuracy regions as the lead time increases, the improvement of FAs and MAEs surpasses 10% and 20%, respectively, across all grids within the lead time of 96–102 h. Furthermore, certain grids in the northwestern part show an extension of ELTs by 18 to 54 h. These findings highlight that EQM-BGG significantly enhances both categorical and quantitative accuracy simultaneously, resulting in precipitation forecasts that exhibit greater reliability over longer lead times. This advancement enriches the methodologies for hydro-meteorological forecasts.

Maximum Likelihood Estimation for Non-Stationary Location Models with Mixture of Normal Distributions

We consider an observation-driven location model where the unobserved location variable is modeled as a random walk process and where the error variable is from a mixture of normal distributions. The time-varying location can be extended with a stationary process to account for cyclical and/or higher order autocorrelation. The mixed normal distribution can accurately approximate many continuous error distributions. We obtain a flexible modeling framework for the robust filtering and forecasting based on time-series models with non-stationary and nonlinear features. We provide sufficient conditions for strong consistency and asymptotic normality of the maximum likelihood estimator of the parameter vector in the specified model. The asymptotic properties are valid under correct model specification and can be generalized to allow for potential misspecification of the model. A simulation study is carried out to monitor the forecast accuracy improvements when extra mixture components are added to the model. In an empirical study we show that our approach is able to outperform alternative observation-driven location models in forecast accuracy for a time-series of electricity spot prices.

Forecasting realized volatility with wavelet decomposition

Forecasting Realized Volatility (RV) is of paramount importance for both academics and practitioners. During recent decades, academic literature has made substantial progress both in terms of methods and predictors under consideration albeit with scarce reference to technical indicators. This paper examines the out-of-sample forecasting performance of technical indicators for S&P500 RV relative to macroeconomic predictors. Our main contribution is to demonstrate that these sets of predictors impact volatility at different frequencies and thus are complementary. Specifically, technical indicators perform especially strongly for forecasting the short frequency component which complements macroeconomic variables which perform strongly at longer frequencies. We demonstrate that amalgamation forecasts from these predictors that takes into account the frequency dimension leads to substantial improvements in forecast accuracy.

Forecast combination puzzle in the HAR model

AbstractThe heterogeneous autoregressive (HAR) model has become the benchmark model for predicting realized volatility, given its simplicity and consistent empirical performance. Many modifications and extensions to the original model have been proposed that often only provide incremental forecast improvements. In this paper, we take a step back and view the HAR model as a forecast combination that combines three predictors: previous day realization (or random walk forecast), previous week average, and previous month average. When applying the ordinary least squares (OLS) to combine the predictors, the HAR model uses optimal weights that are known to be problematic in the forecast combination literature. In fact, an average of simpler HAR‐style models, and a simple average forecast often outperforms the optimal combination in many empirical applications. We investigate the performance of these simple combination forecasts for the realized volatility of the Dow Jones Industrial Average equity index, and a sample of individual constituent stocks, as well as across a range of other assets, commodities, exchange rates, and a range of global equity market indices. In all cases, we find dramatic improvements in forecast accuracy across all horizons and different time periods. The combinations also perform well relative to the logarithmic form of the HAR model and when using a volatility timing strategy in portfolio allocation. Thisis the first time the forecast combination puzzle is identified in this context.

A novel multi-phase hierarchical forecasting approach with machine learning in supply chain management

Hierarchical time series demands are often associated with products, time frames, or geographic aggregations. Traditionally, these hierarchies have been forecasted using “top-down,” “bottom-up,” or “middle-out” approaches. This study advocates using child-level forecasts in a hierarchical supply chain to improve parent-level forecasts. Improved forecasts can considerably reduce logistics costs, especially in e-commerce. We propose a novel multi-phase hierarchical approach for independently forecasting each series in a hierarchy using machine learning. We then combine all forecasts to allow a second-phase model estimation at the parent level. Sales data from a logistics solutions provider is used to compare our approach to “bottom-up” and “top-down” methods. Our results demonstrate an 82–90% improvement in forecast accuracy. Using the proposed method, supply chain planners can derive more accurate forecasting results by exploiting the benefit of multivariate data.

Age differences in affective forecasting accuracy.

Affective forecasts are people's predictions of their future feelings in response to future events. In this study, we examined whether younger and older adults differ in their affective forecasting accuracy. To do so, we recruited younger and older American voters and asked them to predict how they would feel following the 2020 U.S. presidential election. In the general feelings condition, participants predicted how they would feel, in general, following an election victory or loss. In the event-related feelings condition, participants predicted their future feelings specifically about an election victory and about an election loss. Later, these same participants reported their experienced feelings (either in general or about the election outcome). In the general feelings condition, age differences in affective forecasting accuracy varied as a function of whether participants' preferred candidate won or lost the election. Among election victors, there were age-related improvements in affective forecasting accuracy of negative feelings. In contrast, among election losers there were age-related declines in affective forecasting accuracy of both negative and positive feelings. A different pattern emerged for participants in the event-related feelings condition. These participants were highly accurate in their affective forecasts, and there were minimal age differences in forecasting accuracy. Together, these results show that age differences in affective forecasting accuracy depend upon both the type of future event, and the type of future feeling being predicted. When considered together, these results also suggest that the focusing illusion plays a key role in modulating age differences in affective forecasting accuracy. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

CFO gender and financial statement comparability

This study examines the effect of chief financial officers (CFOs) gender on firms' financial statement comparability. Using a sample of Chinese listed firms, we find that firms with female CFOs exhibit higher comparability relative to firms with male CFOs. We further find that the positive relation between having a female CFO and comparability disappears in the industries that are dominated with male CFOs. In additional analyses, we fail to find any significant effects of having female chief executive officers (CEOs) or other female executives on comparability, highlighting the importance of CFOs in the domain of financial reporting decisions. Finally, we show that only in non-male CFO dominated industries, greater comparability is associated with an improvement in analysts' forecast accuracy and dispersion. Overall, our findings are consistent with the view that, due to their innate personality and behavioral differences, female CFOs are likely to exhibit stronger incentives to comply with accounting rules and standards, which in turn improves comparability. We also highlight the uniqueness of comparability by showing that it does not always co-move with reporting quality since it is an inter-firm attribute rather than a firm's own reporting characteristic.

Bombardier Aftermarket Demand Forecast with Machine Learning

Intermittent demand patterns are commonly present in business aircraft spare parts supply chains. Because of the infrequent arrivals and large variations in demand, aircraft aftermarket demand is difficult to forecast, which often leads to shortages or overstocking of spare parts. In this paper, we present the development and implementation of an advanced analytics framework at Bombardier Aerospace, which is carried out by the Bombardier inventory planning team and IVADO Labs to improve the aftermarket demand forecasting process. This integrated predictive analytics pipeline leverages machine-learning (ML) models and traditional time series models in a single framework in a systematic fashion. We also make use of a tree-based machine-learning method with a large set of input features to estimate two components of intermittent demand, namely demand sizes and interdemand intervals. Through the ML models, we incorporate different features, including those derived from flight data. Outputs of different forecasting models are combined using an ensemble technique that enhances the robustness and accuracy of the forecasts for different groups of aftermarket spare parts categorized by demand patterns. The validation results show an improvement in forecast accuracy of approximately 7% and in unbiased forecast of 5%. The ML-based Bombardier Aftermarket forecasting system has been successfully deployed and used to forecast the aftermarket demand at Bombardier of more than 1 billion Canadian dollars on a regular basis. History: This paper was refereed.

Prediction Error-Based Power Forecasting of Wind Energy System Using Hybrid WT–ROPSO–NARMAX Model

The volatility and intermittency of wind energy result in highly unpredictable wind power output, which poses challenges to the stability of the intact power system when integrating large-scale wind power. The accuracy of wind power prediction is critical for maximizing the utilization of wind energy, improving the quality of power supply, and maintaining the stable operation of the power grid. To address this challenge, this paper proposes a novel hybrid forecasting model, referred to as Hybrid WT–PSO–NARMAX, which combines wavelet transform, randomness operator-based particle swarm optimization (ROPSO), and non-linear autoregressive moving average with external inputs (NARMAX). The model is specifically designed for power generation forecasting in wind energy systems, and it incorporates the interactions between the wind system’s supervisory control and data acquisition’s (SCADA) actual power record and numerical weather prediction (NWP) meteorological data for one year. In the proposed model, wavelet transform is utilized to significantly improve the quality of the chaotic meteorological and SCADA data. The NARMAX techniques are used to map the non-linear relationship between the NWP meteorological variables and SCADA wind power. ROPSO is then employed to optimize the parameters of NARMAX to achieve higher forecasting accuracy. The performance of the proposed model is compared with other forecasting strategies, and it outperforms in terms of forecasting accuracy improvement. Additionally, the proposed Prediction Error-Based Power Forecasting (PEBF) approach is introduced, which retrains the model to update the results whenever the difference between forecasted and actual wind powers exceeds a certain limit. The efficiency of the developed scheme is evaluated through a real case study involving a 180 MW grid-connected wind energy system located in Shenyang, China. The proposed model’s forecasting accuracy is evaluated using various assessment metrics, including mean absolute error (MAE) and root mean square error (RMSE), with the average values of MAE and RMSE being 0.27% and 0.30%, respectively. The simulation and numerical results demonstrated that the proposed model accurately predicts wind output power.

Wind Power Forecasts and Network Learning Process Optimization through Input Data Set Selection

Energy policies of the European Union, the United States, China, and many other countries are focused on the growth in the number of and output from renewable energy sources (RES). That is because RES has become increasingly more competitive when compared to conventional sources, such as coal, nuclear energy, oil, or gas. In addition, there is still a lot of untapped wind energy potential in Europe and worldwide. That is bound to result in continuous growth in the share of sources that demonstrate significant production variability in the overall energy mix, as they depend on the weather. To ensure efficient energy management, both its production and grid flow, it is necessary to employ forecasting models for renewable energy source-based power plants. That will allow us to estimate the production volume well in advance and take the necessary remedial actions. The article discusses in detail the development of forecasting models for RES, dedicated, among others, to wind power plants. Describes also the forecasting accuracy improvement process through the selection of the network structure and input data set, as well as presents the impact of weather factors and how much they affect the energy generated by the wind power plant. As a result of the research, the best structures of neural networks and data for individual objects were selected. Their diversity is due to the differences between the power plants in terms of location, installed capacity, energy conversion technology, land orography, the distance between turbines, and the available data set. The method proposed in the article, using data from several points and from different meteorological forecast providers, allowed us to reduce the forecast error of the NMAPE generation to 3.3%.

Cost-sensitive Tensor-based Dual-stage Attention LSTM with Feature Selection for Data Center Server Power Forecasting

Power forecasting has a guiding effect on power-aware scheduling strategies to reduce unnecessary power consumption in data centers. Many metrics related to power consumption can be collected in physical servers, such as the status of CPU, memory, and other components. However, most existing methods empirically exploit a small number of metrics to forecast power consumption. To this end, this article uses feature selection based on causality to explore the metrics that strongly influence the power consumption of different tasks. Moreover, we propose a tensor-based dual-stage attention LSTM to forecast the non-linear and non-periodic power consumption. In the proposed model, a multi-way delay embedding transform is utilized to convert the time series into tensors along the temporal direction. The LSTM combines with the tensor technique and the attention mechanism to capture the temporal pattern effectively. In addition, we adopt the cost-sensitive loss function to optimize the specific power forecasting problem in data centers. The experimental results demonstrate that our method can achieve up to 1.4% to 4.3% forecasting accuracy improvement compared with the state-of-the-art models.

Forecasting stock market volatility with regime-switching GARCH-MIDAS: The role of geopolitical risks

We investigate the role of geopolitical risks in forecasting stock market volatility at monthly horizons within a robust autoregressive Markov-switching GARCH mixed-data-sampling (AR-MSGARCH-MIDAS) framework. Our approach accounts for structural breaks through regime switching and allows us to disentangle short- and long-run volatility components. We conduct an empirical out-of-sample forecasting analysis using (i) daily Dow Jones Industrial Average returns, and (ii) monthly sampled geopolitical risks and macroeconomic variables over a time span of 122 years. We find that the impact of geopolitical risks as explanatory variables for stock market volatility forecasts at monthly horizons hinges crucially on the specific prediction model chosen by the forecaster. After capturing the non-stationarities in the data via an MSGARCH framework, we do not find significant forecast accuracy improvements through the inclusion of geopolitical risk indices.

Does audit regulation improve the underlying information used by managers? Evidence from PCAOB inspection access and management forecast accuracy

Survey evidence and academic research raise the possibility that audit regulation can impact not only the information contained in external financial reports but also the internal information used by management. We investigate this possibility by examining the improvement in management forecast accuracy around initiation of the Public Company Accounting Oversight Board's (PCAOB) international inspection program. Consistent with managers having improved information, we find that managers issue more accurate forecasts following PCAOB inspection access. Multiple additional analyses support that an improved information environment is the mechanism underlying our results, and this effect is distinct from, and incremental to, any effects of PCAOB inspection on external reporting quality. Our study provides evidence that audit regulation benefits an important internal stakeholder—managers.

A support vector machine-based method for improving real-time hourly precipitation forecast in Japan

• Improved real-time hourly precipitation forecast accuracy using machine learning. • Investigated the use of CDF-transform for short-range forecast bias correction. • Provided forcing data for the next step to enhance flood early warning accuracy. Real-time precipitation forecast facilitates water management and water-associated disaster early warning. However, numerical weather prediction (NWP) models provide precipitation forecasts with bias. This study proposed to combine support vector machine (SVM) regression with quantile-based bias correction method to improve real-time 39-hour precipitation forecasts in Japan. Five methods were compared and evaluated against observations, which include SVM regression, quantile mapping (QM), cumulative distribution function transform (CDFt), and the combination of SVM and QM (or CDFt). Results indicated that the combination of SVM and CDFt (i.e., SVM-CDFt) generally provided the highest accuracy with good computational efficiency. SVM alone improved the spatial representation of hourly precipitation with a correlation coefficient increased from 0.387 to 0.490 in January and from 0.235 to 0.296 in July in the cross-validation experiment. However, SVM underestimated the variability of hourly precipitation and heavy precipitation events. QM and CDFt perform well in correcting the bias in modeled precipitation, while they have limited capability in correcting the rainband location. Combining SVM and quantile-based method took advantage of both approaches, providing a more consistent variability with observations and better predicted extreme precipitation events, although overestimation of rainfall area was witnessed. The simple concept, high computational efficiency, as well as evident improvement in forecast accuracy make the combined cases, especially the SVM-CDFt method, beneficial for real-time precipitation forecast and flood early warning.

Pricing Information in Smart Grids: A Quality-Based Data Valuation Paradigm

With the development of Internet technology, information has become an increasingly important asset for the operation and planning of power systems. However, the existing studies and practices pay little attention to information value evaluation, i.e., the potential for information to be converted into actual economic benefits. To this end, this paper designs an information market framework and proposes a generalized information valuation model to help price data in smart grids efficiently. Here we analyze the information value of photovoltaic (PV)-related data in a power system operation problem. Specifically, we examine how additional meteorological and PV power data help to improve day-ahead forecasting accuracy, thus enhancing unit commitment (UC). In this paper, information quality is captured by two indices of a set of PV-related data, i.e., Shannon entropy and non-noise ratio. Then a neural network-based engine is employed to predict day-ahead hourly solar power on the premise of input datasets with different information quality. Here we define forecasting accuracy as information utility, and discover an exponential relationship between such utility and information quality. Finally, a two-stage stochastic UC model is formulated to quantify the contributions of different PV-related datasets, in which real-time solar power deviation is penalized. In this instance, the economic value of PV-related data is measured as the operational cost reduction induced by forecasting accuracy improvement, which we find can be estimated by information quality. Case studies based on the IEEE 30- and 118-bus systems validate the effectiveness of the proposed paradigm and method.

The closer we get, the better we are?

AbstractNot always. A general requirement in models of expectations formation is that forecast accuracy should improve when getting closer to the target date. We apply a multi‐horizon bootstrap test to a unique Israeli survey of firm‐level inflation forecasts, which encompasses periods of three digits annual rates, and periods of moderate and low inflation. We find that improvements in forecast accuracy were significant during high and moderate inflation periods, but not in the low‐inflation environment. The results are in line with rational inattention, induced by a decline in inflation predictability. Further support is provided by evidence from the US SPF survey.