Deep learning models for visibility forecasting using climatological data

Low visibility conditions affect safety and traffic operations, leading to adverse scenarios that often result in serious accidents. Due to the complexity and variability associated with modeling weather variables, visibility forecasting remains a highly challenging task and a matter of significant interest for transportation agencies nationwide. Given that the literature on single-step visibility forecasting is very scarce, this study explores the use of deep learning models for single-step visibility forecasting using time series climatological data. Five different deep learning models were developed, trained, and tested using data from two weather stations located in the US state of Florida, which is one of the top states nationwide dealing with low visibility problems. The authors provide discussions of the models’ results and areas for future research.     

Evaluating the forecasting performance of econometric models of air passenger traffic flows using multiple error measures

Airline traffic forecasting is important to airlines and regulatory authorities. This paper examines a number of approaches to forecasting short- to medium-term air traffic flows. It contributes as a rare replication, testing a variety of alternative modelling approaches. The econometric models employed include autoregressive distributed lag (ADL) models, time-varying parameter (TVP) models and an automatic method for econometric model specification. A vector autoregressive (VAR) model and various univariate alternatives are also included to deliver unconditional forecast comparisons. Various approaches for taking into account interactions between contemporaneous air traffic flows are examined, including pooled ADL models and the enhanced models with the addition of a “world trade” variable. Based on the analysis of a number of forecasting error measures, it is concluded that pooled ADL models that include the “world trade” variable outperform the alternatives, and in particular univariate methods; and, second, that automatic modelling procedures are enhanced through judgmental intervention. In contrast to earlier results, the TVP models do not improve accuracy. Depending on the preferred error measure, the difference in accuracy may be substantial.     

A novel text-based framework for forecasting agricultural futures using massive online news headlines

The agricultural futures prices are generally considered difficult to forecast because the causes of fluctuations are incredibly complicated. We propose a text-based forecasting framework, which can effectively identify and quantify factors affecting agricultural futures based on massive online news headlines. A comprehensive list of influential factors can be formed using a text mining method called topic modeling. A new sentiment-analysis-based way is designed to quantify the factors such as the weather and policies that are important yet difficult to quantify. The proposed framework is empirically tested at forecasting soybean futures prices in the Chinese market. Testing was based on 9715 online news headlines from July 19, 2012 to July 9, 2018. The results show that the identified influential factors and sentiment-based variables are effective, and the proposed framework performs significantly better in medium-term and long-term forecasting than the benchmark model.     

Systemic risk in European financial and energy sectors: Dynamic factor copula approach

We perform an analysis of systemic risk in financial and energy sectors in Europe using daily time series of CDS spreads. We employ the factor copula model with GAS dynamics from Oh and Patton (2018) for the purpose of estimating dependency structures between market participants. Based on the estimated models, we perform Monte Carlo simulations to obtain future values of CDS spreads, and then measure the probability of systemic events at given time points. We conclude that substantially higher systemic risk is present in the financial sector compared to the energy sector. We also find that the most systemically vulnerable financial and energy companies come from Spain.     

Diversification for general copula dependence

We generalize the extreme value analysis for Archimedean copulas (see Alink , Löwe and Wüthrich , 2003) to the non-Archimedean case: Assume we have d ≥2 exchangeable and continuously distributed risks X ₁,…, X _d . Under appropriate assumptions there is a constant q _d such that, for all large u , we have . The constant q _d describes the asymptotic dependence structure. Typically, q _d will depend on more aspects of this dependence structure than the well-known tail dependence coefficient.     

Bayesian forecasting and portfolio decisions using dynamic dependent sparse factor models

We extend the recently introduced latent threshold dynamic models to include dependencies among the dynamic latent factors which underlie multivariate volatility. With an ability to induce time-varying sparsity in factor loadings, these models now also allow time-varying correlations among factors, which may be exploited in order to improve volatility forecasts. We couple multi-period, out-of-sample forecasting with portfolio analysis using standard and novel benchmark neutral portfolios. Detailed studies of stock index and FX time series include: multi-period, out-of-sample forecasting, statistical model comparisons, and portfolio performance testing using raw returns, risk-adjusted returns and portfolio volatility. We find uniform improvements on all measures relative to standard dynamic factor models. This is due to the parsimony of latent threshold models and their ability to exploit between-factor correlations so as to improve the characterization and prediction of volatility. These advances will be of interest to financial analysts, investors and practitioners, as well as to modeling researchers.     

Macroeconomic forecasting using structural factor analysis

The use of a small number of underlying factors to summarize the information from a much larger set of information variables is one of the new frontiers in forecasting. In prior work, the estimated factors have not usually had a structural interpretation and the factors have not been chosen on a theoretical basis. In this paper we propose several variants of a general structural factor forecasting model, and use these to forecast certain key macroeconomic variables. We make the choice of factors more structurally meaningful by estimating factors from subsets of information variables, where these variables can be assigned to subsets on the basis of economic theory. We compare the forecasting performance of the structural factor forecasting model with that of a univariate AR model, a standard VAR model, and some non-structural factor forecasting models. The results suggest that our structural factor forecasting model performs significantly better in forecasting real activity variables, especially at short horizons.     

Predicting monthly biofuel production using a hybrid ensemble forecasting methodology

This paper proposes a hybrid ensemble forecasting methodology that integrating empirical mode decomposition (EMD), long short-term memory (LSTM) and extreme learning machine (ELM) for the monthly biofuel (a typical agriculture-related energy) production based on the principle of decomposition—reconstruction—ensemble. The proposed methodology involves four main steps: data decomposition via EMD, component reconstruction via a fine-to-coarse (FTC) method, individual prediction via LSTM and ELM algorithms, and ensemble prediction via a simple addition (ADD) method. For illustration and verification, the biofuel monthly production data of the USA is used as the our sample data, and the empirical results indicate that the proposed hybrid ensemble forecasting model statistically outperforms all considered benchmark models considered in terms of the forecasting accuracy. This indicates that the proposed hybrid ensemble forecasting methodology integrating the EMD-LSTM-ELM models based on the decomposition—reconstruction—ensemble principle has been proved to be a competitive model for the prediction of biofuel production.     

A general method for addressing forecasting uncertainty in inventory models

In practice, inventory decisions depend heavily on demand forecasts, but the literature typically assumes that demand distributions are known. This means that estimates are substituted directly for the unknown parameters, leading to insufficient safety stocks, stock-outs, low service, and high costs. We propose a framework for addressing this estimation uncertainty that is applicable to any inventory model, demand distribution, and parameter estimator. The estimation errors are modeled and a predictive lead time demand distribution obtained, which is then substituted into the inventory model. We illustrate this framework for several different demand models. When the estimates are based on ten observations, the relative savings are typically between 10% and 30% for mean-stationary demand. However, the savings are larger when the estimates are based on fewer observations, when backorders are costlier, or when the lead time is longer. In the presence of a trend, the savings are between 50% and 80% for several scenarios.     

Text-based crude oil price forecasting: A deep learning approach

This study proposes a new, novel crude oil price forecasting method based on online media text mining, with the aim of capturing the more immediate market antecedents of price fluctuations. Specifically, this is an early attempt to apply deep learning techniques to crude oil forecasting, and to extract hidden patterns within online news media using a convolutional neural network (CNN). While the news-text sentiment features and the features extracted by the CNN model reveal significant relationships with the price change, they need to be grouped according to their topics in the price forecasting in order to obtain a greater forecasting accuracy. This study further proposes a feature grouping method based on the Latent Dirichlet Allocation (LDA) topic model for distinguishing effects from various online news topics. Optimized input variable combination is constructed using lag order selection and feature selection methods. Our empirical results suggest that the proposed topic-sentiment synthesis forecasting models perform better than the older benchmark models. In addition, text features and financial features are shown to be complementary in producing more accurate crude oil price forecasts.     

Modeling and forecasting of Brazilian reservoir inflows via dynamic linear models

This work focuses on developing a forecasting model for the water inflow at an hydroelectric plant’s reservoir for operations planning. The planning horizon is 5 years in monthly steps. Due to the complex behavior of the monthly inflow time series we use a Bayesian dynamic linear model that incorporates seasonal and autoregressive components. We also use climate variables like monthly precipitation, El Niño and other indices as predictor variables when relevant. The Brazilian power system has 140 hydroelectric plants. Based on geographical considerations, these plants are collated by basin and classified into 15 groups that correspond to the major river basins, in order to reduce the dimension of the problem. The model is then tested for these 15 groups. Each group will have a different forecasting model that can best describe its unique seasonality and characteristics. The results show that the forecasting approach taken in this paper produces substantially better predictions than the current model adopted in Brazil (see Maceira & Damazio, 2006), leading to superior operations planning.     

Forecast combinations of computational intelligence and linear models for the NN5 time series forecasting competition

In this work we introduce the forecasting model with which we participated in the NN5 forecasting competition (the forecasting of 111 time series representing daily cash withdrawal amounts at ATM machines). The main idea of this model is to utilize the concept of forecast combination, which has proven to be an effective methodology in the forecasting literature. In the proposed system we attempted to follow a principled approach, and make use of some of the guidelines and concepts that are known in the forecasting literature to lead to superior performance. For example, we considered various previous comparison studies and time series competitions as guidance in determining which individual forecasting models to test (for possible inclusion in the forecast combination system). The final model ended up consisting of neural networks, Gaussian process regression, and linear models, combined by simple average. We also paid extra attention to the seasonality aspect, decomposing the seasonality into weekly (which is the strongest one), day of the month, and month of the year seasonality.     

The performance of alternative forecasting methods for SETAR models

We compare a number of methods that have been proposed in the literature for obtaining h-step ahead minimum mean square error forecasts for self-exciting threshold autoregressive (SETAR) models. These forecasts are compared to those from an AR model. The comparison of forecasting methods is made using Monte Carlo simulation. The Monte-Carlo method of calculating SETAR forecasts is generally at least as good as that of the other methods we consider. An exception is when the disturbances in the SETAR model come from a highly asymmetric distribution, when a Bootstrap method is to be preferred.An empirical application calculates multi-period forecasts from a SETAR model of US gross national product using a number of the forecasting methods. We find that whether there are improvements in forecast performance relative to a linear AR model depends on the historical epoch we select, and whether forecasts are evaluated conditional on the regime the process was in at the time the forecast was made.     

Comparison of intraday probabilistic forecasting of solar irradiance using only endogenous data

Accurate solar forecasts are necessary to improve the integration of solar renewables into the energy grid. In recent years, numerous methods have been developed for predicting the solar irradiance or the output of solar renewables. By definition, a forecast is uncertain. Thus, the models developed predict the mean and the associated uncertainty. Comparisons are therefore necessary and useful for assessing the skill and accuracy of these new methods in the field of solar energy.The aim of this paper is to present a comparison of various models that provide probabilistic forecasts of the solar irradiance within a very strict framework. Indeed, we consider focusing on intraday forecasts, with lead times ranging from 1 to 6 h. The models selected use only endogenous inputs for generating the forecasts. In other words, the only inputs of the models are the past solar irradiance data. In this context, the most common way of generating the forecasts is to combine point forecasting methods with probabilistic approaches in order to provide prediction intervals for the solar irradiance forecasts. For this task, we selected from the literature three point forecasting models (recursive autoregressive and moving average (ARMA), coupled autoregressive and dynamical system (CARDS), and neural network (NN)), and seven methods for assessing the distribution of their error (linear model in quantile regression (LMQR), weighted quantile regression (WQR), quantile regression neural network (QRNN), recursive generalized autoregressive conditional heteroskedasticity (GARCHrls), sieve bootstrap (SB), quantile regression forest (QRF), and gradient boosting decision trees (GBDT)), leading to a comparison of 20 combinations of models.None of the model combinations clearly outperform the others; nevertheless, some trends emerge from the comparison. First, the use of the clear sky index ensures the accuracy of the forecasts. This derived parameter permits time series to be deseasonalized with missing data, and is also a good explanatory variable of the distribution of the forecasting errors. Second, regardless of the point forecasting method used, linear models in quantile regression, weighted quantile regression and gradient boosting decision trees are able to forecast the prediction intervals accurately.     

Probabilistic wind forecasting up to three months ahead using ensemble predictions for geopotential height

We develop a method for forecasting the distribution of the daily surface wind speed at timescales from 15-days to 3-months in France. On such long-term timescales, ensemble predictions of the surface wind speed have poor performance, however, the wind speed distribution may be related to the large-scale circulation of the atmosphere, for which the ensemble forecasts have better skill. The information from the large-scale circulation, represented by the 500 hPa geopotential height, is summarized into a single index by first running a PCA and then a polynomial regression. We estimate, over 20 years of daily data, the conditional probability density of the wind speed at a specific location given the index. We then use the ECMWF seasonal forecast ensemble to predict the index for horizons from 15-days to 3-months. These predictions are plugged into the conditional density to obtain a distributional forecast of surface wind. These probabilistic forecasts remain sharper than the climatology up to 1-month forecast horizon. Using a statistical postprocessing method to recalibrate the ensemble leads to further improvement of our probabilistic forecast, which then remains calibrated and sharper than the climatology up to 3-months horizon, particularly in the north of France in winter and fall.     

Density forecasting with Bayesian Vector Autoregressive models under macroeconomic data uncertainty

Macroeconomic data are subject to data revisions. Yet, the usual way of generating real-time density forecasts from Bayesian Vector Autoregressive (BVAR) models makes no allowance for data uncertainty from future data revisions. We develop methods of allowing for data uncertainty when forecasting with BVAR models with stochastic volatility. First, the BVAR forecasting model is estimated on real-time vintages. Second, the BVAR model is jointly estimated with a model of data revisions such that forecasts are conditioned on estimates of the ‘true’ values. We find that this second method generally improves upon conventional practice for density forecasting, especially for the United States.     

Automatic selection of unobserved components models for supply chain forecasting

For many companies, automatic forecasting has come to be an essential part of business analytics applications. The large amounts of data available, the short life-cycle of the analysis and the acceleration of business operations make traditional manual data analysis unfeasible in such environments. In this paper, an automatic forecasting support system that comprises several methods and models is developed in a general state space framework built in the SSpace toolbox written for Matlab. Some of the models included are well-known, such as exponential smoothing and ARIMA, but we also propose a new model family that has been used only very rarely in this context, namely unobserved components models. Additional novelties include the use of unobserved components models in an automatic identification environment and the comparison of their forecasting performances with those of exponential smoothing and ARIMA models estimated using different software packages. The new system is tested empirically on a daily dataset of all of the products sold by a franchise chain in Spain (166 products over a period of 517 days). The system works well in practice and the proposed automatic unobserved components models compare very favorably with other methods and other well-known software packages in forecasting terms.     

Parameter-efficient deep probabilistic forecasting

Probabilistic time series forecasting is crucial in many application domains, such as retail, ecommerce, finance, and biology. With the increasing availability of large volumes of data, a number of neural architectures have been proposed for this problem. In particular, Transformer-based methods achieve state-of-the-art performance on real-world benchmarks. However, these methods require a large number of parameters to be learned, which imposes high memory requirements on the computational resources for training such models. To address this problem, we introduce a novel bidirectional temporal convolutional network that requires an order of magnitude fewer parameters than a common Transformer-based approach. Our model combines two temporal convolutional networks: the first network encodes future covariates of the time series, whereas the second network encodes past observations and covariates. We jointly estimate the parameters of an output distribution via these two networks. Experiments on four real-world datasets show that our method performs on par with four state-of-the-art probabilistic forecasting methods, including a Transformer-based approach and WaveNet, on two point metrics (sMAPE and NRMSE) as well as on a set of range metrics (quantile loss percentiles) in the majority of cases. We also demonstrate that our method requires significantly fewer parameters than Transformer-based methods, which means that the model can be trained faster with significantly lower memory requirements, which as a consequence reduces the infrastructure cost for deploying these models.     

Online adaptive lasso estimation in vector autoregressive models for high dimensional wind power forecasting

Wind power forecasts with lead times of up to a few hours are essential to the optimal and economical operation of power systems and markets. Vector autoregression (VAR) is a framework that has been shown to be well suited to predicting for several wind farms simultaneously by considering the spatio-temporal dependencies in their time series. Lasso penalisation yields sparse models and can avoid overfitting the large numbers of coefficients in higher dimensional settings. However, estimation in VAR models usually does not account for changes in the spatio-temporal wind power dynamics that are related to factors such as seasons or wind farm setup changes, for example. This paper tackles this problem by proposing a time-adaptive lasso estimator and an efficient coordinate descent algorithm for updating the VAR model parameters recursively online. The approach shows good abilities to track changes in the multivariate time series dynamics on simulated data. Furthermore, in two case studies it shows clearly better predictive performances than the non-adaptive lasso VAR and univariate autoregression.     

Relative performance of judgmental methods for forecasting the success of megaprojects

Forecasting the success of megaprojects, such as the Olympic Games or space exploration missions, is a very difficult but important task, due to their complexity and the large capital investment they require. Typically, megaproject stakeholders do not employ formal forecasting methods, but instead rely on impact assessments and/or cost–benefit analysis; however, as these tools do not necessarily include forecasts, there is no accountability. This study evaluates the effectiveness of judgmental methods for successfully forecasting the accomplishment of specific megaproject objectives, where the measure of success is the collective accomplishment of such objectives. We compare the performances of three judgmental methods used by a group of 69 semi-experts: unaided judgement (UJ), semi-structured analogies (s-SA), and interaction groups (IG). The empirical evidence reveals that the use of s-SA leads to accuracy improvements relative to UJ. These improvements are amplified further when we introduce the pooling of analogies through teamwork in IG.