Forecasting

Accurate forecasts of the number of newly infected people during an epidemic are critical for making effective timely decisions. This paper addresses this challenge using the SIMLR model, which incorporates machine learning (ML) into the epidemiological SIR model. For each region, SIMLR tracks the changes in the policies implemented at the government level, which it uses to estimate the time-varying parameters of an SIR model for forecasting the number of new infections one to four weeks in advance. It also forecasts the probability of changes in those government policies at each of these future times, which is essential for the longer-range forecasts. We applied SIMLR to data from in Canada and the United States, and show that its mean average percentage error is as good as state-of-the-art forecasting models, with the added advantage of being an interpretable model. We expect that this approach will be useful not only for forecasting COVID-19 infections, but also in predicting the evolution of other infectious diseases. Full article

The present paper considers the problem of choosing among a collection of competing electricity price forecasting models to address a stochastic decision-making problem. We propose an event-based evaluation framework applicable to any optimization problem, where uncertainty is captured through ensembles. The task of forecast evaluation is simplified from assessing a multivariate distribution over prices to assessing a univariate distribution over a binary outcome directly linked to the underlying decision-making problem. The applicability of our framework is demonstrated for two exemplary profit-maximization problems of a risk-neutral energy trader, (i) the optimal operation of a pumped-hydro storage plant and (ii) the optimal trading of subsidized renewable energy in Germany. We compare and contrast the approach with the full probabilistic and profit–loss-based evaluation frameworks. It is concluded that the event-based evaluation framework more reliably identifies economically equivalent forecasting models, and in addition, the results suggest that an event-based evaluation specifically tailored to the rare event is crucial for decision-making problems linked to rare events. Full article

Vietnam has experienced a tourism expansion over the last decade, proving itself as one of the top tourist destinations in Southeast Asia. The country received more than 18 million international tourists in 2019, compared to only 1.5 million twenty-five years ago. Tourist spending has translated into rising employment and incomes for Vietnam’s tourism sector, making it the key driver to the socio-economic development of the country. Following the COVID-19 pandemic, only 3.8 million international tourists visited Vietnam in 2020, plummeting by 78.7% year-on-year. The latest outbreak in early summer 2021 made the sector continue to hit bottom. Although Vietnam’s tourism has suffered extreme losses, once the contagion is under control worldwide, the number of international tourists to Vietnam is expected to rise again to reach pre-pandemic levels in the next few years. First, the paper aims to provide a summary of Vietnam’s tourism characteristics with a special focus on international tourists. Next, the predictive capability of artificial neural network (ANN) methodology is examined with the datasets of international tourists to Vietnam from 2008 to 2020. Some ANN architectures are experimented with to predict the monthly number of international tourists to the country, including some lockdown periods due to the COVID-19 pandemic. The results show that, with the correct selection of ANN architectures and data from the previous 12 months, the best ANN models can be forecast for next month with a MAPE between 7.9% and 9.2%. As the method proves its forecasting accuracy, it would serve as a valuable tool for Vietnam’s policymakers and firm managers to make better investment and strategic decisions. Full article

The evolution of functional autonomy loss leads to institutionalization of people affected by Alzheimer’s disease (AD), to an alteration of their quality of life and that of their caregivers. To predict loss of functional autonomy could optimize prevention strategies, aids and cost of care. The aim of this study was to develop and to cross-validate a model to predict loss of functional autonomy as assessed by Instrumental Activities of Daily Living (IADL) score. Outpatients with probable AD and with 2 or more visits to the Clinical and Research Memory Centre of the University Hospital were included. Four Tree-Augmented Naïve bayesian networks (6, 12, 18 and 24 months of follow-up) were built. Variables included in the model were demographic data, IADL score, MMSE score, comorbidities, drug prescription (psychotropics and AD-specific drugs). A 10-fold cross-validation was conducted to evaluate robustness of models. The study initially included 485 patients in the prospective cohort. The best performance after 10-fold cross-validation was obtained with the model able to predict loss of functional autonomy at 18 months (area under the curve of the receiving operator characteristic curve = 0.741, 27% of patients misclassified, positive predictive value = 77% and negative predictive value = 73%). The 13 variables used explain 41.6% of the evolution of functional autonomy at 18 months. A high-performing predictive model of AD evolution of functional autonomy was obtained. An external validation is needed to use the model in clinical routine so as to optimize the patient care. Full article

Hybrid methods have been shown to outperform pure statistical and pure deep learning methods at forecasting tasks and quantifying the associated uncertainty with those forecasts (prediction intervals). One example is Exponential Smoothing Recurrent Neural Network (ES-RNN), a hybrid between a statistical forecasting model and a recurrent neural network variant. ES-RNN achieves a 9.4% improvement in absolute error in the Makridakis-4 Forecasting Competition. This improvement and similar outperformance from other hybrid models have primarily been demonstrated only on univariate datasets. Difficulties with applying hybrid forecast methods to multivariate data include (i) the high computational cost involved in hyperparameter tuning for models that are not parsimonious, (ii) challenges associated with auto-correlation inherent in the data, as well as (iii) complex dependency (cross-correlation) between the covariates that may be hard to capture. This paper presents Multivariate Exponential Smoothing Long Short Term Memory (MES-LSTM), a generalized multivariate extension to ES-RNN, that overcomes these challenges. MES-LSTM utilizes a vectorized implementation. We test MES-LSTM on several aggregated coronavirus disease of 2019 (COVID-19) morbidity datasets and find our hybrid approach shows consistent, significant improvement over pure statistical and deep learning methods at forecast accuracy and prediction interval construction. Full article

Despite the large efforts made by the ocean modeling community, such as the GODAE (Global Ocean Data Assimilation Experiment), which started in 1997 and was renamed as OceanPredict in 2019, the prediction of ocean currents has remained a challenge until the present day—particularly in ocean regions that are characterized by rapid changes in their circulation due to changes in atmospheric forcing or due to the release of available potential energy through the development of instabilities. Ocean numerical models’ useful forecast window is no longer than two days over a given area with the best initialization possible. Predictions quickly diverge from the observational field throughout the water and become unreliable, despite the fact that they can simulate the observed dynamics through other variables such as temperature, salinity and sea surface height. Numerical methods such as harmonic analysis are used to predict both short- and long-term tidal currents with significant accuracy. However, they are limited to the areas where the tide was measured. In this study, a new approach to ocean current prediction based on deep learning is proposed. This method is evaluated on the measured energetic currents of the Gulf of Mexico circulation dominated by the Loop Current (LC) at multiple spatial and temporal scales. The approach taken herein consists of dividing the velocity tensor into planes perpendicular to each of the three Cartesian coordinate system directions. A Long Short-Term Memory Recurrent Neural Network, which is best suited to handling long-term dependencies in the data, was thus used to predict the evolution of the velocity field in each plane, along each of the three directions. The predicted tensors, made of the planes perpendicular to each Cartesian direction, revealed that the model’s prediction skills were best for the flow field in the planes perpendicular to the direction of prediction. Furthermore, the fusion of all three predicted tensors significantly increased the overall skills of the flow prediction over the individual model’s predictions. The useful forecast period of this new model was greater than 4 days with a root mean square error less than 0.05 cm·s${}^{-1}$ and a correlation coefficient of 0.6. Full article

Forecasting volatility from econometric datasets is a crucial task in finance. To acquire meaningful volatility predictions, various methods were built upon GARCH-type models, but these classical techniques suffer from instability of short and volatile data. Recently, a novel existing normalizing and variance-stabilizing (NoVaS) method for predicting squared log-returns of financial data was proposed. This model-free method has been shown to possess more accurate and stable prediction performance than GARCH-type methods. However, whether this method can sustain this high performance for long-term prediction is still in doubt. In this article, we firstly explore the robustness of the existing NoVaS method for long-term time-aggregated predictions. Then, we develop a more parsimonious variant of the existing method. With systematic justification and extensive data analysis, our new method shows better performance than current NoVaS and standard GARCH(1,1) methods on both short- and long-term time-aggregated predictions. The success of our new method is remarkable since efficient predictions with short and volatile data always carry great importance. Additionally, this article opens potential avenues where one can design a model-free prediction structure to meet specific needs. Full article

The present study employs daily data made available by the STR SHARE Center covering the period from 1 January 2010 to 31 January 2020 for six Viennese hotel classes and their total. The forecast variable of interest is hotel room demand. As forecast models, (1) Seasonal Naïve, (2) Error Trend Seasonal (ETS), (3) Seasonal Autoregressive Integrated Moving Average (SARIMA), (4) Trigonometric Seasonality, Box–Cox Transformation, ARMA Errors, Trend and Seasonal Components (TBATS), (5) Seasonal Neural Network Autoregression (Seasonal NNAR), and (6) Seasonal NNAR with an external regressor (seasonal naïve forecast of the inflation-adjusted ADR) are employed. Forecast evaluation is carried out for forecast horizons h = 1, 7, 30, and 90 days ahead based on rolling windows. After conducting forecast encompassing tests, (a) mean, (b) median, (c) regression-based weights, (d) Bates–Granger weights, and (e) Bates–Granger ranks are used as forecast combination techniques. In the relative majority of cases (i.e., in 13 of 28), combined forecasts based on Bates–Granger weights and on Bates–Granger ranks provide the highest level of forecast accuracy in terms of typical measures. Finally, the employed methodology represents a fully replicable toolkit for practitioners in terms of both forecast models and forecast combination techniques. Full article

COVID-19 has significantly influenced tourism, including tourists’ and residents’ attitudes toward tourism. At the same time, attitudes and consumer confidence are important for economic recovery in the tourism sector. This study explores the effects of the COVID-19 pandemic on people’s attitudes toward tourism by analyzing time-series data on the number of COVID-19 positive cases, vaccinations, news sentiment, a total number of daily mentions of tourism, and the share of voice for positive and negative sentiment toward tourism. The applied data analysis techniques include descriptive analysis, visual representation of data, data decomposition into trend and cycle components, unit root tests, Granger causality test, and multiple time series regression. The results demonstrate that the COVID-19 statistics and media coverage have significant effects on interest in tourism in general, as well as the positive and negative sentiment toward tourism. The results contribute to knowledge and practice by describing the effects of the disease statistics on attitudes toward tourism, introducing social media sentiment analysis as an opportunity to measure positive and negative sentiment toward tourism, and providing recommendations for government authorities, destination management organizations, and tourism providers. Full article

High-dimensional, non-stationary vector time-series data are often seen in ground motion monitoring of geo-hazard events, e.g., landslides. For timely and reliable forecasts from such data, we developed a new statistical approach based on two advanced econometric methods, i.e., error-correction cointegration (ECC) and vector autoregression (VAR), and a newly developed dimension reduction technique named empirical dynamic quantiles (EDQ). Our ECC–VAR–EDQ method was born by analyzing a big landslide dataset, comprising interferometric synthetic-aperture radar (InSAR) measurements of ground displacement that were observed at 5090 time states and 1803 locations on a slope. The aim was to develop an early warning system for reliably forecasting any impending slope failure whenever a precursory slope deformation is on the horizon. Specifically, we first reduced the spatial dimension of the observed landslide data by representing them as a small set of EDQ series with negligible loss of information. We then used the ECC–VAR model to optimally fit these EDQ series, from which forecasts of future ground motion can be efficiently computed. Moreover, our method is able to assess the future landslide risk by computing the relevant probability of ground motion to exceed a red-alert threshold level at each future time state and location. Applying the ECC–VAR–EDQ method to the motivating landslide data gives a prediction of the incoming slope failure more than 8 days in advance. Full article

Exponential smoothing methods are one of the classical time series forecasting methods. It is well known that exponential smoothing methods are powerful forecasting methods. In these methods, exponential smoothing parameters are fixed on time, and they should be estimated with efficient optimization algorithms. According to the time series component, a suitable exponential smoothing method should be preferred. The Holt method can produce successful forecasting results for time series that have a trend. In this study, the Holt method is modified by using time-varying smoothing parameters instead of fixed on time. Smoothing parameters are obtained for each observation from first-order autoregressive models. The parameters of the autoregressive models are estimated by using a harmony search algorithm, and the forecasts are obtained with a subsampling bootstrap approach. The main contribution of the paper is to consider the time-varying smoothing parameters with autoregressive equations and use the bootstrap method in an exponential smoothing method. The real-world time series are used to show the forecasting performance of the proposed method. Full article

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. Full article

This paper examines the suitability of Google Trends data for the modeling and forecasting of interregional migration in Russia. Monthly migration data, search volume data, and macro variables are used with a set of univariate and multivariate models to study the migration data of the two Russian cities with the largest migration inflows: Moscow and Saint Petersburg. The empirical analysis does not provide evidence that the more people search online, the more likely they are to relocate to other regions. However, the inclusion of Google Trends data in a model improves the forecasting of the migration flows, because the forecasting errors are lower for models with internet search data than for models without them. These results also hold after a set of robustness checks that consider multivariate models able to deal with potential parameter instability and with a large number of regressors. Full article

The verification of probabilistic forecasts in hydro-climatology is integral to their development, use, and adoption. We propose here a means of utilizing goodness of fit measures for verifying the reliability of probabilistic forecasts. The difficulty in measuring the goodness of fit for a probabilistic prediction or forecast is that predicted probability distributions for a target variable are not stationary in time, meaning one observation alone exists to quantify goodness of fit for each prediction issued. Therefore, we suggest an additional dissociation that can dissociate target information from the other time variant part—the target to be verified in this study is the alignment of observations to the predicted probability distribution. For this dissociation, the probability integral transformation is used. To measure the goodness of fit for the predicted probability distributions, this study uses the root mean squared deviation metric. If the observations after the dissociation can be assumed to be independent, the mean square deviation metric becomes a chi-square test statistic, which enables statistically testing the hypothesis regarding whether the observations are from the same population as the predicted probability distributions. An illustration of our proposed rationale is provided using the multi-model ensemble prediction for El Niño–Southern Oscillation. Full article

In this paper, a detailed study on crime classification and prediction using deep learning architectures is presented. We examine the effectiveness of deep learning algorithms in this domain and provide recommendations for designing and training deep learning systems for predicting crime areas, using open data from police reports. Having time-series of crime types per location as training data, a comparative study of 10 state-of-the-art methods against 3 different deep learning configurations is conducted. In our experiments with 5 publicly available datasets, we demonstrate that the deep learning-based methods consistently outperform the existing best-performing methods. Moreover, we evaluate the effectiveness of different parameters in the deep learning architectures and give insights for configuring them to achieve improved performance in crime classification and finally crime prediction. Full article

In this paper, we provide a novel Bayesian solution to forecasting extreme quantile thresholds that are dynamic in nature. This is an important problem in many fields of study including climatology, structural engineering, and finance. We utilize results from extreme value theory to provide the backdrop for developing a state-space model for the unknown parameters of the observed time-series. To solve for the requisite probability densities, we derive a Rao-Blackwellized particle filter and, most importantly, a computationally efficient, recursive solution. Using the filter, the predictive distribution of future observations, conditioned on the past data, is forecast at each time-step and used to compute extreme quantile levels. We illustrate the improvement in forecasting ability, versus traditional methods, using simulations and also apply our technique to financial market data. Full article

The autoregressive model is a tool used in time series analysis to describe and model time series data. Its main structure is a linear equation using the previous values to compute the next time step; i.e., the short time relationship is the core component of the autoregressive model. Therefore, short-term effects can be modeled in an easy way, but the global structure of the model is not obvious. However, this global structure is a crucial aid in the model selection process in data analysis. If the global properties are not reflected in the data, a corresponding model is not compatible. This helpful knowledge avoids unsuccessful modeling attempts. This article analyzes the global structure of the autoregressive model through the derivation of a closed form. In detail, the closed form of an autoregressive model consists of the basis functions of a fundamental system of an ordinary differential equation with constant coefficients; i.e., it consists of a combination of polynomial factors with sinusoidal, cosinusoidal, and exponential functions. This new insight supports the model selection process. Full article

Forest fires from lightnings create a tense situation in various regions of states with forested areas. It is noted that in mountainous areas this is especially important in view of the geophysical processes of lightning activity. The aim of the study is to develop a deterministic-probabilistic approach to predicting forest fire danger due to lightning activity in mountainous regions. To develop a mathematical model, the main provisions of the theory of probability and mathematical statistics, as well as the general theory of heat transfer, were used. The scientific novelty of the research is due to the complex use of probabilistic criteria and deterministic mathematical models of tree ignition by a cloud-to-ground lightning discharge. The paper presents probabilistic criteria for predicting forest fire danger, taking into account the lightning activity, meteorological data, and forest growth conditions, as well as deterministic mathematical models of ignition of deciduous and coniferous trees by electric current of a cloud-to-ground lightning discharge. The work uses synthetic data on the discharge parameters and characteristics of the forest-covered area, which correspond to the forest fire situation in the Republic of Altay and the Republic of Buryatia (Russian Federation). The dependences of the probability for occurrence of forest fires on various parameters have been obtained. Full article