Forecasting, Volume 3, Issue 2 (June 2021) – 12 articles

The random walk, no-change forecast is a customary benchmark in the literature on forecasting commodity prices. We challenge this custom by examining whether alternative models are more suited for this purpose. Based on a literature review and the results of two out-of-sample forecasting experiments, we draw two conclusions. First, in forecasting nominal commodity prices at shorter horizons, the random walk benchmark should be supplemented by futures-based forecasts. Second, in forecasting real commodity prices, the random walk benchmark should be supplemented, if not substituted, by forecasts from the local projection models. In both cases, the alternative benchmarks deliver forecasts of comparable and, in many cases, of superior accuracy. Full article

The Southeast Mediterranean (SEM) is characterized by increased vulnerability to river/stream flooding. However, impact-oriented, operational fluvial flood forecasting is far away from maturity in the region. The current paper presents the first attempt at introducing an operational impact-based warning system in the area, which is founded on the coupling of a state-of-the-art numerical weather prediction model with an advanced spatially-explicit hydrological model. The system’s modeling methodology and forecasting scheme are presented, as well as prototype results, which were derived under a pre-operational mode. Future developments and challenges needed to be addressed in terms of validating the system and increasing its efficiency are also discussed. This communication highlights that standard approaches used in operational weather forecasting in the SEM for providing flood-related information and alerts can, and should, be replaced by advanced coupled hydrometeorological systems, which can be implemented without a significant cost on the operational character of the provided services. This is of great importance in establishing effective early warning services for fluvial flooding in the region. Full article

Previous studies have shown that the treasury yield curve, T, forecasts upcoming recessions when it obtains a negative value. In this paper, we try to improve the yield curve model while keeping its parsimony. First, we show that adding the federal funds rate, FF, to the model, GDP = f(T, FF), gives seven months vs. five months warning time, and it gives a higher prediction skill for the recessions in the out-of-sample test set. Second, we find that including the quadratic term of the yield curve and the federal funds rate improves the prediction of the 1990 recession, but not the other recessions in the period 1977 to 2019. Third, the T caused a pronounced false peak in GDP for the test set. Restricting the learning set to periods where T and FF were leading the GDP in the learning set did not improve the forecast. In general, recessions are predicted better than the general movement in the economy. A “horse race” between GDP = f(T, FF) and the Michigan consumer sentiment index suggests that the first beats the latter by being a leading index for the observed GDP for more months (50% vs. 6%) during the first test year. Full article

This paper focuses on forecasting the price of Bitcoin, motivated by its market growth and the recent interest of market participants and academics. We deploy six machine learning algorithms (e.g., Artificial Neural Network, Support Vector Machine, Random Forest, k-Nearest Neighbours, AdaBoost, Ridge regression), without deciding a priori which one is the ‘best’ model. The main contribution is to use these data analytics techniques with great caution in the parameterization, instead of classical parametric modelings (AR), to disentangle the non-stationary behavior of the data. As soon as Bitcoin is also used for diversification in portfolios, we need to investigate its interactions with stocks, bonds, foreign exchange, and commodities. We identify that other cryptocurrencies convey enough information to explain the daily variation of Bitcoin’s spot and futures prices. Forecasting results point to the segmentation of Bitcoin concerning alternative assets. Finally, trading strategies are implemented. Full article

A novel forecasting method based on copula functions is proposed. It consists of an iterative algorithm in which a dependent variable is decomposed as a sum of error terms, where each one of them is estimated identifying the input variable which best “copulate” with it. The method has been tested over popular reference datasets, achieving competitive results in comparison with other well-known machine learning techniques. Full article

This study investigates the daily co-movements in commodity prices over the period 2006–2020 using a novel approach based on a time-varying Gerber correlation. The statistic is computed considering a set of probabilities estimated via non-traditional models that give a time-varying structure to the measure. The results indicate that there are several co-movements across commodities, that these co-movements change over time, and that they are tendentially positive. Conditional auto-regressive multithreshold logit models show higher forecasting accuracy for agricultural returns, while dynamic conditional correlation models are more accurate for energy products and metals. The proposed models are shown to be superior in terms of forecasting power to the benchmark method which is based on estimating the Gerber correlation moving a rolling window. Full article

Currently, manufacturing is characterized by increasing complexity both on the technical and organizational levels. Thus, more complex and intelligent production control methods are developed in order to remain competitive and achieve operational excellence. Operations management described early on the influence among target metrics, such as queuing times, queue length, and production speed. However, accurate predictions of queue lengths have long been overlooked as a means to better understanding manufacturing systems. In order to provide queue length forecasts, this paper introduced a methodology to identify queue lengths in retrospect based on transitional data, as well as a comparison of easy-to-deploy machine learning-based queue forecasting models. Forecasting, based on static data sets, as well as time series models can be shown to be successfully applied in an exemplary semiconductor case study. The main findings concluded that accurate queue length prediction, even with minimal available data, is feasible by applying a variety of techniques, which can enable further research and predictions. Full article

Recent improvements in deepfake creation have made deepfake videos more realistic. Moreover, open-source software has made deepfake creation more accessible, which reduces the barrier to entry for deepfake creation. This could pose a threat to the people’s privacy. There is a potential danger if the deepfake creation techniques are used by people with an ulterior motive to produce deepfake videos of world leaders to disrupt the order of countries and the world. Therefore, research into the automatic detection of deepfaked media is essential for public security. In this work, we propose a deepfake detection method using upper body language analysis. Specifically, a many-to-one LSTM network was designed and trained as a classification model for deepfake detection. Different models were trained by varying the hyperparameters to build a final model with benchmark accuracy. We achieved 94.39% accuracy on the deepfake test set. The experimental results showed that upper body language can effectively detect deepfakes. Full article

Accurate short-term forecasts of building energy consumption are necessary for profitable demand response. Short-term forecasting methods can be roughly classified into physics-based modelling and data-based modelling. Both of these approaches have their advantages and disadvantages and it would be therefore ideal to combine them. This paper proposes a novel approach that allows us to combine the best parts of physics-based modelling and machine learning while avoiding many of their drawbacks. A key idea in the approach is to provide a variety of building parameters as input for an Artificial Neural Network (ANN) and train the model with data from a large group of simulated buildings. The hypothesis is that this forces the ANN model to learn the underlying simulation model-based physics, and thus enables the ANN model to be used in place of the simulator. The advantages of this type of model is the combination of robustness and accuracy from a high-detail physics-based model with the inference speed, ease of deployment, and support for gradient based optimization provided by the ANN model. To evaluate the approach, an ANN model was developed and trained with simulated data from 900–11,700 buildings, including equal distribution of office buildings, apartment buildings, and detached houses. The performance of the ANN model was evaluated with a test set consisting of 60 buildings (20 buildings for each category). The normalized root mean square errors (NRMSE) were on average 0.050, 0.026, 0.052 for apartment buildings, office buildings, and detached houses, respectively. The results show that the model was able to approximate the simulator with good accuracy also outside of the training data distribution and generalize to new buildings in new geographical locations without any building specific heat demand data. Full article

The importance of high-resolution meteorological time-series data for detection of transformative changes in the climate system is unparalleled. These data sequences allow for a comprehensive study of natural and forced evolution of warming and cooling tendencies, recognition of distinct structural changes, and periodic behaviors, among other things. Such inquiries call for applications of cutting-edge analytical tools with powerful computational capabilities. In this regard, we documented the application potential of visual analytics (VA) for climate change detection in meteorological time-series data. We focused our study on long- and short-term past-to-current meteorological data of three Central European cities (i.e., Vienna, Munich, and Zürich), delivered in different temporal intervals (i.e., monthly, hourly). Our aim was not only to identify the related transformative changes, but also to assert the degree of climate change signal that can be derived given the varying granularity of the underlying data. As such, coarse data granularity mostly offered insights on general trends and distributions, whereby a finer granularity provided insights on the frequency of occurrence, respective duration, and positioning of certain events in time. However, by harnessing the power of VA, one could easily overcome these limitations and go beyond the basic observations. Full article

Smoking causes substantial amount of mortality and morbidity. This article presents the findings from simulation models that projected the impact of five potential Tobacco Endgame strategies on smoking prevalence in Ontario by 2035 and expected impact of smoking prevalence “less than 5 by 35” on tax revenue. We used Ontario SimSmoke simulation for modelling the expected impact of four strategies: plain packaging, free cessation services, decreasing the number of tobacco outlets, and increasing tobacco taxes. Separate models were used to project the impact of increasing the minimum age to legally purchase tobacco to 21 years on smoking prevalence and impact of price and tax increase to achieve “less than 5 by 35” on taxation revenue. The combined effect of four strategies in Ontario SimSmoke Model are expected to reduce smoking prevalence by 8.5% in 2035. Increasing tobacco taxes had the greatest independent predicted decrease in smoking prevalence (2.8%) followed by raised minimum age for legal purchase to 21 years (2.4%), decreasing tobacco outlets (1.5%), free cessation services (0.7%), and plain packaging (0.6%). Increasing tobacco excise tax and prices are projected to have minimal impact on taxation revenue, with a decrease from 1.5 billion to 1.2 billion annual tax receipts. Full article

The determination of electric energy consumption is remarked as one of the most vital objectives for electrical engineers as it is highly essential in determining the actual energy demand made on the existing electricity supply. Therefore, it is important to find out about the increasing trend in electric energy demands and use all over the world. In this work, we present a prediction scheme for the progression of worldwide aggregates of cumulative electricity consumption using the time series of the records released annually for the net electricity use throughout the world. Consequently, we make use of an autoregressive (AR) model by retaining the best possible autoregression order recording the highest regression accuracy and the lowest standardized regression error. The resultant regression scheme was proficiently employed to regress and forecast the evolution of next-decade data for the net consumption of electricity worldwide from 1980 to 2019 (in billion kilowatt-hours). The experimental outcomes exhibited that the highest accuracy in regressing and forecasting the global consumption of electricity is 95.7%. The prediction results disclose a linearly growing trend in the amount of electricity issued annually over the past four decades’ observation for the global net electricity consumption dataset. Full article