Search results

The purpose of this paper is to introduce a model to measure foreign exchange (FX) rate volatility accurately. The FX rate volatility forecasting is a crucial endeavour in financial markets and has gained the attention of researchers and practitioners over the last several decades. The implied volatility (IV) measure is widely believed to be the best measure of exchange rate volatility. Despite its widespread usage, the IV approach suffers from an obvious chicken‐egg problem: obtaining an unbiased IV requires the options to be priced correctly and calculating option prices accurately requires an unbiased IV.

The authors contribute to the literature by developing a new model for FX rate volatility – the “moneyness volatility (MV)”. This approach is based on measuring the variability of forward‐looking “moneyness” rather than use of options price. To assess volatility forecasting performance of MV against IV, the in‐sample and out‐of‐sample tests are involved using the F‐test, Granger‐Newbold test and Diebold‐Mariano framework.

The MV model outperforms the IV in FX rate volatility forecasting ability in both in‐sample and out‐of‐sample tests. The F‐test, Granger‐Newbold test and Diebold‐Mariano test results consistently reveal that MV outperforms IV in estimating as well as forecasting exchange rate volatility for six major currency options. Furthermore, in Mincer‐Zarnowitz regressions, MV outperforms IV and time‐series models in predicting future volatility.

The authors’ pioneering approach in modeling exchange rate volatility has far‐reaching implications for academicians, professional traders, and financial risk analysts and managers.

This paper aims to assess the quality of interest rate forecasts for the money markets in Argentina, Brazil, Chile, Mexico and Venezuela for the period between 2001 and 2019. Future interest rate trends are of key significance for many business-related decisions. Thus, reliable interest rate forecasts are essential, for example, for banks that make profits by carrying out maturity transformations.

The data that we analyze were collected by Consensus Economics through a monthly survey with over 120 renowned economists and were published between 2001 and 2019 in the journal Latin American Consensus Forecasts. The authors use the Diebold-Mariano test, the sign accuracy test, the TOTA coefficient and the unbiasedness test to determine the precision and biasedness of the forecasts.

The research reveals that the forecasting work carried out in Brazil, Chile and Mexico is remarkably successful. The quality of forecasts from Argentina and Venezuela, on the other hand, is significantly poorer.

Over 50 studies have already been published with regard to the accuracy of interest rate forecasts, emphasizing the importance of the topic. However, interest rate forecasts for Latin American money markets have hardly been considered thus far. The paper closes this research gap. Overall, the analyzed database amounts to a total of 209 forecast time series with 28,451 individual interest rate forecasts. This study is thus far more comprehensive than all previous studies.

Trading on electricity markets occurs such that the price settlement takes place before delivery, often day-ahead. In practice, these prices are highly volatile as they largely depend upon a range of variables such as electricity demand and the feed-in from renewable energy sources. Hence, the purpose of this paper is to provide accurate forecasts..

This paper aims at comparing different predictors stemming from supply-side (solar and wind power generation), demand-side, fuel-related and economic influences. For this reason, this paper implements a broad range of non-linear models from machine learning and draw upon the information-fusion-based sensitivity analysis.

This study disentangles the respective relevance of each predictor. This study shows that external predictors altogether decrease root mean squared errors by up to 21.96%. A Diebold-Mariano test statistically proves that the forecasting accuracy of the proposed machine learning models is superior.

The performance gain from including more predictors might be larger than from a better model. Future research should place attention on expanding the data basis in electricity price forecasting.

When developing pricing models, practitioners can achieve reasonable performance with a simple model (e.g. seasonal-autoregressive moving-average) that is built upon a wide range of predictors.

The benefit of adding further predictors has only recently received traction; however, little is known about how the individual variables contribute to improving forecasts in machine learning.

This study aims to examine the ability of clean energy stocks to provide cover for investors against market risks related to climate change and disturbances in the oil market.

The study adopts the feasible quasi generalized least squares technique to estimate a predictive model based on Westerlund and Narayan’s (2015) approach to evaluating the hedging effectiveness of clean energy stocks. The out-of-sample forecast evaluations of the oil risk-based and climate risk-based clean energy predictive models are explored using Clark and West’s model (2007) and a modified Diebold & Mariano forecast evaluation test for nested and non-nested models, respectively.

The study finds ample evidence that clean energy stocks may hedge against oil market risks. This result is robust to alternative measures of oil risk and holds when applied to data from the COVID-19 pandemic. In contrast, the hedging effectiveness of clean energy against climate risks is limited to 4 of the 6 clean energy indices and restricted to climate risk measured with climate policy uncertainty.

The study contributes to the literature by providing extensive analysis of hedging effectiveness of several clean energy indices (global, the United States (US), Europe and Asia) and sectoral clean energy indices (solar and wind) against oil market and climate risks using various measures of oil risk (WTI (West Texas intermediate) and Brent volatility) and climate risk (climate policy uncertainty and energy and environmental regulation) as predictors. It also conducts forecast evaluations of the clean energy predictive models for nested and non-nested models.

This study aims to predict hotel demand through text analysis by investigating keyword series to increase demand predictions’ precision. To do so, this paper presents a framework for modeling hotel demand that incorporates machine learning techniques.

The empirical forecasting is conducted by introducing a segmented machine learning approach of leveraging hierarchical clustering tied to machine learning and deep learning techniques. These features allow the model to yield more precise estimates. This study evaluates an extensive range of social media–derived words with the most significant probability of gradually establishing an understanding of an optimal outcome. Analyzes were performed on a major hotel chain in an urban market setting within the USA.

The findings indicate that while traditional methods, being the naïve approach and ARIMA models, struggled with forecasting accuracy, segmented boosting methods (XGBoost) leveraging social media predict hotel occupancy with greater precision for all examined time horizons. Additionally, the segmented learning approach improved the forecasts’ stability and robustness while mitigating common overfitting issues within a highly dimensional data set.

Incorporating social media into a segmented learning framework can augment the current generation of forecasting methods’ accuracy. Moreover, the segmented learning approach mitigates the negative effects of market shifts (e.g. COVID-19) that can reduce in-production forecasts’ life-cycles. The ability to be more robust to market deviations will allow hospitality firms to minimize development time.

The results are expected to generate insights by providing revenue managers with an instrument for predicting demand.

Empirical publications on the time series modeling and forecasting of electricity prices vary widely regarding the conditions, and the findings make it difficult to generalize results. Against this background, it is surprising that there is a lack of statistics-based literature reviews on the forecasting performance when comparing different models. The purpose of the present study is to fill this gap.

The authors conduct a comprehensive literature analysis from 2000 to 2015, covering 86 empirical studies on the time series modeling and forecasting of electricity spot prices. Various statistics are presented to characterize the empirical literature on electricity spot price modeling, and the forecasting performance of several model types and modifications is analyzed. The key issue of this study is to offer a comparison between different model types and modeling conditions regarding their forecasting performance, which is referred to as a quasi-meta-analysis, i.e. the analysis of analyses to achieve more general findings independent of the circumstances of single studies.

The authors find evidence that generalized autoregressive conditional heteroscedasticity models outperform their autoregressive–moving-average counterparts and that the consideration of explanatory variables improves forecasts.

To the best knowledge of the authors, this paper is the first to apply the methodology of meta-analyses in a literature review of the empirical forecasting literature on electricity spot markets.

Construction materials comprise a major part of the total construction cost. Given the importance of bitumen as a fundamental material in construction projects, it is imperative to have an accurate forecast of its consumption in the planning and material sourcing phases on the project. This study aims to introduce a flexible genetic algorithm-fuzzy regression approach for forecasting the future bitumen consumption.

In the proposed approach, the parameter tuning process is performed on all parameters of genetic algorithm (GA), and the finest coefficients with minimum errors are identified. Moreover, the fuzzy regression (FR) model is used for estimation. Analysis of variance (ANOVA) is used for selecting among GA, FR or conventional regression (CR). To show the applicability of the proposed approach, Iran’s bitumen consumption data in the period of 1991-2006 are used as a case study.

Production, import, export, road construction and price are considered as the input data used in the present study. It was concluded that, among all the forecasting methods used in this study, GA was the best method for estimating.

The proposed approach outperforms the conventional forecasting methods for the case of bitumen which is a fundamental economic ingredient in road construction projects. This approach is flexible, in terms of amount and uncertainty of the input data, and can be easily adapted for forecasting other materials and in different construction projects. It can have important implications for the managers and policy makers in the construction market where accurate estimation of the raw material demand is crucial.

This is the first in this field introducing a flexible GA-FR approach for improving bitumen consumption estimation in the construction literature. The proposed approach’s significance has two folds. Firstly, it is completely flexible. Secondly, it uses CRs as an alternative approach for estimation because of its dynamic structure.

Container throughput forecasting plays a pivotal role in strategic, tactical and operational level decision-making. The determination and analysis of the influencing factors of container throughput are observed to enhance the predicting accuracy. Therefore, for effective port planning and management, this study employs a deep learning-based method to forecast the container throughput while considering the influence of economic, environmental and social factors on throughput forecasting.

A novel multivariate container throughput forecasting method is proposed using long short-term memory network (LSTM). The external factors influencing container throughput, delineated using triple bottom line, are considered as an input to the forecasting method. The principal component analysis (PCA) is employed to reduce the redundancy of the input variables. The container throughput data of the Port of Los Angeles (PLA) is considered for empirical analysis. The forecasting accuracy of the proposed method is measured via an error matrix. The accuracy of the results is further substantiated by the Diebold-Mariano statistical test.

The result of the proposed method is benchmarked with vector autoregression (VAR), autoregressive integrated moving average (ARIMAX) and LSTM. It is observed that the proposed method outperforms other counterpart methods. Though PCA was not an integral part of the forecasting process, it facilitated the prediction by means of “less data, more accuracy.”

A novel deep learning-based forecasting method is proposed to predict container throughput using a hybridized autoregressive integrated moving average with external factors model and long short-term memory network (ARIMAX-LSTM).

The purpose of this paper is to use filtered extreme‐value theory (EVT) model to forecast one of the main emerging market stock returns and compare the predictive performance of this model with other conditional volatility models.

This paper employs eight filtered EVT models created with conditional quantile to estimate value‐at‐risk (VaR) for the Istanbul Stock Exchange. The performances of the filtered EVT models are compared to those of generalized autoregressive conditional heteroskedasticity (GARCH), GARCH with student‐t distribution, GARCH with skewed student‐t distribution, and FIGARCH by using alternative back‐testing algorithms, namely, Kupiec test, Christoffersen test, Lopez test, Diebold and Mariano test, root mean squared error (RMSE), and h‐step ahead forecasting RMSE.

The results indicate that filtered EVT performs better in terms of capturing fat‐tails in stock returns than parametric VaR models. An increase in the conditional quantile decreases h‐step ahead number of exceptions and this shows that filtered EVT with higher conditional quantile such as 40 days should be used for forward looking forecasting.

The research results show that emerging market stock return should be forecasted with filtered EVT and conditional quantile days lag length should also be estimated based on forecasting performance.

Owing to highly volatile and chaotic external events, predicting future movements of cryptocurrencies is a challenging task. This paper advances a granular hybrid predictive modeling framework for predicting the future figures of Bitcoin (BTC), Litecoin (LTC), Ethereum (ETH), Stellar (XLM) and Tether (USDT) during normal and pandemic regimes.

Initially, the major temporal characteristics of the price series are examined. In the second stage, ensemble empirical mode decomposition (EEMD) and maximal overlap discrete wavelet transformation (MODWT) are used to decompose the original time series into two distinct sets of granular subseries. In the third stage, long- and short-term memory network (LSTM) and extreme gradient boosting (XGB) are applied to the decomposed subseries to estimate the initial forecasts. Lastly, sequential quadratic programming (SQP) is used to fetch the forecast by combining the initial forecasts.

Rigorous performance assessment and the outcome of the Diebold-Mariano’s pairwise statistical test demonstrate the efficacy of the suggested predictive framework. The framework yields commendable predictive performance during the COVID-19 pandemic timeline explicitly as well. Future trends of BTC and ETH are found to be relatively easier to predict, while USDT is relatively difficult to predict.

The robustness of the proposed framework can be leveraged for practical trading and managing investment in crypto market. Empirical properties of the temporal dynamics of chosen cryptocurrencies provide deeper insights.