Journal of Forecasting最新文献

The endless adverse effects of air pollution incidents have raised significant public concerns in the past few decades. The measure of air pollution, that is, the air quality index (AQI), is highly volatile and associated with different kinds of uncertainties. Following this, the study and development of accurate fuzzy time series forecasting (TSF) methods for predicting the AQI have a significant role in air pollution control and management. Motivated by this, in this paper, a systematic study is made to evaluate the true potential of fuzzy TSF methods employing traditional fuzzy set (TFS), intuitionistic fuzzy set (IFS), hesitant fuzzy set (HFS), and neutrosophic fuzzy set (NFS) in forecasting the AQI. Two novel high-order fuzzy TSF methods, TFS-multilayer perceptron (MLP) and HFS-MLP, are proposed employing TFS and HFS in which ratio trend variation of AQI data is used instead of original AQI, MLP is used to model the fuzzy logical relationships (FLRs), and none/mean of aggregated membership values are used while modeling the FLRs using MLP. The results from the proposed fuzzy TSF methods are compared with recently proposed fuzzy TSF methods employing TFS, IFS, and NFS and six popular machine learning models, including MLP, support vector regression (SVR), Bagging Regressors, XGBoost, long-short term memory (LSTM), and convolutional neural network (CNN). The “Wilcoxon Signed-Rank test” and “Friedman and Nemenyi hypothesis test” are applied to the results obtained by employing different ratios in the train-validation-test to draw decisive conclusions reliably. The simulation results show the statistical dominance of the proposed TFS-MLP method over all other crisp and fuzzy TSF methods employed in this paper.

This study develops a multi-stage stochastic model to forecast the issuance of green bonds using the Filtered Historical Simulation (FHS) method to identify the most cost-effective conditions for issuing these bonds amid various risk factors. Drawing on historical yield data and financial metrics of corporate green bonds from December 2014 to June 2023, the model considers fluctuating elements such as risk probabilities, financial risks in worst-case scenarios, and liquidity risks at upcoming issuance moments. Our findings reveal the model's effectiveness in pinpointing the lowest possible costs of issuing new green bond portfolios in the future, while also addressing expected financial risk, risk occurrence probability, and liquidity issues. The results provide issuers with the insights needed to accurately time the market, tailor bond maturities according to a corporation's future risk profile, and enhance liquidity management. Notably, our model indicates that refining the estimated probability of future risk occurrences can lead to significant savings in green bond issuance costs. This approach allows for adaptable bond issuance strategies, addresses inherent debt, and enables detailed risk management, offering substantial benefits for green enterprises navigating the complexities of future financial landscapes.

The study uses time-varying Granger causality models that incorporate two proxies for Twitter policy uncertainty and South African returns stock returns to investigate the causal relationship between Twitter uncertainty and South African stock returns for the period between 2017 and 2023. The findings demonstrate that Twitter Market Uncertainty and Twitter Economic Uncertainty mostly lead JSE returns around the start of the COVID-19 pandemic and the Russia-Ukranainan war respectively. The findings also show significant out-of-sample forecasts using uncertainty indexes from Twitter.

This article analyzes characteristics of takeover targets in the European market—relatively less studied compared with US and UK markets—to develop a takeover prediction model. Our sample includes 320 European companies with 140 targets and 180 non-targets over the period 1994–2007, covering two M&A waves. In this study, we test the discriminating power of many relevant variables including new one that could have a discriminating power in potentially determining (value creation). Our results show that European targets are characterized by a growth-resource imbalance, are less rich in FCF, have growth opportunities, have a higher level of transaction volume of shares prior to the bid, achieve lower economic performance, and destroy value. Furthermore, we develop several predictive models using targets' financial data from 1 year, 2 years, and 3 years before takeover, along with the 3-year average. The correct classification power in the original sample is 70% (in-sample). As for predictive ability, the correct classification power in a control sample is 79.4% (out-of-sample). We also noted that predictive models using data from 1 or 2 years before the bid appear to display more significant predictive ability.

We evaluate whether professional forecasters incorporate valuable information from public discussions on social media. The study covers the case of inflation in Argentina for the period 2016–2022. We find solid evidence consistent with inattention. A simple indicator of attention to inflation on social media is shown to anticipate professional forecast errors. A one standard deviation increment in the indicator is followed by a rise of 0.4% in mean forecast errors in the subsequent month and by a cumulative increment of 0.7% over the next 6 months. Furthermore, social media content anticipates significant revisions in forecasts that target multiple months ahead inflation and calendar year inflation. These findings are different from previously documented forms of inattention. Consistent results are verified by implementing out-of-sample forecasts and using content from an alternative social network. The study has implications for the use of professional forecasts in the context of policymaking and sheds new evidence on the nature of imperfect information in macroeconomics.

Forecasting and analyzing corporate financial performance are of significant value to investors, managers, and regulators. In this paper, we constructed the one-dimensional convolutional neural networks (1D-CNN) and long short-term memory (LSTM) deep learning models to investigate the feasibility of forecasting corporate financial performance with deep learning models, using the corporate financial features and environment, social and governance (ESG) rating index of Chinese A-share listed corporation data from 2015 to 2021. Five evaluation metrics were employed to measure models' forecasting effects, and four competing machine learning models were built to verify the improvement in forecasting accuracy brought by the deep learning models. Furthermore, we also introduced the Accumulated Local Effects method to explore the forecasting processes of the deep learning models. The empirical results show the following: (1) Deep learning models can effectively extract the time-series information in corporate data, thereby solving the task of predicting corporate financial performance with high accuracy. (2) The introduction of ESG information significantly contributes to the forecasting accuracy of corporate financial performance. For both 1D-CNN and LSTM models, the ESG rating index can provide additional useful information for forecasting. (3) The interpretable results reveal the preference and emphasis of the two deep learning models for the different features. This further proves the robustness and reliability of deep learning models in forecasting corporate financial performance.

This paper proposes a method of forecasting US recessions beginning with data displays that contain the last 12 quarters of seven US expansions. These end-of-expansion displays allow observers to see for themselves what is different about the last year before recessions compared with the two earlier years. Using a statistical model that treats this historical data as draws from a 12-dimensional multivariate normal distribution, the most recent data are probabilistically inserted into these images where the recent data are most like the historical data. This is a recession forecast based not on presumed patterns but on patterns revealed by the data.

Financial distress prediction (FDP) has attracted high attention from many financial institutions. Utilizing supervised learning-based methods in FDP, however, is time consuming and labor intensive. Therefore, in this paper, we exploit active-pSVM method, which combines potential data distribution information and existing expert experience to solve FDP problem. Moreover, with the increasingly popular textual information, we construct several features on our protocol that are based on the Management Discussion and Analysis (MD&A) text information. Using datasets that are collected in different time windows from the listed Chinese companies, we conducted an extensive experiment and were able to confirm a better efficiency of our active-pSVM, when compared with some common supervised learning-based methods. Our study also covers the application of MD&A text information on weakly supervised learning model in FDP.

This paper aims to study the volatility forecasting of Chinese crude oil futures from the large-scale variables perspective by considering both the information on international futures markets volatility and technical indicators of Chinese crude oil futures. We employ the dual feature processing method (LASSO-PCA) by integrating least absolute shrinkage and selection operator (LASSO) and principal component analysis (PCA) to extract important factors of the large-scale exogenous variables. Besides the traditional ordinary least squares (OLS) estimation, the nonlinear support vector regression (SVR) approach is employed to integrate with the LASSO-PCA method. The empirical results show that both the OLS and SVR combined with LASSO-PCA can improve the forecasting accuracy, especially SVR-LASSO-PCA owns the best forecasting performance. The analysis of the selected variables finds international futures volatility is chosen more frequently. These results are further validated through a series of robust experiments. Finally, the time difference between China and the United States is also considered in order to obtain more reasonable out-of-sample forecasting.

Models developed by banks to forecast losses in their credit card portfolios have generally performed poorly during the COVID-19 pandemic, particularly in 2020, when large forecast errors were observed at many banks. In this study, we attempt to understand the source of this error and explore ways to improve model fit. We use account-level monthly performance data from the largest credit card banks in the U.S. between 2008 and 2018 to build models that mimic the typical model design employed by large banks to forecast credit card losses. We then fit these on data from 2019 to 2021. We find that COVID-period model errors can be reduced significantly through two simple modifications: (1) including measures of the macroeconomic environment beyond indicators of the labor market, which served as the primary macro drivers used in many pre-pandemic models and (2) adjusting macro drivers to capture persistent/sustained changes, as opposed to temporary volatility in these variables. These model improvements, we find, can be achieved without a significant reduction in model performance for the pre-COVID period, including the Great Recession. Moreover, in broadening the set of macro influences and capturing sustained changes, we believe models can be made more robust to future downturns, which may bear little resemblance to past recessions.