Journal of Forecasting最新文献

Electronic and digital trading models have made stock trading more accessible and convenient, leading to exponential growth in trading data. With a wealth of trading data available, researchers have found opportunities to extract valuable insights by uncovering patterns in stock price movements and market dynamics. Deep learning models are increasingly being employed for stock price prediction. While neural networks offer superior computational capabilities compared with traditional statistical methods, their results often lack interpretability, limiting their utility in explaining stock price volatility and investment behavior. To address this challenge, we propose a causality-based method that incorporates a multivariate approach, integrating news event attention sequences and sentiment index sequences. The goal is to capture the intricate and multifaceted relationships among news events, media sentiment, and stock prices. We illustrate the application of this proposed approach using a Global Database of Events, Language, and Tone global event database, demonstrating its benefits through the analysis of attention sequences and media sentiment index sequences for news events across various categories. This research not only identifies promising directions for further exploration but also offers insights with implications for informed investment decisions.

In recent years, the semiparametric methods for the joint estimation and prediction of value at risk (VaR) and expected shortfall (ES) have triggered great interests and attention. Compared to existing literature which usually incorporates realized volatility (RV) into the dynamic semiparametric risk models, this paper considers three more robust proxies (medRV, BPV, and RK) of intraday volatility in the models to verify whether high-frequency information can improve the joint prediction ability of risk measures. To strengthen the persuasion of conclusions, four international stock indices (S&P500, Nikkei225, GDAXI, and DJIA) are applied to these models to estimate and forecast VaR and ES at different probability levels (1%, 2.5%, 5%, and 10%). Then, the predicted VaR and ES are backtested by several methods individually, and the popular score function FZ0 and MCS test are used to compare the effects of jointly predicting risk measures. Our results confirm that these semiparametric models containing intraday information outperform the benchmark models for four stocks and various probability levels, and medRV is the best volatility measure in improving the effects of models.

This study presents a novel and fully probabilistic approach for combining model-based forecasts with surveys or other judgmental forecasts. In our method, survey forecasts are integrated as penalty terms for the model parameters, facilitating a probabilistic exploration of additional insights obtained from surveys. We apply this approach to estimate a growth-at-risk model for real GDP growth in the United States. The results reveal that this additional shrinkage significantly improves prediction performance, with the information from surveys even exerting an influence on the lower tails of the distribution.

New fashion product sales forecasting is a challenging problem that involves many business dynamics and cannot be solved by classical forecasting approaches. In this paper, we investigate the effectiveness of systematically probing exogenous knowledge in the form of Google Trends time series and combining it with multi-modal information related to a brand-new fashion item, in order to effectively forecast its sales despite the lack of past data. In particular, we propose a neural network-based approach, where an encoder learns a representation of the exogenous time series, while the decoder forecasts the sales based on the Google Trends encoding and the available visual and metadata information. Our model works in a non-autoregressive manner, avoiding the compounding effect of large first-step errors. As a second contribution, we present VISUELLE, a publicly available dataset for the task of new fashion product sales forecasting, containing multimodal information for 5,577 real, new products sold between 2016 and 2019 from Nunalie, an Italian fast-fashion company. The dataset is equipped with images of products, metadata, related sales, and associated Google Trends. We use VISUELLE to compare our approach against state-of-the-art alternatives and several baselines, showing that our neural network-based approach is the most accurate in terms of both percentage and absolute error. It is worth noting that the addition of exogenous knowledge boosts the forecasting accuracy by 1.5% in terms of Weighted Absolute Percentage Error (WAPE), revealing the importance of exploiting informative external information. The code and dataset are both available online (at https://github.com/HumaticsLAB/GTM-Transformer).

This paper presents an efficient heuristic to generate multi-stage scenario trees for portfolio selection problems. In the case of two or more risky assets, investors need to account for the complex multivariate dependence among different assets. The dependence patterns have shown not only asymmetric and fat tails but also time-varying, and the upper and lower tails have different effect on portfolio management. In this paper, we design a new scenario generation method by combining the GARCH-type model and vine copula model to properly reflect these complex dependence patterns in multiple assets in a flexible way. A multi-stage scenario tree is generated sequentially from this model by simultaneously utilizing the simulation and clustering methods. The scenarios' nodal probabilities are determined by solving an improved moment matching model, whose objective is to maintain the central moments and lower tails of the original distribution. The resulting scenario trees are then tested on a multi-stage portfolio selection model. The experimental results prove the efficiency and advantages of our proposed scenario generation method over other existing models or methods and the positive influence of moment matching on our method.

This systematic literature review examines cryptocurrency forecasting trends, influential sources, and research themes. Following PRISMA guidelines, 168 articles from Q1 or A-tier journals in the Scopus database were analyzed using bibliometric techniques. The findings reveal a significant increase in cryptocurrency forecasting research output since 2017, particularly in 2021. “Finance Research Letters” emerges as the most productive journal, whereas “Economics Letters” receives the highest number of citations. Elie Bouri is identified as the most prolific author, and China is the top contributor country. Key research themes include bitcoin, cryptocurrency, volatility, forecasting, machine learning, investments, and blockchain. Future research directions involve utilizing internet search-based measures, time-varying mixture models, economic policy uncertainty, expert predictions, machine learning algorithms, and analyzing cryptocurrency risk. This review contributes unique insights into the field's growth, influential sources, and collaborative structures and offers a foundation for advancing methodology and enhancing cryptocurrency forecasting models.

In this paper, we study the predictive power of electricity consumption data for regional economic activity. Using unique high-frequency electricity consumption data from industrial firms for the second-largest German state, the Free State of Bavaria, we conduct a pseudo out-of-sample forecasting experiment for the monthly growth rate of Bavarian industrial production. We find that electricity consumption is the best performing indicator in the nowcasting setup and has higher accuracy than other conventional indicators in a monthly forecasting experiment. Exploiting the high-frequency nature of the data, we find that the weekly electricity consumption indicator also provides good predictions about industrial activity in the current month with only 2 weeks of information. Overall, our results indicate that regional electricity consumption is a promising avenue for measuring and forecasting regional economic activity.

In this paper, we propose a correlation-based test for the evaluation of two competing forecasts. Under the null hypothesis of equal correlations with the target variable, we derive the asymptotic distribution of our test using the Delta method. This null hypothesis is not necessarily equivalent to the null of equal Mean Squared Prediction Errors (MSPE). Specifically, it might be the case that the forecast displaying the lowest MSPE also exhibits the lowest correlation with the target variable: this is known as “The MSPE paradox.” In this sense, our approach should be seen as complementary to traditional tests of equality in MSPE. Monte Carlo simulations indicate that our test has good size and power. Finally, we illustrate the use of our test in an empirical exercise in which we compare two different inflation forecasts for a sample of OECD economies. We find more rejections of the null of equal correlations than rejections of the null of equality in MSPE.

Electricity price forecasting (EPF) is an emergent research domain that focuses on forecasting the future electricity market price both deterministically and probabilistically. EPF has attracted enormous interest from both practitioners and scholars since the deregulation of the power market and wide applications of renewable energy sources, such as wind and solar energy. However, forecasting the electricity price accurately and efficiently is an extremely challenging task because of its high volatility, randomness, and fluctuation. Although quantile regression averaging (QRA) has been demonstrated to be efficacious in probabilistic EPF since the global energy forecasting competition in 2014 (GEFCom2014), it is sensitive to nuisance variables especially when the number of variables is large. The forecasting accuracy will be negatively affected by these nuisance variables. To address these challenges, this study investigates a nonconvex regularized QRA in probabilistic forecasting. Two types of nonconvex regularized QRA select the important inputs obtained from point forecasting to obtain more accurate forecasting outcomes. To demonstrate the effectiveness of the proposed EPF model, two real datasets from the European power market are considered.

Peak power load forecasting is a key part of the commercial operation of the energy industry. Although various load forecasting methods and technologies have been put forward and tested in practice, the growing subject of tolerance for abnormal accidents is to develop robust peak load forecasting models. In this paper, we propose a robust smooth non-convex support vector regression method, which improves the robustness of the model by adjusting adaptive control loss values and adaptive robust parameters and by reducing the negative impact of outliers or noise on the decision function. A concave-convex programming algorithm is used to solve the non-convexity of the optimization problem. Good results are obtained in both linear regression model and nonlinear regression model and two real data sets. An experiment is carried out in a power company in Jiangxi Province, China, to evaluate the performance of the robust smooth non-convex support vector regression model. The results show that the proposed method is superior to support vector regression and generalized quadratic non-convex support vector regression in robustness and generalization ability.