Journal of Forecasting最新文献

Stock price forecasting has always been a classic and challenging task, attracting widespread attention from stakeholders such as market regulators, financial practitioners, and individual investors. Developing new models to improve the accuracy of stock price forecasting is also a persistent goal pursued by researchers. In recent years, quantum computing has developed rapidly. The emergence of quantum machine learning (QML) and quantum neural network (QNN) models has made it possible to develop new stock price forecasting models that leverage the advantages of quantum algorithms. To improve predictive accuracy, this study proposes a novel decomposition-ensemble approach based on multivariate empirical mode decomposition and QNN. In the prediction, multi-source big data from the stock market, search engines, and social media are employed to represent investor anticipation, attention, and sentiments, respectively. Using the daily average stock price in the Shenzhen Stock Exchange, an empirical analysis is conducted to illustrate the proposed approach. The results suggest that the proposed approach outperforms benchmark models, indicating that it is a promising method for forecasting stock price series with high volatility and nonlinearity.

Credit rating serves as a crucial instrument for lenders to evaluate borrowers' creditworthiness and mitigate the risk of nonperforming loans. However, credit rating tasks often face significant challenges due to multiclass distributions and severe class imbalances. Given the advantages of ensemble learning methods in addressing these challenges, this study presents a novel multiclass imbalance classification framework that integrates the Error Correcting Output Codes (ECOC) decomposition approach with diverse dichotomizer imbalance algorithms to enhance credit ratings. Nevertheless, selecting and quantifying the uncertainty of dichotomizer sets poses challenges. To this end, we introduce a dynamic ensemble selection strategy and evidence theory within the ECOC setup. By tailoring specific dichotomizers to individual samples and consolidating uncertain binary outcomes using belief functions, a resilient ensemble classifier is developed. Extensive experiments on nine KEEL benchmark datasets and two real credit datasets demonstrate its effectiveness in handling severe imbalance in credit rating tasks.

A positive relationship between Earning Call Sentiment and Stock Market Reaction has already been identified. Still, this utilization for prediction has yet to gain much attention. This study explores the predictive potential of earnings calls by employing the BERT model to extract key topics and their sentiments. Various machine learning techniques are then employed to leverage these insights for predicting stock market reactions and associated risks, evaluating the extent to which earnings call topics and sentiments can enhance prediction accuracy. Analyzing all quarterly earnings calls from S&P 500 companies in 2022, the results indicate that the decomposition into key topics with their respective sentiment outperforms the usage of overall sentiment across multiple scenarios and models. The random forest model is found to make the best utilization of the decomposition.

Repurchase prediction is a vital aspect of marketing strategy and a complex decision-making task, especially in the airline industry, where data are uncertain, incomplete, and ambiguous. To address this, this study proposes a novel multi-classifier evidence ensemble algorithm that integrates evidence theory with machine learning to predict travelers' repurchase behavior. The model was trained using 29 behavioral features derived from a low-cost Chinese airline. Empirical results show that the proposed algorithm outperforms traditional models in terms of the accuracy, the precision, the recall, the F1-score, and the AUC. Specifically, it achieved over 80% accuracy and precision in binary classification tasks. Ablation experiments using four classifier combinations at different sampling rates (30%, 50%, and 70%) further validated the robustness and effectiveness of the framework. The results suggest that the proposed ensemble framework outperforms traditional prediction models in terms of overall predictive performance for analyzing airline passenger behavior in real-world settings.

This paper introduced HyperVIX, a novel hybrid framework that integrates ARIMA modeling, LSTM neural networks, and Gray Wolf Optimizer (GWO) to forecast the Chicago Board Options Exchange (CBOE) Volatility Index (VIX). Using a multilayered approach, HyperVIX first employs ARIMA to capture linear time series patterns, followed by LSTM networks that model the residuals to identify complex nonlinear relationships. The GWO algorithm optimizes the LSTM hyperparameters, enhancing the framework's ability to capture Volatility Index (VIX)'s intricate dynamics. Empirical analysis demonstrates that HyperVIX significantly outperforms both traditional and contemporary financial forecasting models in terms of accuracy and robustness. Compared to single models, HyperVIX achieves approximately 15%, 12%, and 10% improvements in root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) metrics respectively, with the R² value increasing by about 5%. Notably, the model exhibits exceptional performance during extreme market volatility periods, making it particularly valuable for risk management applications. This research contributes to the literature by providing an innovative and effective method for VIX forecasting while offering valuable insights for financial market volatility analysis and investment strategy optimization.