|
on Forecasting |
| By: | Tiantian Tu |
| Abstract: | Time series forecasting is crucial for decision-making across various domains, particularly in financial markets where stock prices exhibit complex and non-linear behaviors. Accurately predicting future price movements is challenging due to the difficulty of capturing both short-term fluctuations and long-term dependencies in the data. Convolutional Neural Networks (CNNs) are well-suited for modeling localized, short-term patterns but struggle with long-range dependencies due to their limited receptive field. In contrast, Transformers are highly effective at capturing global temporal relationships and modeling long-term trends. In this paper, we propose a hybrid architecture that combines CNNs and Transformers to effectively model both short- and long-term dependencies in financial time series data. We apply this approach to forecast stock price movements for S\&P 500 constituents and demonstrate that our model outperforms traditional statistical models and popular deep learning methods in intraday stock price forecasting, providing a robust framework for financial prediction. |
| Date: | 2025–04 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2504.19309 |
| By: | Marco Zanotti |
| Abstract: | In an era of increasing computational capabilities and growing environmental consciousness, organizations face a critical challenge in balancing the accuracy of their forecasting models with computational efficiency and sustainability. Global forecasting models, which leverage data across multiple time series to improve prediction accuracy, lowering the computational time, have gained significant attention over the years. However, the common practice of retraining these models with new observations raises important questions about the costs of producing forecasts. Using ten different machine learning and deep learning models, we analyzed various retraining scenarios, ranging from continuous updates to no retraining at all, across two large retail datasets. We showed that less frequent retraining strategies can maintain the forecast accuracy while reducing the computational costs, providing a more sustainable approach to large-scale forecasting. We also found that machine learning models are a marginally better choice to reduce the costs of forecasting when coupled with less frequent model retraining strategies as the frequency of the data increases. Our findings challenge the conventional belief that frequent retraining is essential for maintaining forecasting accuracy. Instead, periodic retraining offers a good balance between predictive performance and efficiency, both in the case of point and probabilistic forecasting. These insights provide actionable guidelines for organizations seeking to optimize forecasting pipelines while reducing costs and energy consumption. |
| Keywords: | Time series, Demand forecasting, Forecasting competitions, Cross-learning, Global models, Machine learning, Deep learning, Green AI, Conformal predictions. |
| JEL: | C53 C52 C55 |
| Date: | 2025–04 |
| URL: | https://d.repec.org/n?u=RePEc:mib:wpaper:551 |
| By: | Kyungsu Kim |
| Abstract: | This thesis studies the effectiveness of Long Short Term Memory model in forecasting future Job Openings and Labor Turnover Survey data in the United States. Drawing on multiple economic indicators from various sources, the data are fed directly into LSTM model to predict JOLT job openings in subsequent periods. The performance of the LSTM model is compared with conventional autoregressive approaches, including ARIMA, SARIMA, and Holt-Winters. Findings suggest that the LSTM model outperforms these traditional models in predicting JOLT job openings, as it not only captures the dependent variables trends but also harmonized with key economic factors. These results highlight the potential of deep learning techniques in capturing complex temporal dependencies in economic data, offering valuable insights for policymakers and stakeholders in developing data-driven labor market strategies |
| Date: | 2025–03 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2503.19048 |
| By: | Giovanni Ballarin; Jacopo Capra; Petros Dellaportas |
| Abstract: | Stock return prediction is a problem that has received much attention in the finance literature. In recent years, sophisticated machine learning methods have been shown to perform significantly better than ''classical'' prediction techniques. One downside of these approaches is that they are often very expensive to implement, for both training and inference, because of their high complexity. We propose a return prediction framework for intraday returns at multiple horizons based on Echo State Network (ESN) models, wherein a large portion of parameters are drawn at random and never trained. We show that this approach enjoys the benefits of recurrent neural network expressivity, inherently efficient implementation, and strong forecasting performance. |
| Date: | 2025–04 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2504.19623 |
| By: | Amelie BARBIER-GAUCHARD; Emmanouil SOFIANOS |
| Abstract: | The situation of public finance in the eurozone remains a burning issue for certain Euro area countries. The financial markets, the main lenders of the Member States, are more attentive than ever to any factor which could affect the trajectory of public debt in the long term. The risk of bankruptcy of a Member State and a domino effect for the entire monetary union represents the ultimate risk weighing on the Eurozone. This paper aims to forecast the public debt, with a universal model, on a national level within the Euro area. We use a dataset that includes 566 independent variables (economic, financial, institutional, political and social) for 17 Euro area countries, spanning the period from 2000 to 2022 in annual frequency. The dataset is fed to four machine learning (ML) algorithms: Decision Trees, Random Forests, XGBoost and Support Vector Machines (SVM). We also employ the Elastic-Net Regression algorithm from the area of Econometrics. The best model is an XGBoost with an out-of-sample MAPE of 8.41%. Moreover, it outperforms the projections of European Commission and IMF. According to the VIM from XGBoost, the most influential variables are the past values of public debt, the male population in the ages 50-54, the regulatory quality, the control of corruption, the female employment to population ratio for the ages over 15 and the 10 year bond spread. |
| Keywords: | Public Debt; Euro Area; Machine Learning; Forecasting. |
| JEL: | C53 H63 H68 |
| Date: | 2024 |
| URL: | https://d.repec.org/n?u=RePEc:ulp:sbbeta:2024-47 |
| By: | Lucile Marescot (UMR CBGP - Centre de Biologie pour la Gestion des Populations - Cirad - Centre de Coopération Internationale en Recherche Agronomique pour le Développement - IRD [Occitanie] - Institut de Recherche pour le Développement - INRAE - Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement - Institut Agro Montpellier - Institut Agro - Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement - UM - Université de Montpellier, Cirad-BIOS - Département Systèmes Biologiques - Cirad - Centre de Coopération Internationale en Recherche Agronomique pour le Développement); Elodie Fernandez (UMR CBGP - Centre de Biologie pour la Gestion des Populations - Cirad - Centre de Coopération Internationale en Recherche Agronomique pour le Développement - IRD [Occitanie] - Institut de Recherche pour le Développement - INRAE - Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement - Institut Agro Montpellier - Institut Agro - Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement - UM - Université de Montpellier); Hichem Dridi (FAO - Food and Agriculture Organization of the United Nations, Regional Office for the Near East and North Africa - FAO - Food and Agriculture Organization of the United Nations [Rome, Italie], CLCPRO - Commission de Lutte Contre le Criquet Pèlerin en Région Occidentale); Ahmed Salem Benahi (CNLA - Centre National de Lutte Antiacridienne); Mohamed Lemine Hamouny (FAO - Food and Agriculture Organization of the United Nations, Regional Office for the Near East and North Africa - FAO - Food and Agriculture Organization of the United Nations [Rome, Italie], CLCPRO - Commission de Lutte Contre le Criquet Pèlerin en Région Occidentale); Koutaro Ould Maeno (JIRCAS - Japan International Research Center for Agricultural Sciences); Maria-José Escorihuela (isardSAT); Giovanni Paolini (isardSAT); Cyril Piou (UMR CBGP - Centre de Biologie pour la Gestion des Populations - Cirad - Centre de Coopération Internationale en Recherche Agronomique pour le Développement - IRD [Occitanie] - Institut de Recherche pour le Développement - INRAE - Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement - Institut Agro Montpellier - Institut Agro - Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement - UM - Université de Montpellier, Cirad-BIOS - Département Systèmes Biologiques - Cirad - Centre de Coopération Internationale en Recherche Agronomique pour le Développement) |
| Abstract: | Highlights: • We built an operational forecasting system for Desert locust preventive management. • We used random forest model for real-time forecasting of locust presence and update every decade. • Pest distribution was explained by sand cover, ecoregions, temperature, precipitations and vegetation cover. • Field evaluation revealed a strong correlation between predicted probabilities and observed locust densities. Abstract: Desert locust (Schistocerca gregaria) is a major agricultural pest that poses significant socioeconomic challenges to food security. This study aims to enhance preventive management of desert locusts in Western and Northern Africa by improving an operational model developed by Piou et al. (2019). The model employs satellite remote sensing data and machine learning to forecast locust occurrence at a 1 km 2 resolution every ten days. Objectives include identifying environmental risk factors, training random forest models with high-predictive power and providing updated forecasts via a web interface. It is the first implementation of a statistical forecasting model for this species within an automated system, delivering updated locust presence probabilities every ten days. Validated through field surveys with a positive error rate of 23%, the forecasting tool shows a strong correlation between predicted probabilities and observed locust densities. This operational tool can guide survey teams, optimize resource allocation, and mitigate environmental impacts efficiently. We believe continuous evaluation and integration of the forecast system will enhance its effectiveness in preventing locust outbreaks, thereby safeguarding food security in the region. |
| Keywords: | Automatic forecast system, Locust outbreak, Machine learning, Remote sensing, Schistocerca gregaria |
| Date: | 2025–01 |
| URL: | https://d.repec.org/n?u=RePEc:hal:journl:hal-04995261 |
| By: | Ambedkar Dukkipati; Kawin Mayilvaghanan; Naveen Kumar Pallekonda; Sai Prakash Hadnoor; Ranga Shaarad Ayyagari |
| Abstract: | Fluctuations in stock prices are influenced by a complex interplay of factors that go beyond mere historical data. These factors, themselves influenced by external forces, encompass inter-stock dynamics, broader economic factors, various government policy decisions, outbreaks of wars, etc. Furthermore, all of these factors are dynamic and exhibit changes over time. In this paper, for the first time, we tackle the forecasting problem under external influence by proposing learning mechanisms that not only learn from historical trends but also incorporate external knowledge from temporal knowledge graphs. Since there are no such datasets or temporal knowledge graphs available, we study this problem with stock market data, and we construct comprehensive temporal knowledge graph datasets. In our proposed approach, we model relations on external temporal knowledge graphs as events of a Hawkes process on graphs. With extensive experiments, we show that learned dynamic representations effectively rank stocks based on returns across multiple holding periods, outperforming related baselines on relevant metrics. |
| Date: | 2025–04 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2504.20058 |
| By: | Masoud Ataei |
| Abstract: | This paper investigates the structural dynamics of stock market volatility through the Financial Chaos Index, a tensor- and eigenvalue-based measure designed to capture realized volatility via mutual fluctuations among asset prices. Motivated by empirical evidence of regime-dependent volatility behavior and perceptual time dilation during financial crises, we develop a regime-switching framework based on the Modified Lognormal Power-Law distribution. Analysis of the FCIX from January 1990 to December 2023 identifies three distinct market regimes, low-chaos, intermediate-chaos, and high-chaos, each characterized by differing levels of systemic stress, statistical dispersion and persistence characteristics. Building upon the segmented regime structure, we further examine the informational forces that shape forward-looking market expectations. Using sentiment-based predictors derived from the Equity Market Volatility tracker, we employ an elastic net regression model to forecast implied volatility, as proxied by the VIX index. Our findings indicate that shifts in macroeconomic, financial, policy, and geopolitical uncertainty exhibit strong predictive power for volatility dynamics across regimes. Together, these results offer a unified empirical perspective on how systemic uncertainty governs both the realized evolution of financial markets and the anticipatory behavior embedded in implied volatility measures. |
| Date: | 2025–04 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2504.18958 |
| By: | Davide Furceri; Domenico Giannone; Mr. Faizaan Kisat; Mr. Waikei R Lam; Hongchi Li |
| Abstract: | This paper proposes a novel framework for analyzing the risks surrounding the public debt outlook, the “Debt-at-Risk.” It employs a quantile panel regression framework to assess how current macrofinancial and political conditions impact the entire spectrum of possible future debt outcomes. Many of these factors—including financial conditions and economic variables such as initial debt and GDP growth—predict both the expected level and the uncertainty of future debt, implying pronounced variations in risks, especially in the upper tail of the distribution. By combining the roles of these factors, we find that in a severely adverse scenario—the 95th percentile of the future debt distribution, or debt-at-risk—global public debt could be approximately 20 percentage points higher than currently projected. The magnitudes and sources of debt risks vary over time and across countries, with high initial debt amplifying the effects of economic and financial conditions on debt-at-risk. Furthermore, empirical estimates indicate that debt-at-risk is a key variable for predicting fiscal crises. |
| Keywords: | Debt; Risks; Forecasts. |
| Date: | 2025–05–05 |
| URL: | https://d.repec.org/n?u=RePEc:imf:imfwpa:2025/086 |
| By: | Lutfu S. Sua; Haibo Wang; Jun Huang |
| Abstract: | A novel spatiotemporal framework using diverse econometric approaches is proposed in this research to analyze relationships among eight economy-wide variables in varying market conditions. Employing Vector Autoregression (VAR) and Granger causality, we explore trade policy effects on emerging manufacturing hubs in China, India, Malaysia, Singapore, and Vietnam. A Bayesian Global Vector Autoregression (BGVAR) model also assesses interaction of cross unit and perform Unconditional and Conditional Forecasts. Utilizing time-series data from the Asian Development Bank, our study reveals multi-way cointegration and dynamic connectedness relationships among key economy-wide variables. This innovative framework enhances investment decisions and policymaking through a data-driven approach. |
| Date: | 2025–03 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2503.17790 |