Isabela Caroline de Sousa, T. Sigahi, Izabella Rampasso, G. H. S. M. Moraes, W. Leal Filho, João Henrique Paulino Pires Eustachio, R. Anholon
The COVID-19 pandemic has affected all Sustainable Development Goals (SDGs), leading to setbacks in various Latin American countries. In Brazil, progress in technological development and the adoption of sustainable practices by organizations has been significantly hindered. Yet, there remains a limited understanding of the long-term impacts on the country’s development, and a structured national plan for recovery and resuming progress toward the SDGs is lacking. This paper aims to investigate the repercussions of COVID-19 on SDGs 9 (industry, innovation, and infrastructure) and 12 (sustainable consumption and production) in the context of a latecomer country such as Brazil. This study adopted the Delphi-based scenario and Fuzzy Delphi approach and involved the participation of 15 sustainability experts with extensive experience in the Brazilian industrial sector. The findings elucidate the long-term impacts of the pandemic on these SDGs, focusing on Brazil’s socioeconomic landscape and developmental challenges. The pandemic worsened pre-existing issues, hindering infrastructure modernization, technological investment, and sustainable practices. Insufficient research funding, industry modernization, and small business integration further impede progress. Additionally, the paper identifies implications for research, companies, and public policies, aiming to provide actionable insights for fostering sustainable development in the post-pandemic era.
{"title":"A Delphi–Fuzzy Delphi Study on SDGs 9 and 12 after COVID-19: Case Study in Brazil","authors":"Isabela Caroline de Sousa, T. Sigahi, Izabella Rampasso, G. H. S. M. Moraes, W. Leal Filho, João Henrique Paulino Pires Eustachio, R. Anholon","doi":"10.3390/forecast6030030","DOIUrl":"https://doi.org/10.3390/forecast6030030","url":null,"abstract":"The COVID-19 pandemic has affected all Sustainable Development Goals (SDGs), leading to setbacks in various Latin American countries. In Brazil, progress in technological development and the adoption of sustainable practices by organizations has been significantly hindered. Yet, there remains a limited understanding of the long-term impacts on the country’s development, and a structured national plan for recovery and resuming progress toward the SDGs is lacking. This paper aims to investigate the repercussions of COVID-19 on SDGs 9 (industry, innovation, and infrastructure) and 12 (sustainable consumption and production) in the context of a latecomer country such as Brazil. This study adopted the Delphi-based scenario and Fuzzy Delphi approach and involved the participation of 15 sustainability experts with extensive experience in the Brazilian industrial sector. The findings elucidate the long-term impacts of the pandemic on these SDGs, focusing on Brazil’s socioeconomic landscape and developmental challenges. The pandemic worsened pre-existing issues, hindering infrastructure modernization, technological investment, and sustainable practices. Insufficient research funding, industry modernization, and small business integration further impede progress. Additionally, the paper identifies implications for research, companies, and public policies, aiming to provide actionable insights for fostering sustainable development in the post-pandemic era.","PeriodicalId":508737,"journal":{"name":"Forecasting","volume":" 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141828351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Previous research provides conflicting results regarding how R&D expenditures impact market value. Given that financial analysts are the primary intermediaries between companies and investors, our study focused on the impact of R&D-related uncertainty, growth, and information asymmetry associated on analysts’ earnings forecasts. Based on 19,834 firm-year observations in the European market between 2005 and 2020, our results show that R&D activities lead to higher absolute forecast error and negative forecast error, indicating higher forecast inaccuracy with an optimistic bias. Additionally, these investments contribute to higher forecast dispersion, indicating disagreement among financial analysts. The comparison between 17 industries revealed that these effects are more pronounced in R&D-intensive industries than in non-R&D industries, uncovering the varied relationship between R&D investments and analyst forecasts across sectors.
{"title":"R&D Expenditures and Analysts’ Earnings Forecasts","authors":"Taoufik Elkemali","doi":"10.3390/forecast6030029","DOIUrl":"https://doi.org/10.3390/forecast6030029","url":null,"abstract":"Previous research provides conflicting results regarding how R&D expenditures impact market value. Given that financial analysts are the primary intermediaries between companies and investors, our study focused on the impact of R&D-related uncertainty, growth, and information asymmetry associated on analysts’ earnings forecasts. Based on 19,834 firm-year observations in the European market between 2005 and 2020, our results show that R&D activities lead to higher absolute forecast error and negative forecast error, indicating higher forecast inaccuracy with an optimistic bias. Additionally, these investments contribute to higher forecast dispersion, indicating disagreement among financial analysts. The comparison between 17 industries revealed that these effects are more pronounced in R&D-intensive industries than in non-R&D industries, uncovering the varied relationship between R&D investments and analyst forecasts across sectors.","PeriodicalId":508737,"journal":{"name":"Forecasting","volume":"8 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141668266","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In a dynamic business environment, the accuracy of sales forecasts plays a pivotal role in strategic decision making and resource allocation. This article offers a systematic review of the existing literature on techniques and methodologies used in forecasting, especially in sales forecasting across various domains, aiming to provide a nuanced understanding of the field. Our study examines the literature from 2013 to 2023, identifying key techniques and their evolution over time. The methodology involves a detailed analysis of 516 articles, categorized into classical qualitative approaches, traditional statistical methods, machine learning models, deep learning techniques, and hybrid approaches. The results highlight a significant shift towards advanced methods, with machine learning and deep learning techniques experiencing an explosive increase in adoption. The popularity of these models has surged, as evidenced by a rise from 10 articles in 2013 to over 110 by 2023. This growth underscores their growing prominence and effectiveness in handling complex time series data. Additionally, we explore the challenges and limitations that influence forecasting accuracy, focusing on complex market structures and the benefits of extensive data availability.
{"title":"Systematic Mapping Study of Sales Forecasting: Methods, Trends, and Future Directions","authors":"Hamid Ahaggach, L. Abrouk, Eric Lebon","doi":"10.3390/forecast6030028","DOIUrl":"https://doi.org/10.3390/forecast6030028","url":null,"abstract":"In a dynamic business environment, the accuracy of sales forecasts plays a pivotal role in strategic decision making and resource allocation. This article offers a systematic review of the existing literature on techniques and methodologies used in forecasting, especially in sales forecasting across various domains, aiming to provide a nuanced understanding of the field. Our study examines the literature from 2013 to 2023, identifying key techniques and their evolution over time. The methodology involves a detailed analysis of 516 articles, categorized into classical qualitative approaches, traditional statistical methods, machine learning models, deep learning techniques, and hybrid approaches. The results highlight a significant shift towards advanced methods, with machine learning and deep learning techniques experiencing an explosive increase in adoption. The popularity of these models has surged, as evidenced by a rise from 10 articles in 2013 to over 110 by 2023. This growth underscores their growing prominence and effectiveness in handling complex time series data. Additionally, we explore the challenges and limitations that influence forecasting accuracy, focusing on complex market structures and the benefits of extensive data availability.","PeriodicalId":508737,"journal":{"name":"Forecasting","volume":" 15","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141676554","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Eli Hadad, Sohail Hodarkar, Beakal Lemeneh, Dennis Shasha
Forecasting returns in financial markets is notoriously challenging due to the resemblance of price changes to white noise. In this paper, we propose novel methods to address this challenge. Employing high-frequency Brazilian stock market data at one-minute granularity over a full year, we apply various statistical and machine learning algorithms, including ARIMA, Bidirectional Long Short-Term Memory (BiLSTM) with attention, Transformers, N-BEATS, N-HiTS, Convolutional Neural Networks (CNNs), and Temporal Convolutional Networks (TCNs) to predict changes in the price ratio of closely related stock pairs. Our findings indicate that a combination of reversion and machine learning-based forecasting methods yields the highest profit-per-trade. Additionally, by allowing the model to abstain from trading when the predicted magnitude of change is small, profits per trade can be further increased. Our proposed forecasting approach, utilizing a blend of methods, demonstrates superior accuracy compared to individual methods for high-frequency data.
{"title":"Machine Learning-Enhanced Pairs Trading","authors":"Eli Hadad, Sohail Hodarkar, Beakal Lemeneh, Dennis Shasha","doi":"10.3390/forecast6020024","DOIUrl":"https://doi.org/10.3390/forecast6020024","url":null,"abstract":"Forecasting returns in financial markets is notoriously challenging due to the resemblance of price changes to white noise. In this paper, we propose novel methods to address this challenge. Employing high-frequency Brazilian stock market data at one-minute granularity over a full year, we apply various statistical and machine learning algorithms, including ARIMA, Bidirectional Long Short-Term Memory (BiLSTM) with attention, Transformers, N-BEATS, N-HiTS, Convolutional Neural Networks (CNNs), and Temporal Convolutional Networks (TCNs) to predict changes in the price ratio of closely related stock pairs. Our findings indicate that a combination of reversion and machine learning-based forecasting methods yields the highest profit-per-trade. Additionally, by allowing the model to abstain from trading when the predicted magnitude of change is small, profits per trade can be further increased. Our proposed forecasting approach, utilizing a blend of methods, demonstrates superior accuracy compared to individual methods for high-frequency data.","PeriodicalId":508737,"journal":{"name":"Forecasting","volume":"93 23","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141359290","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this article, we document the use of hail cannons in Mexico to dispel or suppress heavy rain episodes, a common practice among farmers, without scientific evidence to support its effectiveness. This study uses two rain databases: one compiled from the Global Precipitation Measurement (GPM) mission and the other generated with the implementation of the Weather Research and Forecasting (WRF) model. The aim is to explore the association between heavy rain episodes and hail cannon locations. The analysis includes two geographic features: a pair of coordinates and a 3 km radius area of influence around each hail cannon. This dimension is based on the size and distribution of the heavy rainfall events. This study analyzes four years of half-hourly rain data using the Python ecosystem environment with machine learning libraries. The results show no relationship between the operation of hail cannons and the dissipation or attenuation of heavy rainfall events. However, this study highlights that the significant differences between the GPM and WRF databases in registering heavy rain events may be attributable to their own uncertainty. Despite the unavailability of ground-based observations, the inefficiency of hail cannons in affecting the occurrence of heavy rain events is evident. Overall, this study provides scientific evidence that hail cannons are inefficient in preventing the occurrence of heavy rain episodes.
{"title":"Heavy Rainfall Events in Selected Geographic Regions of Mexico, Associated with Hail Cannons","authors":"V. M. Rodríguez-Moreno, J. Estrada-Ávalos","doi":"10.3390/forecast6020023","DOIUrl":"https://doi.org/10.3390/forecast6020023","url":null,"abstract":"In this article, we document the use of hail cannons in Mexico to dispel or suppress heavy rain episodes, a common practice among farmers, without scientific evidence to support its effectiveness. This study uses two rain databases: one compiled from the Global Precipitation Measurement (GPM) mission and the other generated with the implementation of the Weather Research and Forecasting (WRF) model. The aim is to explore the association between heavy rain episodes and hail cannon locations. The analysis includes two geographic features: a pair of coordinates and a 3 km radius area of influence around each hail cannon. This dimension is based on the size and distribution of the heavy rainfall events. This study analyzes four years of half-hourly rain data using the Python ecosystem environment with machine learning libraries. The results show no relationship between the operation of hail cannons and the dissipation or attenuation of heavy rainfall events. However, this study highlights that the significant differences between the GPM and WRF databases in registering heavy rain events may be attributable to their own uncertainty. Despite the unavailability of ground-based observations, the inefficiency of hail cannons in affecting the occurrence of heavy rain events is evident. Overall, this study provides scientific evidence that hail cannons are inefficient in preventing the occurrence of heavy rain episodes.","PeriodicalId":508737,"journal":{"name":"Forecasting","volume":"7 48","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141266044","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abubaker Younis, Fatima Belabbes, P. Cotfas, D. Cotfas
This study introduces a novel adjustment to the firefly algorithm (FA) through the integration of rare instances of cannibalism among fireflies, culminating in the development of the honeybee mating-based firefly algorithm (HBMFA). The IEEE Congress on Evolutionary Computation (CEC) 2005 benchmark functions served as a rigorous testing ground to evaluate the efficacy of the new algorithm in diverse optimization scenarios. Moreover, thorough statistical analyses, including two-sample t-tests and fitness function evaluation analysis, the algorithm’s optimization capabilities were robustly validated. Additionally, the coefficient of determination, used as an objective function, was utilized with real-world wind speed data from the SR-25 station in Brazil to assess the algorithm’s applicability in modeling wind speed parameters. Notably, HBMFA achieved superior solution accuracy, with enhancements averaging 0.025% compared to conventional FA, despite a moderate increase in execution time of approximately 18.74%. Furthermore, this dominance persisted when the algorithm’s performance was compared with other common optimization algorithms. However, some limitations exist, including the longer execution time of HBMFA, raising concerns about its practical applicability in scenarios where computational efficiency is critical. Additionally, while the new algorithm demonstrates improvements in fitness values, establishing the statistical significance of these differences compared to FA is not consistently achieved, which warrants further investigation. Nevertheless, the added value of this work lies in advancing the state-of-the-art in optimization algorithms, particularly in enhancing solution accuracy for critical engineering applications.
本研究通过整合萤火虫之间罕见的食人现象，对萤火虫算法（FA）进行了新的调整，最终开发出基于蜜蜂交配的萤火虫算法（HBMFA）。IEEE 2005 年进化计算大会（CEC）的基准函数是评估新算法在各种优化方案中有效性的严格试验场。此外，通过全面的统计分析，包括双样本 t 检验和适应度函数评估分析，该算法的优化能力得到了有力的验证。此外，还利用巴西 SR-25 站的实际风速数据来评估该算法在风速参数建模中的适用性。值得注意的是，与传统 FA 相比，HBMFA 实现了更高的求解精度，平均提高了 0.025%，尽管执行时间适度增加了约 18.74%。此外，当该算法的性能与其他常见优化算法进行比较时，这种优势依然存在。不过，HBMFA 也存在一些局限性，包括执行时间较长，这让人担心它在对计算效率要求较高的场景中的实际应用性。此外，虽然新算法在适应度值上有所改进，但与 FA 相比，这些差异在统计意义上的确定并不一致，这值得进一步研究。不过，这项工作的附加值在于推进了优化算法的最新发展，特别是提高了关键工程应用的求解精度。
{"title":"Utilizing the Honeybees Mating-Inspired Firefly Algorithm to Extract Parameters of the Wind Speed Weibull Model","authors":"Abubaker Younis, Fatima Belabbes, P. Cotfas, D. Cotfas","doi":"10.3390/forecast6020020","DOIUrl":"https://doi.org/10.3390/forecast6020020","url":null,"abstract":"This study introduces a novel adjustment to the firefly algorithm (FA) through the integration of rare instances of cannibalism among fireflies, culminating in the development of the honeybee mating-based firefly algorithm (HBMFA). The IEEE Congress on Evolutionary Computation (CEC) 2005 benchmark functions served as a rigorous testing ground to evaluate the efficacy of the new algorithm in diverse optimization scenarios. Moreover, thorough statistical analyses, including two-sample t-tests and fitness function evaluation analysis, the algorithm’s optimization capabilities were robustly validated. Additionally, the coefficient of determination, used as an objective function, was utilized with real-world wind speed data from the SR-25 station in Brazil to assess the algorithm’s applicability in modeling wind speed parameters. Notably, HBMFA achieved superior solution accuracy, with enhancements averaging 0.025% compared to conventional FA, despite a moderate increase in execution time of approximately 18.74%. Furthermore, this dominance persisted when the algorithm’s performance was compared with other common optimization algorithms. However, some limitations exist, including the longer execution time of HBMFA, raising concerns about its practical applicability in scenarios where computational efficiency is critical. Additionally, while the new algorithm demonstrates improvements in fitness values, establishing the statistical significance of these differences compared to FA is not consistently achieved, which warrants further investigation. Nevertheless, the added value of this work lies in advancing the state-of-the-art in optimization algorithms, particularly in enhancing solution accuracy for critical engineering applications.","PeriodicalId":508737,"journal":{"name":"Forecasting","volume":"56 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141112662","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The modeling and simulation of societies requires identifying the spatio-temporal patterns of people’s activities. In urban areas, it is key to effective urban planning; it can be used in real estate projects to predict their future impacts on behavior in surrounding accessible areas. The work presented here aims at developing a method for making it possible to model the potential visits of the various equipment and public spaces of a district under construction by mobilizing data from census at the regional level and the layout of shops and activities as defined by the real estate project. This agent-based model takes into account the flow of external visitors, estimated realistically based on the pre-occupancy movements in the surrounding cities. To perform this evaluation, we implemented a multi-agent-based simulation model (MATSim) at the regional scale and at the scale of the future district. In its design, the district is physically open to the outside and will offer services that will be of interest to other residents or users of the surrounding area. To know the effect of this opening on a potential transit of visitors in the district, as well as the places of interest for the inhabitants, it is necessary to predict the flows of micro-trips within the district once it is built. We propose an attraction model to estimate the daily activities and trips of the future residents based on the attractiveness of the facilities and the urbanistic potential of the blocks. This transportation model is articulated in conjunction with the regional model in order to establish the flow of outgoing and incoming visitors. The impacts of the future district on the mobility of its surrounding area is deduced by implementing a simulation in the projection situation.
{"title":"Forecasting Daily Activity Plans of a Synthetic Population in an Upcoming District","authors":"R. Belaroussi, Younes Delhoum","doi":"10.3390/forecast6020021","DOIUrl":"https://doi.org/10.3390/forecast6020021","url":null,"abstract":"The modeling and simulation of societies requires identifying the spatio-temporal patterns of people’s activities. In urban areas, it is key to effective urban planning; it can be used in real estate projects to predict their future impacts on behavior in surrounding accessible areas. The work presented here aims at developing a method for making it possible to model the potential visits of the various equipment and public spaces of a district under construction by mobilizing data from census at the regional level and the layout of shops and activities as defined by the real estate project. This agent-based model takes into account the flow of external visitors, estimated realistically based on the pre-occupancy movements in the surrounding cities. To perform this evaluation, we implemented a multi-agent-based simulation model (MATSim) at the regional scale and at the scale of the future district. In its design, the district is physically open to the outside and will offer services that will be of interest to other residents or users of the surrounding area. To know the effect of this opening on a potential transit of visitors in the district, as well as the places of interest for the inhabitants, it is necessary to predict the flows of micro-trips within the district once it is built. We propose an attraction model to estimate the daily activities and trips of the future residents based on the attractiveness of the facilities and the urbanistic potential of the blocks. This transportation model is articulated in conjunction with the regional model in order to establish the flow of outgoing and incoming visitors. The impacts of the future district on the mobility of its surrounding area is deduced by implementing a simulation in the projection situation.","PeriodicalId":508737,"journal":{"name":"Forecasting","volume":"3 9","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141108506","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. N. Grekov, E. Vyshkvarkova, Aleksandr S. Mavrin
Evaluation of water quality and accurate prediction of water pollution indicators are key components in water resource management and water pollution control. The use of biological early warning systems (BEWS), in which living organisms are used as biosensors, allows for a comprehensive assessment of the aquatic environment state and a timely response in the event of an emergency. In this paper, we examine three machine learning algorithms (Theta, Croston and Prophet) to forecast bivalves’ activity data obtained from the BEWS developed by the authors. An algorithm for anomalies detection in bivalves’ activity data was developed. Our results showed that for one of the anomalies, Prophet was the best method, and for the other two, the anomaly detection time did not differ between the methods. A comparison of methods in terms of computational speed showed the advantage of the Croston method. This anomaly detection algorithm can be effectively incorporated into the software of biological early warning systems, facilitating rapid responses to changes in the aquatic environment.
{"title":"Forecasting and Anomaly Detection in BEWS: Comparative Study of Theta, Croston, and Prophet Algorithms","authors":"A. N. Grekov, E. Vyshkvarkova, Aleksandr S. Mavrin","doi":"10.3390/forecast6020019","DOIUrl":"https://doi.org/10.3390/forecast6020019","url":null,"abstract":"Evaluation of water quality and accurate prediction of water pollution indicators are key components in water resource management and water pollution control. The use of biological early warning systems (BEWS), in which living organisms are used as biosensors, allows for a comprehensive assessment of the aquatic environment state and a timely response in the event of an emergency. In this paper, we examine three machine learning algorithms (Theta, Croston and Prophet) to forecast bivalves’ activity data obtained from the BEWS developed by the authors. An algorithm for anomalies detection in bivalves’ activity data was developed. Our results showed that for one of the anomalies, Prophet was the best method, and for the other two, the anomaly detection time did not differ between the methods. A comparison of methods in terms of computational speed showed the advantage of the Croston method. This anomaly detection algorithm can be effectively incorporated into the software of biological early warning systems, facilitating rapid responses to changes in the aquatic environment.","PeriodicalId":508737,"journal":{"name":"Forecasting","volume":"30 25","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141118135","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Convective storms represent a dangerous atmospheric phenomenon, particularly for the heavy and concentrated precipitation they can trigger. Given their high velocity and variability, their prediction is challenging, though it is crucial to issue reliable alarms. The paper presents a neural network approach to forecast the convective cell trajectory and intensity, using, as an example, a region in northern Italy that is frequently hit by convective storms in spring and summer. The predictor input is constituted by radar-derived information about the center of gravity of the cell, its reflectivity (a proxy for the intensity of the precipitation), and the area affected by the storm. The essential characteristic of the proposed approach is that the neural network directly forecasts the evolution of the convective cell position and of the other features for the following hour at a 5-min temporal resolution without a relevant loss of accuracy in comparison to predictors trained for each specific variable at a particular time step. Besides its accuracy (R2 of the position is about 0.80 one hour in advance), this machine learning approach has clear advantages over the classical numerical weather predictors since it runs at orders of magnitude more rapidly, thus allowing for the implementation of a real-time early-warning system.
{"title":"Forecasting Convective Storms Trajectory and Intensity by Neural Networks","authors":"Niccolò Borghi, Giorgio Guariso, M. Sangiorgio","doi":"10.3390/forecast6020018","DOIUrl":"https://doi.org/10.3390/forecast6020018","url":null,"abstract":"Convective storms represent a dangerous atmospheric phenomenon, particularly for the heavy and concentrated precipitation they can trigger. Given their high velocity and variability, their prediction is challenging, though it is crucial to issue reliable alarms. The paper presents a neural network approach to forecast the convective cell trajectory and intensity, using, as an example, a region in northern Italy that is frequently hit by convective storms in spring and summer. The predictor input is constituted by radar-derived information about the center of gravity of the cell, its reflectivity (a proxy for the intensity of the precipitation), and the area affected by the storm. The essential characteristic of the proposed approach is that the neural network directly forecasts the evolution of the convective cell position and of the other features for the following hour at a 5-min temporal resolution without a relevant loss of accuracy in comparison to predictors trained for each specific variable at a particular time step. Besides its accuracy (R2 of the position is about 0.80 one hour in advance), this machine learning approach has clear advantages over the classical numerical weather predictors since it runs at orders of magnitude more rapidly, thus allowing for the implementation of a real-time early-warning system.","PeriodicalId":508737,"journal":{"name":"Forecasting","volume":"117 23","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141124382","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Since cryptocurrencies are among the most extensively traded financial instruments globally, predicting their price has become a crucial topic for investors. Our dataset, which includes fluctuations in Bitcoin’s hourly prices from 15 May 2018 to 19 January 2024, was gathered from Crypto Data Download. It is made up of over 50,000 hourly data points that provide a detailed view of the price behavior of Bitcoin over a five-year period. In this study, we used potent algorithms, including gradient descent, attention mechanisms, long short-term memory (LSTM), and artificial neural networks (ANNs). Furthermore, to estimate the price of Bitcoin, we first merged two deep learning algorithms, LSTM and attention mechanisms, and then combined LSTM-Attention with gradient-specific optimization to increase our model’s performance. Then we integrated ANN-LSTM and included gradient-specific optimization for the same reason. Our results show that the hybrid model with gradient-specific optimization can be used to anticipate Bitcoin values with better accuracy. Indeed, the hybrid model combines the best features of both approaches, and gradient-specific optimization improves predictive performance through frequent analysis of pricing data changes.
{"title":"Deep Learning Models for Bitcoin Prediction Using Hybrid Approaches with Gradient-Specific Optimization","authors":"Amina Ladhari, Heni Boubaker","doi":"10.3390/forecast6020016","DOIUrl":"https://doi.org/10.3390/forecast6020016","url":null,"abstract":"Since cryptocurrencies are among the most extensively traded financial instruments globally, predicting their price has become a crucial topic for investors. Our dataset, which includes fluctuations in Bitcoin’s hourly prices from 15 May 2018 to 19 January 2024, was gathered from Crypto Data Download. It is made up of over 50,000 hourly data points that provide a detailed view of the price behavior of Bitcoin over a five-year period. In this study, we used potent algorithms, including gradient descent, attention mechanisms, long short-term memory (LSTM), and artificial neural networks (ANNs). Furthermore, to estimate the price of Bitcoin, we first merged two deep learning algorithms, LSTM and attention mechanisms, and then combined LSTM-Attention with gradient-specific optimization to increase our model’s performance. Then we integrated ANN-LSTM and included gradient-specific optimization for the same reason. Our results show that the hybrid model with gradient-specific optimization can be used to anticipate Bitcoin values with better accuracy. Indeed, the hybrid model combines the best features of both approaches, and gradient-specific optimization improves predictive performance through frequent analysis of pricing data changes.","PeriodicalId":508737,"journal":{"name":"Forecasting","volume":"65 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140668046","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：