A Novel Framework for Agricultural Futures Price Prediction With BERT‐Based Topic Identification and Sentiment Analysis DOI
Wensheng Wang, Yuxi Liu

Journal of Forecasting, Journal Year: 2025, Volume and Issue: unknown

Published: April 11, 2025

ABSTRACT In China's financial and economic system, the agricultural futures market plays an important role in guiding to self regulate providing efficient information transmission for regulators. The effective prediction of prices can assist production, monitoring operational risks arising from significant price fluctuations, enhancing predictability pertinence country's macroeconomic regulation policies. This study investigates main variety grain futures—soybean futures, taking into account complex non‐market influencing factors. Using historical data related news headlines soybean as source integrating topic identification sentiment analysis techniques, a novel framework predicting that integrates is constructed. model uses BERTopic extract texts, then FinBERT construct topic‐based features, fuses them with structured constructs LSTM multi‐feature inputs. order better short‐term features state transfer patterns time series, hidden Markov (HMM) further used states, which are deeply fused model. empirical results show fusing significantly improves forecasting accuracy all lags, works best forecasting, combination HMM exhibits performance advantages medium‐ long‐term forecasting. Compared baseline relies only on provide incremental contribution each feature calculated based PI metric close 50%. addition, deep learning–based performs than machine learning models dealing extreme external shocks such climate disasters, COVID‐19 pandemic, Russia–Ukraine conflict.

Language: Английский

Time series forecasting of bed occupancy in mental health facilities in India using machine learning DOI Creative Commons
G. Avinash, Hariom Pachori, Avinash Sharma

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 21, 2025

Machine learning models are vital for forecasting and optimizing healthcare parameters, especially in the context of rising mental health issues India globally. With increasing demand services, effective resource management, like bed occupancy forecasting, is crucial to ensure proper patient care reduce burden on facilities. This study applies six machine models, namely Support Vector Regression, eXtreme Gradient Boosting, Random Forest, K-Nearest Neighbors, Decision Tree, forecast weekly second largest hospital India, using data from 2008 2024. Accuracy were evaluated Mean Absolute Percentage Error, Diebold–Mariano test assessing differences predictive performance. Further, we occupancy, providing insights administrators capacity planning allocation, supporting data-driven decisions enhancing quality services India.

Language: Английский

Citations

1
Deep Learning Approaches for Potato Price Forecasting: Comparative Analysis of LSTM, Bi-LSTM, and AM-LSTM Models DOI
A. Praveen Kumar, Girish Kumar Jha,

Sharanbasappa D. Madival

et al.

Potato Research, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 25, 2024

Language: Английский

Citations

4
A Vegetable-Price Forecasting Method Based on Mixture of Experts DOI Creative Commons
Chong-Ke Zhao, Xiaodong Wang, Anping Zhao

et al.

Agriculture, Journal Year: 2025, Volume and Issue: 15(2), P. 162 - 162

Published: Jan. 13, 2025

The accurate forecasting of vegetable prices is crucial for policy formulation, market decisions, and agricultural stability. Traditional time-series models often require manual parameter tuning struggle to effectively handle the complex non-linear characteristics price data, limiting their predictive accuracy. This study conducts a comprehensive analysis performance traditional methods, deep learning approaches, cutting-edge large language in vegetable-price using multiple metrics. Experimental results demonstrate that generally outperform other but do not have consistent all kinds vegetables across different time scales. As result, we propose novel method based on mixture expert (VPF-MoE), which combines strengths methods. Different from single model prediction method, VPF-MoE can dynamically adapt types, select best significantly improve accuracy robustness prediction. In addition, optimized application forecasting, offering new technological pathway

Language: Английский

Citations

0
NARX Model for Potato Price Prediction Utilising Multimarket Information DOI Creative Commons
Ronit Jaiswal, Girish Kumar Jha, Rajeev Ranjan Kumar

et al.

Potato Research, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 17, 2025

Language: Английский

Citations

0
A Novel Framework for Agricultural Futures Price Prediction With BERT‐Based Topic Identification and Sentiment Analysis DOI
Wensheng Wang, Yuxi Liu

Journal of Forecasting, Journal Year: 2025, Volume and Issue: unknown

Published: April 11, 2025

ABSTRACT In China's financial and economic system, the agricultural futures market plays an important role in guiding to self regulate providing efficient information transmission for regulators. The effective prediction of prices can assist production, monitoring operational risks arising from significant price fluctuations, enhancing predictability pertinence country's macroeconomic regulation policies. This study investigates main variety grain futures—soybean futures, taking into account complex non‐market influencing factors. Using historical data related news headlines soybean as source integrating topic identification sentiment analysis techniques, a novel framework predicting that integrates is constructed. model uses BERTopic extract texts, then FinBERT construct topic‐based features, fuses them with structured constructs LSTM multi‐feature inputs. order better short‐term features state transfer patterns time series, hidden Markov (HMM) further used states, which are deeply fused model. empirical results show fusing significantly improves forecasting accuracy all lags, works best forecasting, combination HMM exhibits performance advantages medium‐ long‐term forecasting. Compared baseline relies only on provide incremental contribution each feature calculated based PI metric close 50%. addition, deep learning–based performs than machine learning models dealing extreme external shocks such climate disasters, COVID‐19 pandemic, Russia–Ukraine conflict.

Language: Английский

Citations

0