Related Experiment Videos
Deep learning-enabled cherry price forecasting and real-time system deployment across multi-market supply chains in
F A Shaheen1, Aqib Gul2, Nazir Ganai3
1Institute of Business and Policy Research, Sher-e-Kashmir University of Agricultural Sciences and Technology of Kashmir, Srinagar, J&K, 190025, India. fashaheen@yahoo.com.
Scientific Reports
|December 10, 2025
Summary
Deep learning models, specifically Long Short-Term Memory (LSTM) and Transformer, significantly outperform traditional methods for daily cherry price forecasting. These advanced AI models achieved over 92% accuracy, offering a scalable framework for agricultural market intelligence in India.
Area of Science:
- Agricultural Economics
- Data Science
- Artificial Intelligence
Background:
- Accurate price forecasting for high-value perishable goods like cherries is vital for supply chain efficiency, producer income stability, and informed decision-making.
- Existing statistical and machine learning models often struggle to capture the complex, non-linear dynamics inherent in agricultural commodity prices.
Purpose of the Study:
- To investigate the efficacy of Deep Learning (DL) architectures for real-time daily cherry price prediction.
- To compare the performance of DL models against conventional statistical and Machine Learning (ML) methods.
- To develop a practical, AI-driven advisory tool for agricultural market intelligence.
Main Methods:
- Utilized daily cherry price data from five Indian wholesale markets (2012-2024).
- Evaluated six forecasting models: Seasonal Auto-regressive Integrated Moving Average (SARIMA), Prophet, Random Forest (RF), Extreme Gradient Boosting (XGBoost), Long Short-Term Memory (LSTM), and Transformer.
- Implemented the best-performing LSTM model as a live, web-based forecasting system during the 2025 cherry season.
Main Results:
- Deep learning models (LSTM, Transformer) demonstrated superior ability in capturing non-linear price fluctuations compared to statistical and tree-based methods.
- The LSTM model achieved over 92% accuracy in real-world application, with low error margins (MAE 5-8, RMSE 8-12) and sMAPE below 5-10% in major markets.
- The Diebold-Mariano (DM) test confirmed the statistical superiority of deep learning approaches over baseline models.
Conclusions:
- Deep learning models offer a robust and accurate solution for real-time agricultural price forecasting, surpassing conventional methods.
- The developed AI framework provides a scalable and operational methodology for integrating advanced analytics into India's agricultural market intelligence systems.
- This study establishes a precedent for leveraging AI in the agriculture sector for enhanced decision support and market stability.
Related Concept Videos
01:25Distribution Reliability and Automation
474
Distribution reliability in electrical power systems is critical for ensuring an uninterrupted power supply to consumers at minimal cost. According to IEEE Standard Terms, reliability is the probability that a device will function without failure over a specified time period or amount of usage. For electric power distribution, this translates to maintaining continuous power supply and addressing customer concerns over power outages. Several indices, as defined by IEEE Standard 1366-2012, are...
474
01:12Observational Learning
791
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
791
01:18Introduction to Learning
895
Learning is the process of acquiring knowledge or skills through practice or experience, leading to long-lasting behavioral changes. This acquisition occurs through interaction with the environment and requires practice or experience. For instance, mastering a skill such as surfing requires considerable practice and experience, highlighting the essential role of repeated interactions with the environment in learning.
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
895