Related Experiment Videos
Enterprise retail price prediction method based on improved HPO-LSTM algorithm.
1Jining College, Qufu, China.
Plos One
|January 2, 2026
Summary
This study introduces an enhanced Hunter-Prey optimization-long short-term memory algorithm for accurate retail price prediction. The improved model significantly boosts prediction accuracy, reducing costs and increasing profits for businesses.
Area of Science:
- Economics
- Computer Science
- Artificial Intelligence
Background:
- Accurate price prediction is crucial for enterprise success in market economies.
- Current methods may lack the precision needed for optimal inventory management and profit maximization.
Purpose of the Study:
- To develop an advanced optimization algorithm for precise retail price prediction.
- To enhance resource allocation, economic efficiency, and business profitability.
Main Methods:
- Integration of Hunter-Prey optimization algorithm with long short-term memory (LSTM) networks.
- Incorporation of attention mechanisms and Q-learning for model optimization.
Main Results:
- The proposed algorithm demonstrated superior prediction accuracy (RMSE: 0.48, MAE: 0.20) compared to control models.
- Achieved high accuracy (0.972) and recall (0.921) post-convergence.
- Led to significant reductions in inventory costs (15.2%) and promotion costs (20.3%), with increased sales revenue (15.4%) and profits (20.4%).
Conclusions:
- The enhanced algorithm offers a robust and adaptable tool for retail price prediction.
- Provides enterprises with improved inventory management, reduced waste, and enhanced market competitiveness.
