As an essential part of daily life, the drastic fluctuations in agricultural commodity prices significantly impact producers’ motivation and consumers’ quality of life, further exacerbating market uncertainty and unsustainability. The ability to scientifically and effectively predict agricultural commodity prices is of great significance for the rational deployment of market mechanisms, the timely adjustment of supply chains, and the promotion of food policy adjustments. This paper proposes a sustainable hybrid model SV-PSO-BiLSTM which integrates Seasonal-Trend decomposition procedure based on Loess (STL), Variational Mode Decomposition (VMD), Particle Swarm Optimization (PSO), and Bidirectional Long Short-Term Memory (BiLSTM) neural networks. This innovative approach first performs seasonal decomposition of the original data using the STL method, then applies the VMD method for double decomposition of the residual components, reconstructs the data based on sample entropy, and finally predicts agricultural commodity market prices using the BiLSTM network model optimized by the PSO algorithm. This paper investigates the market price dynamics of four agricultural commodities (chili, garlic, ginger, and pork) and one agricultural financial derivative (soybean futures). The experimental results indicate that the proposed SV-PSO-BiLSTM hybrid model achieves average values of 0.2241 for root mean square error (RMSE), 0.1665 for mean absolute error (MAE), 0.0207 for mean absolute percentage error (MAPE), and 0.9851 for the coefficient of determination (R²). These results surpass those of other comparative models, demonstrating stronger generalization, reliability, and stability. The research findings can provide effective guidance for the reasonable regulation of agricultural commodity market prices and further promote the healthy and sustainable development of the agricultural commodity industry.