ABSTRACT Accurate forecasting of agricultural prices is essential for informed production planning, market stabilisation and effective policy design. This review examines 773 studies published between 2006 and 2025 to synthesise recent advances. We begin by analysing the factor systems and structural characteristics of agri‐price data, and organise forecasting tasks by input–output design, temporal resolution and prediction objectives—ranging from point estimates to trend detection and probabilistic forecasting. Evaluation practices are reviewed across multiple dimensions, including error metrics, trend alignment, model selection and uncertainty estimation. We then trace the evolution of forecasting 15 methods from traditional statistical models to machine learning and deep neural 16 architectures (RNN, CNN, GNN, Transformer), as well as decomposition‐based and 17 ensemble strategies. These developments are contextualised within bibliometric trends, highlighting shifts in research focus and global collaboration. Empirical evidence shows that hybrid pipelines combining decomposition, feature learning and ensemble techniques tend to outperform standalone models, while simple linear models remain competitive for long‐horizon or low‐frequency forecasts. Common challenges include data leakage, inconsistent testing horizons and insufficient treatment of uncertainty. Looking ahead, future research should emphasise integrating diverse data sources—such as weather, trade and policy signals—and building models that can adapt to unexpected market changes. It is equally important to understand how price dynamics respond to policy actions, improve model transferability across regions and commodities and provide well‐calibrated forecasts with interpretable uncertainty estimates to enhance the practical value of agricultural price prediction.

ABSTRACT With the growing complexity of real‐world engineering optimisation problems, interest in meta‐heuristic algorithms is increasing. However, existing meta‐heuristic algorithms still suffer from several shortcomings, including a poor balance between global and local search, a tendency to converge toward the centre of the solution space, and susceptibility to getting trapped in local optima. To overcome these shortcomings, a novel meta‐heuristic algorithm, called artificial orca optimiser (AOO), is proposed based on the unique behaviours of orcas in nature. Within the framework of AOO, the switching factor, guidance phase, and iterative formulas that do not converge toward the centre of the solution space, are designed to enhance the equilibrium between exploration and exploitation, ensure agents the ability to escape from the local optimum, and comprehensively explore the solution space without being limited to the centre of the solution space, thereby increasing the likelihood of finding the global optimal solution. Qualitative, quantitative, scalability, sensitivity, and practical application analyses of the experimental results demonstrate that AOO overcomes the issue of converging to the centre of the solution space, alleviates the problems of poor balance and susceptibility to the local optimum, and exhibits outstanding optimising performance, fast convergence, great scalability, high robustness, and excellent practicality.

ABSTRACT More and more companies have realised that implementing a joint replenishment and delivery (JRD) strategy can lead to significant cost savings. This paper presents a practical JRD problem for heterogeneous products, taking into account resource constraints. An enhanced hiking optimization technique called BHHOA is proposed. BHHOA incorporates a bound heuristic to refine the delivery frequency boundaries and introduces two new population generation methods based on the differential evolution algorithm and attention mechanism. Experimental results demonstrate that BHHOA outperforms six other algorithms with a lower average total cost. The JRD model presented in this study is effectively solved using the BHHOA algorithm. This study provides a practical technical method for companies to implement the JRD strategy.

Abstract There has been much work in establishing joint replenishment model and designing effective and robust algorithms. Little research has been done by direct grouping methods. In this paper, we present a differential evolution (DE) algorithm that uses direct grouping to solve joint replenishment problem (JRP). Extensive computational experiments are performed to compare the performances of the DE algorithm with results of evolutionary algorithm (GA). The experimental results indicate that the DE algorithm can find a replenishment policy that incurs a lower total cost than the GA. We also conducted a case study to test the proposed DE algorithm for the JRP. The findings suggest that the proposed model is successful in decreasing spare parts ordering costs and holding costs significantly in a power plant.