Zhejiang Pharmaceutical University, Ningbo 315000, China.
Comput Intell Neurosci. 2022 Jul 4;2022:6836524. doi: 10.1155/2022/6836524. eCollection 2022.
The establishment of enterprise target inventory is directly related to the forecast of drug sales volume. Accurate sales forecasting can help businesses not only set accurate target inventory but also avoid inventory backlogs and shortages. In this paper, NN technology is used to forecast sales and is optimized using the PSO algorithm, resulting in the creation of a drug sale forecast model. The model optimizes the weights and thresholds of NN using the improved PSO optimization algorithm and predicts the periodic components based on time correlation characteristics, effectively describing the trend growth and seasonal fluctuations of sales forecast data. Furthermore, the model in this paper has been creatively improved according to the needs of practical application, which has improved the shortcomings of traditional NN, such as long training time, slow convergence speed, and ease to fall into local minima, to improve performance and quality, and has received positive results in application. The experimental results show that this model has a prediction accuracy of 96.14 percent, which is 12.78 percent higher than the traditional BP model. The optimized model can be used to forecast drug sales in a practical and feasible way.
企业目标库存的建立直接关系到药品销售量的预测。准确的销售预测不仅可以帮助企业设定准确的目标库存，还可以避免库存积压和短缺。本文使用 NN 技术进行销售预测，并使用 PSO 算法进行优化，从而创建了一个药品销售预测模型。该模型使用改进的 PSO 优化算法优化 NN 的权重和阈值，并根据时间相关性特征预测周期性分量，从而有效描述销售预测数据的趋势增长和季节性波动。此外，根据实际应用的需要，本文对模型进行了创新性的改进，提高了传统 NN 训练时间长、收敛速度慢、容易陷入局部最小值等缺点的性能和质量，在应用中取得了积极的效果。实验结果表明，该模型的预测准确率为 96.14%，比传统的 BP 模型高出 12.78%。优化后的模型可以用于实际可行的药品销售预测。
