基于时间序列模型的动态零售环境下产品月销量预测——基于多个模型的比较分析

Prediction of Monthly Product Sales in a Dy-namic Retail Environment Based on Time Series Models—Comparative Analysis Based on Multiple Models

摘要: 本研究旨在探讨如何在动态零售环境下有效地应用时间序列模型来预测产品的月销量。零售业的不断变化和不确定性使得销量预测变得至关重要。利用销售数据，进行数据分析和特征工程。研究包括不同类型的模型，如统计模型、机器学习模型和深度学习模型。实验结果以均方根任务(RMSE)为指标，分析各模型的预测效果。本研究揭示了动态零售环境中的时间序列模型的潜力，为员工提供更好的销量预测工具，从而提高竞争力和盈利能力。这项研究还提供了时间序列模型在其他领域的潜在应用的意见。

Abstract: This study aims to explore how to effectively apply time series models in a dynamic retail environ-ment to predict monthly product sales. The continuous changes and uncertainties in the retail in-dustry make sales forecasting crucial. Utilize sales data for data analysis and feature engineering. Research includes different types of models, such as statistical models, machine learning models, and deep learning models. The experimental results were analyzed using the root mean square task (RMSE) as an indicator to evaluate the predictive performance of each model. The discovery reveals the potential of time series models in dynamic retail environments, providing employees with better sales forecasting tools, thereby improving competitiveness and profitability. This study also provides insights into the potential applications of time series models in other fields.