对比多种模型在零售销量预测中的表现，发现树模型更优。
Comparative Analysis of Modern Machine Learning Models for Retail Sales Forecasting
- 用树模型和深度学习模型对比预测零售销量
- XGBoost在所有配置中误差最低，RMSE为4.833
- 模型选择应匹配实际问题，而非追求复杂架构
准确的需求预测对实体零售商优化库存管理、降低运营成本至关重要。本研究在具有间歇性需求、大量缺失数据和频繁商品更新的零售销售数据上，评估了统计基线、树模型集成（XGBoost、LightGBM）以及深度学习架构（N-BEATS、N-HiTS、Temporal Fusion Transformer）。模型在四种不同聚合层级与插补策略组合下进行比较，采用符合各类模型典型部署模式的评估协议。结果显示，局部化树模型表现最优，其中XGBoost取得最低RMSE为4.833。尽管基于SAITS的插补方法在聚合场景中提升了神经网络性能，但其整体仍逊于集成方法。结果表明，在当前约束条件下，模型选择应优先考虑与问题特征的匹配度，而非架构复杂度。
原文摘要 · Abstract (English)
Accurate demand forecasting is critical for brick-and-mortar retailers to optimize inventory management and minimize costs. This study evaluates statistical baselines, tree-based ensembles (XGBoost and LightGBM), and deep learning architectures (N-BEATS, N-HiTS, and the Temporal Fusion Transformer) on retail sales data characterized by intermittent demand, substantial missingness, and frequent product turnover. Models are compared across four configurations varying by aggregation level and imputation strategy, using evaluation protocols that reflect typical deployment patterns for each model class. Localized tree-based methods achieve superior performance, with XGBoost attaining the lowest RMSE of 4.833. While SAITS-based imputation improved neural network performance in aggregated settings, these models remained inferior to ensemble methods. The results suggest that, under the studied constraints, model selection should prioritize alignment with problem characteristics over architectural sophistication.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。