压缩LSTM模型可让小零售业用更低算力实现更高精度销售预测。
Optimizing LSTM Neural Networks for Resource-Constrained Retail Sales Forecasting: A Model Compression Study
- 通过逐步减少LSTM隐藏单元数，研究模型压缩与精度的权衡。
- 64单元模型比128单元模型误差更低，MAPE从23.6%降至12.4%。
- 模型缩小73%，准确率提升47%，适合资源受限的中小零售场景。
标准LSTM神经网络在零售销售预测中表现精准，但计算开销大，对中小型零售企业构成挑战。本文通过将隐藏单元数从128逐步降至16，对LSTM模型进行压缩研究。基于包含91.3万条日销售记录的Kaggle Store Item Demand Forecasting数据集（10家门店、50个商品），评估模型大小与预测精度的权衡。实验表明，将隐藏单元数降至64时，模型精度不降反升，均绝对百分比误差（MAPE）由128单元模型的23.6%降至12.4%。优化后模型体积从280KB减至76KB，缩小73%，准确率提升47%。结果表明，更大模型并非必然更优。
原文摘要 · Abstract (English)
Standard LSTM(Long Short-Term Memory) neural networks provide accurate predictions for sales data in the retail industry, but require a lot of computing power. It can be challenging especially for mid to small retail industries. This paper examines LSTM model compression by gradually reducing the number of hidden units from 128 to 16. We used the Kaggle Store Item Demand Forecasting dataset, which has 913,000 daily sales records from 10 stores and 50 items, to look at the trade-off between model size and how accurate the predictions are. Experiments show that lowering the number of hidden LSTM units to 64 maintains the same level of accuracy while also improving it. The mean absolute percentage error (MAPE) ranges from 23.6% for the full 128-unit model to 12.4% for the 64-unit model. The optimized model is 73% smaller (from 280KB to 76KB) and 47% more accurate. These results show that larger models do not always achieve better results.
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。