对比经典与深度学习模型，评估孟加拉农产品价格预测效果
A Benchmark of Classical and Deep Learning Models for Agricultural Commodity Price Forecasting on A Novel Bangladeshi Market Price Dataset
- 构建了1779条日度价格数据的农业市场基准数据集
- 朴素持续性模型在随机游走型商品上表现最优
- 时间编码对预测无显著提升，部分模型出现严重崩溃
准确预测短期农产品价格对发展中国家粮食安全和小农户收入稳定至关重要，但南亚地区可用于机器学习的数据集仍十分稀缺。本文贡献两点：一是引入AgriPriceBD数据集，包含2020年7月至2025年6月期间五种孟加拉商品（大蒜、鹰嘴豆、青辣椒、黄瓜、甜南瓜）共1,779条日度零售中间价，通过大语言模型辅助数字化流程从政府报告中提取；二是评估七种预测方法——包括朴素持续性、SARIMA、Prophet等经典模型，以及BiLSTM、Transformer、Time2Vec增强Transformer和Informer等深度学习架构，并使用Diebold-Mariano检验进行统计显著性分析。结果表明：商品价格可预测性存在根本异质性，朴素持续性在近似随机游走商品上占优；时间编码未带来统计显著优势，反而使青辣椒预测误差增加146.1%（p<0.001），导致灾难性退化；Prophet系统性失效，因其平滑分解假设无法适应离散阶跃式价格动态；Informer产生高度不稳定的预测（方差达真实值50倍），证实稀疏注意力Transformer在小型农业数据集上训练不足。所有代码、模型与数据已公开，以支持未来对孟加拉及类似经济体农业市场价格预测的研究。
原文摘要 · Abstract (English)
Accurate short-term forecasting of agricultural commodity prices is critical for food security planning and smallholder income stabilisation in developing economies, yet machine-learning-ready datasets for this purpose remain scarce in South Asia. This paper makes two contributions. First, we introduce AgriPriceBD, a benchmark dataset of 1,779 daily retail mid-prices for five Bangladeshi commodities - garlic, chickpea, green chilli, cucumber, and sweet pumpkin - spanning July 2020 to June 2025, extracted from government reports via an LLM-assisted digitisation pipeline. Second, we evaluate seven forecasting approaches spanning classical models - naïve persistence, SARIMA, and Prophet - and deep learning architectures - BiLSTM, Transformer, Time2Vec-enhanced Transformer, and Informer - with Diebold-Mariano statistical significance tests. Commodity price forecastability is fundamentally heterogeneous: naïve persistence dominates on near-random-walk commodities. Time2Vec temporal encoding provides no statistically significant advantage over fixed sinusoidal encoding and causes catastrophic degradation on green chilli (+146.1% MAE, p<0.001). Prophet fails systematically, attributable to discrete step-function price dynamics incompatible with its smooth decomposition assumptions. Informer produces erratic predictions (variance up to 50x ground-truth), confirming sparse-attention Transformers require substantially larger training sets than small agricultural datasets provide. All code, models, and data are released publicly to support replication and future forecasting research on agricultural commodity markets in Bangladesh and similar developing economies.
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。