发表机构
Faculty of Economic Sciences, University of Warsaw; WeSub; Faculty of Mathematics and Information Science, Warsaw University of Technology（华沙大学经济科学学院; WeSub; 华沙理工大学数学与信息科学学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文构建首个二手电子产品价格预测的多周期基准，对比11种统计与深度学习模型，发现N-BEATS在长期预测中表现最优，且可泛化至短期周期，无需针对特定周期单独建模。
AI 中文摘要
二手电子产品转售价格预测对基于订阅制的平台至关重要，定价误差会直接转化为风险。与结构化金融市场不同，二手电子产品价格波动大、挂牌历史稀疏、价格动态非正态分布，但该领域尚无系统性时间序列基准。本文提出首个针对二手电子产品价格预测的统计模型与深度学习模型多周期基准测试。我们使用来自波兰在线市场的大规模每日价格挂牌数据集（2022年1月至2025年3月，涵盖100+款智能手机和笔记本电脑型号），对11种模型在1至365天的6个预测周期进行评估，模型包括经典方法（ARIMA、ETS、Theta）、循环与卷积网络（LSTM、TCN）以及现代深度学习架构（N-BEATS、N-HiTS、TFT、PatchTST、Informer）。三种互补评估协议分别评估轨迹拟合度、单次端点准确率和跨周期迁移能力。N-BEATS在30天以上周期实现最低平均绝对百分比误差（MAPE），365天周期达8.51%，而最佳统计基准为14.94%，降幅达43%。在短期周期（1-7天），所有模型的MAPE均收敛至0.72%附近，朴素基准仍具竞争力。在365天周期训练的单个N-BEATS模型可泛化至所有更短周期，无需针对特定周期训练模型，且N-BEATS与N-HiTS还展现出更优的超参数稳定性。
英文摘要
Forecasting resale prices of used electronics is critical for subscription-based platforms where pricing errors translate directly into risk. Unlike structured financial markets, second-hand electronics exhibit high volatility, sparse listing histories, and non-normal price dynamics - yet no systematic time-series benchmark exists for this domain. This paper presents the first multi-horizon benchmark of statistical and deep learning forecasting models for used electronics price prediction. We use a large-scale dataset of daily price listings from Polish online marketplaces (January 2022 to March 2025, 100+ smartphone and laptop models) and evaluate eleven models across six horizons from 1 to 365 days, covering classical methods (ARIMA, ETS, Theta), recurrent and convolutional networks (LSTM, TCN), and modern deep architectures (N-BEATS, N-HiTS, TFT, PatchTST, Informer). Three complementary evaluation protocols assess trajectory fitness, one-shot endpoint accuracy, and cross-horizon transfer. N-BEATS achieves the lowest MAPE beyond 30 days, reaching 8.51% at 365 days versus 14.94% for the best statistical baseline - a 43% reduction. At short horizons (1-7 days), all models converge near 0.72% MAPE and the naive baseline remains competitive. A single N-BEATS model trained at 365 days generalizes to all shorter horizons, eliminating the need for horizon-specific models. N-BEATS and N-HiTS also demonstrate superior hyperparameter stability.
Comments41 pages, 7 figures, 13 tables
