Paper: arXiv 2610.10727

Authors: Mateusz Buczyński, Michał Woźniak, Konrad Kaczyński, Anna Wróblewska, Sebastian Kuk

Abstract

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.

Complexity vs Empirical Score

  • Math Complexity: 6.0/10
  • Empirical Rigor: 9.0/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: This paper presents a highly rigorous empirical benchmark using advanced deep learning models, addressing a novel problem domain. The methodology is clearly articulated, and the results offer significant practical implications for pricing in second-hand electronics markets.

Research Flowchart

  flowchart TD
    A[Research Goal: Benchmark DL vs. Statistical Models for Multi-Horizon Price Forecasting of Used Electronics] --> B{Key Methodology: Systematic Benchmarking};
    B --> C[Data Inputs: Large-scale dataset of daily price listings (Jan 2022 - Mar 2025) for 100+ smartphone/laptop models];
    C --> D{Computational Process: Evaluate 11 models across 6 horizons (1-365 days) using 3 evaluation protocols};
    D --> E[Key Findings/Outcomes: N-BEATS outperforms beyond 30 days (43% MAPE reduction at 365 days vs. best statistical model)];
    E --> F[Further Findings: N-BEATS generalizes across horizons; all models converge at short horizons; N-BEATS/N-HiTS show hyperparameter stability];