Information Sets and Learning Models for First Exits from Dynamic Price Zones: An Empirical Competing-Risk Study
- 1Department of Computer Software Engineering, Soonchunhyang University, 22 Soonchunhyang-ro, Asan-si 31538, Chungcheongnam-do, Republic of Korea
- 2Department of Software Convergence, Soonchunhyang University, 22 Soonchunhyang-ro, Asan-si 31538, Chungcheongnam-do, Republic of Korea
Abstract
We evaluate the information and model complexity needed to forecast first closing-price exits from pre-issued dynamic zones. Established competing-risk principles encode no exit within 60 min and first upper/lower exits in four intervals as nine outcomes. Annual historical analysis uses 502,443 DZ-LSTM-zone and 474,591 causal moving-quantile (MQ60) test origins for BTC, ETH, and XRP from 2020 through June 2026. Multinomial logit, XGBoost, survival forest, and an auxiliary MLP receive 22 non-zone predictors, 2 added distances, or all 32 inputs. Exact-calendar reconstruction repeats all 504 learner/information-set fits on unchanged historical targets and samples. Full inputs have lower Brier loss than non-zone inputs in 4/4 DZ-LSTM and 4/4 MQ60 learners, with signed relative reductions of 10.02–11.85% and 13.58–14.53%, respectively. Two distances recover most historical input gains. A locked follow-up applies stored 2026 MQ60 models and training scalers without tuning to 19,056 unused origins from 30 June through 30 September 2026; 4/4 learners have lower full-input Brier, and 4/4 reductions remain Holm-significant under all tested date-block choices. The contribution is empirical evidence about boundary information and learner choice. These retrospective checks do not establish a new output layer or universal neural superiority. Existing volatility benchmarks and negative external-market results delimit interpretation. Episode alerts remain optional illustrations under assumed policies and costs.
Related
- Nonparametric Efficient Estimation of Dynamic Treatment Regimes with Competing Risks
- Advancing Competing Risks Analysis via Adaptive Progressive First-Failure Censoring: The Xgamma Distribution Case with an Application
- Robust and Sparse Group Dynamic Causal Modeling via Student-t Parametric Empirical Bayes and Nonlocal Priors
- An Interaction-Aware Decision Framework for FDIC-Assisted Distressed Bank Acquisitions: Empirical Evidence from the FDIC Failed-Bank Panel and the SVB-First Citizens Case
- Empirical Bayes in Bayesian learning: understanding a common practice
BibTeX
@article{kim2026information,
title = {{Information Sets and Learning Models for First Exits from Dynamic Price Zones: An Empirical Competing-Risk Study}},
author = {Giwon Kim and Yoojeong Song and Sang Ik Han},
journal = {Mathematics},
year = {2026},
month = oct,
doi = {10.3390/math14213963},
url = {https://www.mdpi.com/2227-7390/14/21/3963},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Information Sets and Learning Models for First Exits from Dynamic Price Zones: An Empirical Competing-Risk Study
AU - Giwon Kim
AU - Yoojeong Song
AU - Sang Ik Han
PY - 2026
DA - 2026/10/30
JO - Mathematics
DO - 10.3390/math14213963
UR - https://www.mdpi.com/2227-7390/14/21/3963
AB - We evaluate the information and model complexity needed to forecast first closing-price exits from pre-issued dynamic zones. Established competing-risk principles encode no exit within 60 min and first upper/lower exits in four intervals as nine outcomes. Annual historical analysis uses 502,443 DZ-LSTM-zone and 474,591 causal moving-quantile (MQ60) test origins for BTC, ETH, and XRP from 2020 through June 2026. Multinomial logit, XGBoost, survival forest, and an auxiliary MLP receive 22 non-zone predictors, 2 added distances, or all 32 inputs. Exact-calendar reconstruction repeats all 504 learner/information-set fits on unchanged historical targets and samples. Full inputs have lower Brier loss than non-zone inputs in 4/4 DZ-LSTM and 4/4 MQ60 learners, with signed relative reductions of 10.02–11.85% and 13.58–14.53%, respectively. Two distances recover most historical input gains. A locked follow-up applies stored 2026 MQ60 models and training scalers without tuning to 19,056 unused origins from 30 June through 30 September 2026; 4/4 learners have lower full-input Brier, and 4/4 reductions remain Holm-significant under all tested date-block choices. The contribution is empirical evidence about boundary information and learner choice. These retrospective checks do not establish a new output layer or universal neural superiority. Existing volatility benchmarks and negative external-market results delimit interpretation. Episode alerts remain optional illustrations under assumed policies and costs.
SN - 2227-7390
ER -