|
|
|
|
| LEADER |
00000naa2a2200000 4500 |
| 001 |
687470 |
| 005 |
20260826133848.0 |
| 090 |
|
|
|a 687470
|
| 100 |
|
|
|a 20260713d2026 k||y0rusy50 ca
|
| 101 |
0 |
|
|a eng
|
| 102 |
|
|
|a RU
|
| 135 |
|
|
|a drbn ---uucaa
|
| 200 |
1 |
|
|a Residual-based regime detection using local walk-forward autoregressive models
|f Khalil M. E.T., Aksenov S. V.
|
| 320 |
|
|
|a References: 9 tit
|
| 330 |
|
|
|a Financial markets are non-stationary, causing forecasting models to fail intermittently. This paper proposes a walk-forward ARIMAX framework where residual dynamics, rather than forecasts alone, are used to detect regime changes. Empirical results on hourly XAUUSD data demonstrate that normalized forecast errors provide informative, model-aware regime signals
|
| 336 |
|
|
|a Текстовый файл
|
| 463 |
|
1 |
|0 687244
|9 687244
|t Молодежь и современные информационные технологии
|o сборник трудов XXIII Международной научно-практической конференции студентов, аспирантов и молодых ученых, 18–20 февраля 2026 г., Томск
|c Томск
|d 2026
|n Изд-во ТПУ
|u conference_tpu-2026-C04.pdf
|v С. 496-500
|
| 545 |
1 |
|
|a Искусственный интеллект и машинное обучение
|
| 610 |
1 |
|
|a электронный ресурс
|
| 610 |
1 |
|
|a труды ученых ТПУ
|
| 610 |
1 |
|
|a regime detection
|
| 610 |
1 |
|
|a financial markets
|
| 610 |
1 |
|
|a residual analysis
|
| 610 |
1 |
|
|a time series
|
| 610 |
1 |
|
|a финансовые рынки
|
| 610 |
1 |
|
|a остаточный анализ
|
| 610 |
1 |
|
|a временные ряды
|
| 700 |
|
1 |
|a Khalil
|b M. E. T.
|
| 702 |
|
1 |
|a Aksenov
|b A. V.
|c specialist in the field of informatics and computer technology
|c engineer of Tomsk Polytechnic University
|f 1990-
|g Andrey Vladimirovich
|4 727
|
| 801 |
|
0 |
|a RU
|b 63413507
|c 20260713
|
| 850 |
|
|
|a 63413507
|
| 856 |
4 |
0 |
|u http://earchive.tpu.ru/handle/11683/139121
|z http://earchive.tpu.ru/handle/11683/139121
|
| 942 |
|
|
|c CF
|
