Designing time-series models with hypernetworks and adversarial portfolios
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11640%2F25%3A00639341" target="_blank" >RIV/00216208:11640/25:00639341 - isvavai.cz</a>
Výsledek na webu
<a href="https://doi.org/10.1016/j.ijforecast.2025.01.005" target="_blank" >https://doi.org/10.1016/j.ijforecast.2025.01.005</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1016/j.ijforecast.2025.01.005" target="_blank" >10.1016/j.ijforecast.2025.01.005</a>
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Designing time-series models with hypernetworks and adversarial portfolios
Popis výsledku v původním jazyce
This article describes the methods that achieved fourth and sixth place in the forecasting and investment challenges, respectively, of the M6 competition, ultimately securing first place in the overall duathlon ranking. In the forecasting challenge, we tested a novel meta-learning model that utilizes hypernetworks to design a parametric model tailored to a specific family of forecasting tasks. This approach allowed us to leverage similarities observed across individual forecasting tasks (i.e., assets) while also acknowledging potential heterogeneity in their data generating processes. The model’s training can be directly performed with backpropagation, eliminating the need to rely on higher-order derivatives, and is equivalent to a simultaneous search over the space of parametric functions and their optimal parameter values. The proposed model’s capabilities extend beyond M6, demonstrating superiority over state-of-the-art meta-learning methods in the sinusoidal regression task and outperforming conventional parametric models on time series from the M4 forecasting competition. In the investment challenge, we adjusted portfolio weights to induce greater or smaller correlation between our submission and that of other participants, depending on the current ranking, aiming to maximize the probability of achieving a good rank. While this portfolio strategy can increase the probability of securing a favorable rank, it paradoxically exhibits negative expected returns.
Název v anglickém jazyce
Designing time-series models with hypernetworks and adversarial portfolios
Popis výsledku anglicky
This article describes the methods that achieved fourth and sixth place in the forecasting and investment challenges, respectively, of the M6 competition, ultimately securing first place in the overall duathlon ranking. In the forecasting challenge, we tested a novel meta-learning model that utilizes hypernetworks to design a parametric model tailored to a specific family of forecasting tasks. This approach allowed us to leverage similarities observed across individual forecasting tasks (i.e., assets) while also acknowledging potential heterogeneity in their data generating processes. The model’s training can be directly performed with backpropagation, eliminating the need to rely on higher-order derivatives, and is equivalent to a simultaneous search over the space of parametric functions and their optimal parameter values. The proposed model’s capabilities extend beyond M6, demonstrating superiority over state-of-the-art meta-learning methods in the sinusoidal regression task and outperforming conventional parametric models on time series from the M4 forecasting competition. In the investment challenge, we adjusted portfolio weights to induce greater or smaller correlation between our submission and that of other participants, depending on the current ranking, aiming to maximize the probability of achieving a good rank. While this portfolio strategy can increase the probability of securing a favorable rank, it paradoxically exhibits negative expected returns.
Klasifikace
Druh
J<sub>imp</sub> - Článek v periodiku v databázi Web of Science
CEP obor
—
OECD FORD obor
50202 - Applied Economics, Econometrics
Návaznosti výsledku
Projekt
—
Návaznosti
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Ostatní
Rok uplatnění
2025
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název periodika
International Journal of Forecasting
ISSN
0169-2070
e-ISSN
1872-8200
Svazek periodika
41
Číslo periodika v rámci svazku
4
Stát vydavatele periodika
NL - Nizozemsko
Počet stran výsledku
16
Strana od-do
1461-1476
Kód UT WoS článku
001568757800001
EID výsledku v databázi Scopus
2-s2.0-85219045849