0619365 20260224162647.020250502235959.9 105004009861 001487744100001 10.1016/j.eswa.2025.127716 9 s. P cav_un_epca*02529430957-4174283Elsevier Model structure estimation Exponential family ARX model Feature selection Forecasting of futures cav_un_auth*0101124 Kárný Miroslav UTIA-B Adaptivní systémy Department of Adaptive Systems AS AS 100 A Ústav teorie informace a automatizace AV ČR, v. v. i. https://library.utia.cas.cz/separaty/2025/AS/karny-0619365.pdf https://www.sciencedirect.com/science/article/pii/S0957417425013387?via%3Dihub CA21169 EU-COST XE cav_un_auth*0452289 Model structure estimation has gained attention owing to the challenge of analysing large, scarce, and poorly informative data. Bayesian hypothesis testing formally addresses this issue. For nested model structures, an efficient search method provides the maximum a posteriori (MAP) estimate, even in extensive hypothesis spaces. However, estimation quality highly depends on prior probability densities of the unknown, hypothesis-specific parameters. Existing solutions mitigate this issue by estimating multivariate hyperparameters of these priors, however, these solutions restrict the hyperparameter space, limiting estimation quality. This study enhances model structure estimation for exponential family models by imposing minimal constraints on the selected hyperparameter. For Gaussian models with linearly weighted auto-regression and regression variables, the MAP hyperparameter estimate is analytic and requires solving only one equation for a scalar variable. Experiments, including a complex simulation and multi-step forecasting of futures prices, confirm the solution quality gains. WOS BD 10000 10200 10201 2026 1 RVO:67985556 https://hdl.handle.net/11104/0366453 S 127716 C COMPUTERSCIENCE.ARTIFICIALINTELLIGENCE|ENGINEERING.ELECTRICAL&ELECTRONIC|OPERATIONSRESEARCH&MANAGEMENTSCIENCE 7.8 1.5 3.3 0.09713 1.385 102444 290 1.854 56.83 10.48 63040 Q1 6.800 2925 Q1 90.2 1.49 Q1 93.9 2025 105004009861 SCOPUS PUBMED 001487744100001 WOS cav_un_epca*0252943 Expert Systems With Applications 283 1 2025 0957-4174 1873-6793 Elsevier