3367 KB442 KB0 KB2018-2019Dragan, DejanIntihar, MarkoKramberger, TomažXXI, 162 str., 2 f. pril., 30 cmCOBISSID:512984637URN:URN:NBN:SI:doc-TOWFKJW5slM. Intiharvisokošolska delaBox-Jemkins modeličasovne vrsteDFAdinamična faktorska analizaDisertacijedissertationsdynamic factor analysisEM-algoritemlogistikalogistocsmacroeconomic indicatorsmakroekonomski indikatorjiMC simulacijaMC simulationport throughputpredictive analyticsprediktivna analitikaPretovorpretovor pristaniščPristaniščatime seriesBayesovi pristopi ocenjevanja dinamičnih sistemov za potrebe napovedovanja dinamike pretovora pristanišč| doktorska disertacija|Future events forecasting such as a prediction of demand is nowadays an industry standard. Maritime industry is not an exception since the quality of forecasting of a future port's throughput dynamics is the baseline for port task planning. In our work, an algorithm, which combines several fields of statistics and econometrics, is presented. Algorithm's primary goal is to provide fairly accurate future port's throughput predictions. The idea stands on modeling the output time series concerning the selected inputs. Latter are presented in the form of macroeconomic indicators, which are a priori selected from a bigger set of indicators. For this purpose, an initial data reduction of exogenous indicators has been conducted by regressing different combination of subsets of exogenous indicators randomly chosen in the Monte Carlo procedure, where the optimal set of genuinely influential indicators was chosen by observing the model's error-based criteria adopted in the multiple regression static procedure. In the next stage, the reduced set of influential indicators is aggregated into dynamic factor models using the EM algorithm and Kalman filter. Derived dynamic factors are used as inputs into the ARIMAX time series models. Complete mechanism is executed based on five-step heuristic procedure, where generating different ARIMAX candidates eventually leads to the selection of the final best candidate. The obtained ARIMAX model is robust, complies with adequate statistical and econometrics tests, and last, but not least it can provide quite accurate forecasts. The algorithm has been applied to the real port's data. Achieved ARIMAX predictions of the throughput data values were compared with the standard benchmarking models' predictions, whereas the results are promising and reveal a high level of applicabilityNapovedovanje še nerealiziranih dogodkov kot je na primer prediktivna analitika povpraševanja po količini blaga oz. storitev, je današnja vsakdanja praksa za večino subjektov industrije. Pristaniška dejavnost tukaj ni izjema, saj je potrebno zagotavljati kvalitetne napovedi bodočega pretovora pristanišč, ki so osnova za uspešno planiranje pristaniških dejavnosti. V doktorski disertaciji je prikazan algoritem, ki združuje izbrano paleto paradigm iz področja statistike in ekonometrije, z namenom zagotavljanja natančnih napovedi bodoče dinamike pristaniškega tovora. Ideja algoritma temelji na modeliranju časovne vrste izhoda ob upoštevanju izbranih vhodov, ki jih sestavljajo ustrezni ekonomski kazalniki. Le ti so predhodnje izbrani s selekcijsko proceduro in predimenzionirani z namenom zmanjševanja računske kompleksnosti in ohranjanja koristnih informacij osnovnih časovnih vrst. Algoritem kombinira MC simulacijo za selekcijo osnovnega nabora kazalnikov, ter izračun dinamičnih faktorskih modelov z uporabo EM algoritma in Kalmanovega filtra. Ti modeli se uporabljajo kot vhodi v ARIMAX modele časovne vrste opazovanega procesa. Celotni mehanizem pa povezuje pet-fazna procedura, ki preigrava različne strukture kandidatov ARIMAX modelov, in na koncu izbere enega kandidata za izbrani pretovor pristanišča. Končni kandidat je robusten in izpolnjuje temeljne statistično-ekonometrične teste, ter je predvsem zmožen zagotavljati zadovoljivo natančne napovedi. Dani algoritem je bil apliciran na realne podatke izbranega pristanišča. Nato smo izvedli komparativno analizo, v kateri dobljene rezultate primerjamo z napovedmi nekaterih standardnih modelov časovnih vrst. Analiza razkriva uporabnost apliciranega algoritma in nakazuje na koristno uporabo v praksiTEXTvisokošolska delatheses and dissertationsSlovenian National E-content AggregatorNational and University Library of SloveniaUniverza v Mariboru, Fakulteta za logistiko