20.500.12556/DKUM-95043 Uporaba genetskega programiranja za napoved cen kriptovalut magistrsko delo Use of genetic programming for cryptocurrency prices prediction Odkar so se pojavile kriptovalute in hitro za tem občutek hitrega zaslužka, se je rodilo zanimanje za napoved njihovih cen. Zaradi nepredvidljivosti in visoke volatilnosti gibanja cen tradicionalne metode ne zadoščajo pri ustvarjanju zanesljivih napovedi. Namen magistrskega dela je razvoj napovednega modela, ki bo znal samostojno napovedati ceno kriptovalute naslednjega dne. Cilj napovednega modela je čim natančnejša napoved za več kriptovalut. Model temelji na genetskem programiranju z uporabo simbolične regresije. Vhodni podatki algoritma so zgodovinski podatki in tehnični kazalniki. Z metodo iskanja po mreži smo optimizirali parametre genetskega algoritma. Rezultati napovedovanja kažejo, da je genetsko programiranje učinkovito pri napovedovanju cen kriptovalut, zato smo preizkusili, kako se obnese pri energentih, saj so ti nekoliko manj volatilni. Pri energentih se je model obnesel še bolj učinkovito. Zaključimo lahko, da je naša metoda primerno orodje za obravnavo problemov z visoko volatilnostjo in kompleksnostjo. Naloga je primer praktične uporabe naprednih evolucijskih algoritmov za reševanje realnih problemov in ponuja osnovo za nadaljnje raziskave na področju napovedovanja časovnih vrst. Since the emergence of cryptocurrencies and the accompanying promise of quick profits, interest in forecasting their prices has grown rapidly. Due to the unpredictability and high volatility of price movements, traditional methods often fail to provide reliable predictions. The purpose of this thesis is to develop a predictive model capable of independently forecasting the next-day price of a cryptocurrency. The goal of the model is to deliver accurate predictions across multiple cryptocurrencies. The model is based on genetic programming using symbolic regression. The algorithm uses historical data and technical indicators as input features. We optimized the genetic algorithm parameters using grid search. The forecasting results demonstrate that genetic programming is effective in predicting cryptocurrency prices. Therefore, we also tested the model on energy commodities, which tend to be less volatile. The model performed even better in this domain. We conclude that our method is a suitable tool for addressing problems characterized by high volatility and complexity. This thesis represents a practical application of advanced evolutionary algorithms to real-world forecasting problems and provides a solid foundation for future research in time series prediction. genetsko programiranje napoved cen kriptovalute energenti genetic programming price prediction cryptocurrencies energy commodities true true false [T. Heric] Slovenski jezik Angleški jezik Magistrsko delo/naloga 2025-09-02 17:11:05 2025-10-15 13:17:40 2025-11-29 03:14:51 0000-00-00 00:00:00 2025 0 Maribor 0 Maribor 1 spletni vir (1 datoteka PDF (VIII, 50 str.)) 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 004.421:336.74(043.2) 259168003 MAG_Heric_Tilen_2025.pdf MAG_Heric_Tilen_2025.pdf 1 609E7D121641EC66149702DF94ABF0F8 f78b73ada0563ba7a7266fd099b32cb1822d443223f19f193dc53fd26bd3dbea 7902f683-88b2-11f0-82a8-00155d000105 https://dk.um.si/Dokument.php?lang=slv&id=197471 Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0