magistrsko delo
Luka Štrakl (Author), Peter Kokol (Mentor)

Abstract

V magistrskem delu je opisano področje avtomatiziranega trgovanja z algoritmičnim pristopom, ki temelji na odločitvah napovednih modelov, katerih znanje je pridobljeno s pomočjo strojnega učenja. Opisane je delo z podatki, metode strojnega učenja in izdelava napovednih modelov v programskem jeziku Python. Poudarek je na pridobivanju, manipulaciji in uporabi vhodnih podatkov, ter optimizaciji napovednega modela za dosego boljših odločitev na še ne videnih podatkih. V sklopu magistrske naloge smo izdelali programsko opremo algoritmične narave, ki uporablja sožitje pogojev, ki jih trgovalni instrument mora zadovoljiti, ter odločitve dveh napovednih modelov za odpiranje ali zapiranje trgovalnih pozicij.

Keywords

trgovanje;delnice;strojno učenje;napovedni modeli;magistrske naloge;

Data

Language: Slovenian
Year of publishing:
Typology: 2.09 - Master's Thesis
Organization: UM FERI - Faculty of Electrical Engineering and Computer Science
Publisher: [L. Štrakl]
UDC: 004.85:004.777(043.2)
COBISS: 63069955 Link will open in a new window
Views: 490
Downloads: 74
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Automated trading with a smart prediction model
Secondary abstract: This master's thesis describes the topic of automated trading with the use of an algorithmic approach based on decisions made by smart prediction models. The models possess the knowledge derived from machine learning techniques. We describe the used data set and techniques used for machine learning and implementation of a smart prediction model using the Python programming language. The emphasis is on the gathering, transformation and usage of input data as well as on the optimization of the prediction model to get the best results possible from new data sets. The product of the thesis is a software based on the algorithm that requires that certain market place conditions are met with a conjunction of smart model predictions to open or close the trading positions
Secondary keywords: Trading;Forex;Stocks;machine learning;prediction model;
Type (COBISS): Master's thesis/paper
Thesis comment: Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko, Računalništvo in informacijske tehnologije
Pages: VII, 66 f.
ID: 12613660