magistrsko delo
Jakob Bračun (Author), Vitomir Štruc (Mentor)

Abstract

Avtomatska obdelava finančnih podatkov za namene napovedovanja cen delnic je čedalje pogostejša tako pri posameznikih kot korporacijah. Kljub temu ostaja uspešno napovedovanje za veliko večino nerešena uganka. Dejavnikov, ki vplivajo na oblikovanje cen delnic na delniškem trgu je ogromno, preveč, da bi lahko zaobjeli vse. Poleg tega obstaja še teorija o učinkovitem trgu, ki trdi da je kakršno koli napovedovanje na podlagi javno dostopnih informacij zaman, saj se v ceni vse te informacije že odražajo. Pojavi se še vprašanje, kako modele napovedovanja čim bolje ovrednotiti. V tem magistrskem delu uporabimo metodo podpornih vektorjev za namene napovedovanja končne cene delnic štirih ameriških podjetij. Za napovedovanje razvijemo tako klasifikacijska kot regresijska modela, medtem ko vhodne podatke uporabimo zgodovinske podatke in njihove izpeljanke v obliki tehničnih indikatorjev. Napovedovalno moč modelov ovrednotimo in jo primerjamo z modelom naključnega sprehoda, ki naj bi bil optimalen model za napovedovanje v učinkovitem trgu. Ker gre za finančne časovne vrste, ustreznost modelov preverimo še v simuliranem trgovalnem okolju, z uporabo preproste strategije trgovanja na podlagi napovedanih vrednosti. Pri analizi rezultatov, najprej na podlagi napake med napovedano in dejansko ceno preverimo uspešnost obeh regresijskih modelov in ugotovimo, da smo v nekaj primerih boljši od modela naključnega sprehoda. Analizo nadaljujemo s preverjanjem odstotka pravilno napovedanih smeri sprememb cene, kjer vsi modeli razen enega regresijskega kažejo večjo napovedovalno moč od modela naključnega sprehoda. Na koncu preverimo še uspešnost trgovalne strategije, pri čemer ima daleč najboljše rezultate regresijski model, ki ceno delnic napoveduje na podlagi tehničnih indikatorjev. Pokažemo še, da je donosnost strategije pogojena z nizkimi transakcijskimi stroški.

Keywords

delnice;finančne časovne vrste;strojno učenje;metoda podpornih vektorjev;učinkovit trg;trgovalna strategija;magisteriji;

Data

Language: Slovenian
Year of publishing:
Typology: 2.09 - Master's Thesis
Organization: UL FE - Faculty of Electrical Engineering
Publisher: [J. Bračun]
UDC: 004.8:336.761.5(043.3)
COBISS: 113725443 Link will open in a new window
Views: 81
Downloads: 37
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: Forecasting stock price movements with support vector machines
Secondary abstract: Autonomous processing of financial data for stock price predictions is widely used by individual investors and corporations. successful forecasting however remains, to a great extent, an unsolved problem. The number of factors that impact stock price formation is large, and far too big, for us to be able to factor them all in. Besides that, there is a widespread theory of efficient markets, that claims that forecasting prices based on publicly available data is not possible, since the price already reflects all publicly known information. There is also a question of how to determine the success of forecasting models. In this master’s thesis, we use support vector machines to predict the daily closing stock price of four American corporations. The models used for forecasting are both classification and regression models, the input variables used are historical price data and technical indicators derived from them. The forecasting ability of the models is then tested and compared to the random walk model, which is considered to be the optimal forecasting model in an efficient market. Given that we operate with financial data, the models are also tested in a simulated trading environment using their predictions in a simple trading strategy. For the analysis, we first look at the error metric between the prices we predict using the regression models and the actual prices. We show that in some cases we produce a smaller error that the random walk model. We then analyze the percent of correctly predicted price movement directions, where we compare all the models and show that only one regression model, does not outperform the random walk model. Finally, we compare the returns and risk-adjusted returns using a trading strategy, by far the best results are shown using the predictions of the regression models based on technical indicators. It is also concluded that the minimization of transaction costs is needed for a profitable trading strategy.
Secondary keywords: stocs;financial time series;machine learning;support vector machine;efficient market;trading strategy;
Type (COBISS): Master's thesis/paper
Study programme: 1000316
Embargo end date (OpenAIRE): 1970-01-01
Thesis comment: Univ. v Ljubljani, Fak. za elektrotehniko
Pages: XVIII, 68 str.
ID: 15822498