| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

First page > Show document

Show document

Title:	Razvoj napovednega modela za trgovanje z delniškimi vrednostnimi papirji na slovenskem borznem trgu
Authors:	ID Cimperman, Primož (Author) ID Kljajić Borštnar, Mirjana (Mentor) More about this mentor...
Files:	MAG_Cimperman_Primoz_2018.pdf (2,55 MB) MD5: 0915D7E4C353C4EBFEE4AC072BEBE964 PID: 20.500.12556/dkum/4f49cfe5-84c1-4de5-a300-005b215e2d82
Language:	Slovenian
Work type:	Master's thesis/paper
Organization:	FOV - Faculty of Organizational Sciences in Kranj
Abstract:	Vpetost informacijsko-komunikacijske tehnologije v vsakdanje življenje je povzročila množično zbiranje, shranjevanje in obdelovanje podatkov, iz katerih se pridobivajo različne informacije, ki jih človek spretno uporablja pri vsakdanjih odločitvah tako doma kot na preostalih področjih svojega delovanja. Ob njihovi uporabi mora pri tem oceniti njihovo korist oziroma morebitno tveganje, ki jih pridobljena informacija prinaša. Podobno to velja tudi za trgovanje z vrednostnimi papirji na borzi, saj je primerno za lažjo odločitev o nakupu oziroma prodaji uporabiti določene pripomočke, ki so zasnovani v obliki programskih orodij. Ta nam na podlagi izbranega seta podatkov določene delnice izvajajo simulacije o potencialnem gibanju tečajnih vrednosti v prihodnosti. V magistrskem delu smo izdelali več napovednih modelov, pri katerih smo uporabili različne metode napovedovanja, ki se pogosto uporabljajo pri analizah gibanja tečajnih vrednosti delnic. Z metodologijo CRISP-DM smo razvili štiri napovedne modele, ki se med seboj razlikujejo tako po uporabljeni metodi kot tudi po primernosti časovnega obdobja napovedovanja. Z ocenami posameznih modelov na izbranih delnicah smo prišli do različnih ugotovitev, ki so nam podale širšo sliko o tem, kakšne so prednosti in slabosti posameznih modelov ter kateri model se je izkazal za najučinkovitejšega pri napovedovanju gibanja tečajev delnic. S pridobljenimi spoznanji si lahko pomagamo pri odločanju, ki zadeva borzno trgovanje na primeru izbranih delnic.
Keywords:	odkrivanje znanja v podatkih, strojno učenje, podatkovno rudarjenje, metoda podpornih vektorjev, logistična regresija, trg vrednostnih papirjev.
Place of publishing:	Maribor
Year of publishing:	2018
PID:	20.500.12556/DKUM-70352
COBISS.SI-ID:	8024851
NUK URN:	URN:SI:UM:DK:SWOVCL2Z
Publication date in DKUM:	05.06.2018
Views:	1625
Downloads:	145
Metadata:
Categories:	FOV
:	Copy citation

Average score:	(0 votes)
Your score:	Voting is allowed only for logged in users.
Share:

Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:	CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International

Link:	http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:	The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Licensing start date:	05.05.2018

Secondary language

Language:	English
Title:	The development of predictive model for trading with securities on the slovenia stock market
Abstract:	The integration of information and communication technology into everyday life has resulted in the massive collection, storage and processing of data from which various information is acquired, which human skillfully uses in everyday decisions at home and in other areas of work. At the time of their use, however, they must evaluate their benefit or the potential risk that the acquired information brings. Similarly, this also applies to securities trading on the stock exchange, since it is appropriate to use certain utilities that are designed in the form of software tools to facilitate the decision to buy or sell. With the help of a selected set of data, the latter provides us with simulations about the future movement of exchange rates in the future. In the master's thesis, we produced several predictive models in which we used different predictive methods, which are often used in the analysis of movements in exchange rates of shares. With the CRISP-DM methodology we developed four predictive models that differ in each other according to the method used and the suitability of the prediction time period. With the help of estimates of individual models on selected shares, we have come up with various findings that gave us a wider picture of the advantages and disadvantages of individual models and which model proved to be most effective in predicting the movement of share prices. The lessons learned can serve as a decision-making tool in the area of stock exchange trading in the case of selected shares.
Keywords:	Knowledge discovery from data, Machine learning, Data mining, Support vector machines, Logistic Regression, Securities market

Comments

Leave comment

You must log in to leave a comment.

Comments (0)

0 - 0 / 0

There are no comments!

Back

Logos of partners