Íslenskur hlutabréfamarkaður hefur ákveðna sérstöðu vegna smæðar sinnar og takmarkaðra fjölda breytna sem hafa áhrif á hann í samanburði við erlenda markaði. Í verkefninu er gerð tilraun til þess að nota marglagskipt skynjunarnet (MLP tauganet) til spákaupa á íslenskum hlutabréfamarkaði með því að nota einungis söguleg gögn til þjálfunar. Rannsakað var einnig hvort tenging gæti verið milli velgengni tauganetanna á prófunartímabili og merkjafræðilegra eiginleika hlutabréfaverðs, svo sem aflrófsþéttleika og sjálffylgni. Notast var við tvö mismunandi tauganet, annars vegar var hannað einfalt MLP tauganet sem flokkaði útkomur hlutabréfaverðs í tvo flokka, hækkun- og lækkun hlutabréfaverðs. Hins vegar var notast við sérstakan hugbúnað við þróun ...
With the rapid development of technology in the world in recent years, many innovations have emerged...
Disertacijoje nagrinėjamos terminių srautų paieškos ir prognozavimo autonominio orlaivio skrydžio me...
Deep learning and neural networks has recently become a powerful tool to solve complex problem due t...
Neural networks have been applied as forecasting models in multiple studies to predict stock prices ...
This study is about prediction of the stockmarket through a comparison of neural networks and statis...
Ursprungligen fungerade aktier som ett medel för företag att säkerställa finansiering för nya satsni...
ARTIFICIAL NEURAL NETWORKS IN TECHNICAL ANALYSIS AND APPLICATIONWith the recent improvements in scie...
The idea of predicting the stock market has existed for hundreds of years. From the pre-industrial a...
This paper explores the viability of creating an artificial neural network for stock forecasting usi...
This thesis investigates how neural networks can be used to produce investors' views for the Black-L...
YÖK Tez No: 578499Konutlar insanların barınma ihtiyaçlarını karşılayan taşınmazlardır. Günümüzde üre...
Šajā darbā ir aprakstīti neironu tīkli un to izmantošana valūtu kursu prognozēšanas uzdevuma risināš...
This study investigates a neural networks approach to portfolio choice. Linear regression models are...
Empirical asset pricing literature has widely recognised different factors and they are a well resea...
This study investigates the predictive performance of two different machine learning (ML) models on ...
With the rapid development of technology in the world in recent years, many innovations have emerged...
Disertacijoje nagrinėjamos terminių srautų paieškos ir prognozavimo autonominio orlaivio skrydžio me...
Deep learning and neural networks has recently become a powerful tool to solve complex problem due t...
Neural networks have been applied as forecasting models in multiple studies to predict stock prices ...
This study is about prediction of the stockmarket through a comparison of neural networks and statis...
Ursprungligen fungerade aktier som ett medel för företag att säkerställa finansiering för nya satsni...
ARTIFICIAL NEURAL NETWORKS IN TECHNICAL ANALYSIS AND APPLICATIONWith the recent improvements in scie...
The idea of predicting the stock market has existed for hundreds of years. From the pre-industrial a...
This paper explores the viability of creating an artificial neural network for stock forecasting usi...
This thesis investigates how neural networks can be used to produce investors' views for the Black-L...
YÖK Tez No: 578499Konutlar insanların barınma ihtiyaçlarını karşılayan taşınmazlardır. Günümüzde üre...
Šajā darbā ir aprakstīti neironu tīkli un to izmantošana valūtu kursu prognozēšanas uzdevuma risināš...
This study investigates a neural networks approach to portfolio choice. Linear regression models are...
Empirical asset pricing literature has widely recognised different factors and they are a well resea...
This study investigates the predictive performance of two different machine learning (ML) models on ...
With the rapid development of technology in the world in recent years, many innovations have emerged...
Disertacijoje nagrinėjamos terminių srautų paieškos ir prognozavimo autonominio orlaivio skrydžio me...
Deep learning and neural networks has recently become a powerful tool to solve complex problem due t...