Time series forecasting using a genetically optimized neural network - a comparative study

Postgraduate Thesis uoadl:2918429 191 Read counter

Unit:
Κατεύθυνση Μαθηματικά Χρηματοοικονομικά και Ανάλυση Κινδύνου
Library of the Faculty of Economics and of the Faculty of Business Administration
Deposit date:
2020-07-07
Year:
2020
Author:
Dimou Vasileios
Supervisors info:
Μπασιάκος Ιωάννης, Αναπληρωτής Καθηγητής, Διευθυντής Τομέα VII
Original Title:
Time series forecasting using a genetically optimized neural network - a comparative study
Languages:
English
Translated title:
Time series forecasting using a genetically optimized neural network - a comparative study
Summary:
Utilization of a genetic algorithm for hyper-parameter optimization of a neural network architecture with the intent to implement the model for financial time series forecasting. The model was compared with other widely used techniques from traditional statistics.
Main subject category:
Social, Political and Economic sciences
Keywords:
time series forecasting, neural networks, genetic algorithms, machine learning
Index:
No
Number of index pages:
0
Contains images:
Yes
Number of references:
10
Number of pages:
105
File:
File access is restricted only to the intranet of UoA.

Thesis final draft.pdf
4 MB
File access is restricted only to the intranet of UoA.