University of Twente Student Theses


Machine Learning for Exchange Traded Fund Price Predictions

Horst, Jonas ter (2022) Machine Learning for Exchange Traded Fund Price Predictions.

[img] PDF
Abstract:The financial industry has long made use of machine learning techniques to predict stock prices or price trends. This research paper will focus specifically on exchange traded funds (ETFs) and the usage of machine learning techniques, like feed-forward neural networks, to predict their prices. A machine learning model will be developed to predict if a specific ETF price will go up or down and then predict the actual price. The model is a long short-term memory (LSTM) network, which is a type of feed forward neural network that is often applied to sequence prediction problems, like stock market forecasts. This research is new and relevant to the field because data and information from other ETFs are used to predict ETF prices and comes to the conclusion that there is not one universal set of ETFs that can be included to achieve better forecasting results. There are business sector-specific differences in the accuracy of the results. The results of this model can be used in a variety of different fields, like consultancy firms, but also by private investors.
Item Type:Essay (Bachelor)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:54 computer science, 85 business administration, organizational science
Programme:Business & IT BSc (56066)
Link to this item:
Export this item as:BibTeX
HTML Citation
Reference Manager


Repository Staff Only: item control page