University of Twente Student Theses
Graph generation for synthetic stock data
Reus, M.B.C. (2023) Graph generation for synthetic stock data.
|
PDF
1MB |
| Abstract: | There will always be a finite amount of time over which stocks have been recorded. Therefore, synthetic stock data create fabricated timelines where investment strategies can be tested and enhanced. I investigate how graph generation can assist in generating synthetic stock data. Graphs are used to understand how objects like computers, people, molecules or companies are related. In this work, I use graphs to connect companies with similar stock data in a company correlation graph. The graphs will be encoded as a sequence, to allow a recurrent neural network to be trained and generate new graphs. In turn, such graphs can be used to make predictions about the future stock values. My results show that this model can generate company correlation graphs similar to the original data set. This approach is the first to use graph generation for synthetic stock data. |
| Item Type: | Essay (Bachelor) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science |
| Programme: | Electrical Engineering BSc (56953) |
| Link to this item: | https://purl.utwente.nl/essays/96239 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page