A Transformer Architecture for Time-Series Data Applied to Stock-Market Closing-Price Prediction
dc.contributor.author | Sanjay, Rohit Kuruvilla | |
dc.contributor.advisor | Ortiz, Luis | |
dc.date.accessioned | 2024-05-07T14:02:32Z | |
dc.date.issued | 2024-04-27 | |
dc.date.submitted | 2024-03-26 | |
dc.identifier.uri | https://hdl.handle.net/2027.42/193103 | |
dc.description.abstract | The transformer architecture revolutionized natural language processing (NLP) tasks and gavebirth to powerful models such as the generative pre-trained (GPT) model, bidirectional encoderrepresentation from the transformer (BERT), text-to-text transformer. This thesis dives into thisunexplored landscape, investigating the potential of transformer-based models for accuratelypredicting future closing prices of stocks. We propose a novel architecture, derived from theoriginal transformer, specifically crafted for this task. Our approach involves not only building andoptimizing this model but also tuning its hyperparameters for each of the four major stock marketsectors: technology, finance, pharmaceutical, and FMCG (Fast Moving Consumer Goods). Bycarefully tailoring the model to each sector's unique characteristics, we aim to maximize itseffectiveness and capture nuanced market dynamics. Finally, we put our model to the test,evaluating its performance on unseen data against established time series models such as the long-short-term memory (LSTM) network. This comparative analysis will not only reveal the efficacyof our transformer-based approach but also highlight its potential advantages in terms of accuracyand interpretability compared to traditional methods. Through this exploration, we hope toilluminate a promising new avenue for stock price prediction, offering valuable insights toresearchers and investors alike. | en_US |
dc.language.iso | en_US | en_US |
dc.subject | Time Series Data | en_US |
dc.subject | Stock Market Prediction | en_US |
dc.subject | Machine Learning | en_US |
dc.subject | Transformers | en_US |
dc.subject | Transformer-Encoder | en_US |
dc.subject.other | Artificial Intelligence | en_US |
dc.title | A Transformer Architecture for Time-Series Data Applied to Stock-Market Closing-Price Prediction | en_US |
dc.type | Thesis | en_US |
dc.description.thesisdegreename | Master of Science (MS) | en_US |
dc.description.thesisdegreediscipline | Artificial Intelligence, College of Engineering & Computer Science | en_US |
dc.description.thesisdegreegrantor | University of Michigan-Dearborn | en_US |
dc.contributor.committeemember | Abouelenien, Mohamed | |
dc.contributor.committeemember | Da, Srijita | |
dc.identifier.uniqname | rohitsan | en_US |
dc.description.bitstreamurl | http://deepblue.lib.umich.edu/bitstream/2027.42/193103/1/Sanjay_Thesis_Transformer_Architechture.pdf | |
dc.identifier.doi | https://dx.doi.org/10.7302/22748 | |
dc.description.mapping | febc42ae-d444-43ae-98fd-dc98ee638897 | en_US |
dc.identifier.orcid | 0009-0004-2359-7775 | en_US |
dc.description.filedescription | Description of Sanjay_Thesis_Transformer_Architechture.pdf : Thesis | |
dc.working.doi | 10.7302/22748 | en_US |
dc.owningcollname | Dissertations and Theses (Ph.D. and Master's) |
Files in this item
Remediation of Harmful Language
The University of Michigan Library aims to describe library materials in a way that respects the people and communities who create, use, and are represented in our collections. Report harmful or offensive language in catalog records, finding aids, or elsewhere in our collections anonymously through our metadata feedback form. More information at Remediation of Harmful Language.
Accessibility
If you are unable to use this file in its current format, please select the Contact Us link and we can modify it to make it more accessible to you.