{"id":{"repo_id":"utahstate","oai_identifier":"oai:digitalcommons.usu.edu:etd-9550"},"canonical_url":"https://search.ndltd.org/etd/utahstate/oai:digitalcommons.usu.edu:etd-9550","repository":{"repo_id":"utahstate","name":"Utah State University","base_url":"https://digitalcommons.usu.edu/do/oai/"},"display":{"title":"Artificial Intelligence and Deep Reinforcement Learning Stock Market Predictions","abstract":"Billions of dollars are traded automatically in the stock market every day, including algorithms that use artificial intelligence (AI) techniques, but there are still questions regarding how AI trades successfully. The black box nature of these AI techniques, namely neural networks, gives pause to entrusting it with valuable trading funds. This dissertation applies AI techniques to stock market trading strategies, but it also provides exploratory research into how these techniques predict the stock market successfully. This dissertation presents the work of three research papers. The first paper presented in this dissertation applies a artificial intelligence technique, reinforcement learning, to candlestick pattern trading. This paper also analyzes how the DDQN trades, through the use of a more recent technique, feature map visualizations. The second and third paper analyze AI techniques in a pairs trading strategy. The first paper results show that the DDQN is able to outperform the S&P 500 Index returns. Results also show that the CNN is able to switch its attention from all the candles in a candlestick image to the more recent candles in the image, based on an event such as the coronavirus stock market crash of 2020.The second paper results show fuzzy logic applied to pairs trading strategy for 22 stock pairs, increases annual returns on average from 15% to 17%. The third paper results show a DDQN was able to accurately predict the spread of the Adobe/Red Hat pair, for positive returns. This dissertation shows that AI techniques are successful in predicting the stock market, but more importantly it provides research tools and methods to better understand and implement these techniques in stock market trading.","abstract_html":"Billions of dollars are traded automatically in the stock market every day, including algorithms that use artificial intelligence (AI) techniques, but there are still questions regarding how AI trades successfully. The black box nature of these AI techniques, namely neural networks, gives pause to entrusting it with valuable trading funds. This dissertation applies AI techniques to stock market trading strategies, but it also provides exploratory research into how these techniques predict the stock market successfully. This dissertation presents the work of three research papers. The first paper presented in this dissertation applies a artificial intelligence technique, reinforcement learning, to candlestick pattern trading. This paper also analyzes how the DDQN trades, through the use of a more recent technique, feature map visualizations. The second and third paper analyze AI techniques in a pairs trading strategy. The first paper results show that the DDQN is able to outperform the S&amp;P 500 Index returns. Results also show that the CNN is able to switch its attention from all the candles in a candlestick image to the more recent candles in the image, based on an event such as the coronavirus stock market crash of 2020.The second paper results show fuzzy logic applied to pairs trading strategy for 22 stock pairs, increases annual returns on average from 15% to 17%. The third paper results show a DDQN was able to accurately predict the spread of the Adobe/Red Hat pair, for positive returns. This dissertation shows that AI techniques are successful in predicting the stock market, but more importantly it provides research tools and methods to better understand and implement these techniques in stock market trading.","abstract_has_math":false,"creators":["Brim, Andrew W."],"institution":"Hosted by Utah State University Libraries","degree_name":"Doctor of Philosophy (PhD)","degree_level":"Dissertation","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Nicholas Flann","Vicki H. Allan","Tyler Brough"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T08:52:42Z","subjects":["Artificial Intelligence","Reinforcement Learning","Deep Q-networks","Stock Market Predictions","Computer Sciences"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.26076/3334-5b98"],"render_values":[{"text":"https://doi.org/10.26076/3334-5b98","href":"https://doi.org/10.26076/3334-5b98","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.usu.edu/etd/8393","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.usu.edu/etd/8393","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.usu.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.usu.edu%3Aetd-9550","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Nicholas Flann","Vicki H. Allan","Tyler Brough"]},{"key":"dc:creator","label":"Author","values":["Brim, Andrew W."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2010-01-01T08:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2022-05-01T07:00:00Z"]},{"key":"dc:publisher","label":"Institution","values":["Hosted by Utah State University Libraries"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy (PhD)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Artificial Intelligence","Reinforcement Learning","Deep Q-networks","Stock Market Predictions","Computer Sciences"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.usu.edu/etd/8393"]},{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.26076/3334-5b98"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Billions of dollars are traded automatically in the stock market every day, including algorithms that use artificial intelligence (AI) techniques, but there are still questions regarding how AI trades successfully. The black box nature of these AI techniques, namely neural networks, gives pause to entrusting it with valuable trading funds. This dissertation applies AI techniques to stock market trading strategies, but it also provides exploratory research into how these techniques predict the stock market successfully. This dissertation presents the work of three research papers. The first paper presented in this dissertation applies a artificial intelligence technique, reinforcement learning, to candlestick pattern trading. This paper also analyzes how the DDQN trades, through the use of a more recent technique, feature map visualizations. The second and third paper analyze AI techniques in a pairs trading strategy. The first paper results show that the DDQN is able to outperform the S&P 500 Index returns. Results also show that the CNN is able to switch its attention from all the candles in a candlestick image to the more recent candles in the image, based on an event such as the coronavirus stock market crash of 2020.The second paper results show fuzzy logic applied to pairs trading strategy for 22 stock pairs, increases annual returns on average from 15% to 17%. The third paper results show a DDQN was able to accurately predict the spread of the Adobe/Red Hat pair, for positive returns. This dissertation shows that AI techniques are successful in predicting the stock market, but more importantly it provides research tools and methods to better understand and implement these techniques in stock market trading."]},{"key":"dc:title","label":"Title","values":["Artificial Intelligence and Deep Reinforcement Learning Stock Market Predictions"]}]}],"canonical_facts":{"dc:contributor":["Nicholas Flann","Vicki H. Allan","Tyler Brough"],"dc:creator":["Brim, Andrew W."],"dc:date.available":["2010-01-01T08:00:00Z"],"dc:date.created":["2022-05-01T07:00:00Z"],"dc:description.abstract":["Billions of dollars are traded automatically in the stock market every day, including algorithms that use artificial intelligence (AI) techniques, but there are still questions regarding how AI trades successfully. The black box nature of these AI techniques, namely neural networks, gives pause to entrusting it with valuable trading funds. This dissertation applies AI techniques to stock market trading strategies, but it also provides exploratory research into how these techniques predict the stock market successfully. This dissertation presents the work of three research papers. The first paper presented in this dissertation applies a artificial intelligence technique, reinforcement learning, to candlestick pattern trading. This paper also analyzes how the DDQN trades, through the use of a more recent technique, feature map visualizations. The second and third paper analyze AI techniques in a pairs trading strategy. The first paper results show that the DDQN is able to outperform the S&P 500 Index returns. Results also show that the CNN is able to switch its attention from all the candles in a candlestick image to the more recent candles in the image, based on an event such as the coronavirus stock market crash of 2020.The second paper results show fuzzy logic applied to pairs trading strategy for 22 stock pairs, increases annual returns on average from 15% to 17%. The third paper results show a DDQN was able to accurately predict the spread of the Adobe/Red Hat pair, for positive returns. This dissertation shows that AI techniques are successful in predicting the stock market, but more importantly it provides research tools and methods to better understand and implement these techniques in stock market trading."],"dc:identifier":["https://digitalcommons.usu.edu/etd/8393"],"dc:identifier.doi":["https://doi.org/10.26076/3334-5b98"],"dc:publisher":["Hosted by Utah State University Libraries"],"dc:subject":["Artificial Intelligence","Reinforcement Learning","Deep Q-networks","Stock Market Predictions","Computer Sciences"],"dc:title":["Artificial Intelligence and Deep Reinforcement Learning Stock Market Predictions"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Doctor of Philosophy (PhD)"]},"updated_at":"2026-11-19T08:52:42Z"}