{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/decision-support-from-financial-disclosures","title":"Decision support from financial disclosures with deep neural networks and transfer learning","arxiv_id":"1710.03954","date":"2017-10-11","proceeding":null,"authors":["Mathias Kraus","Stefan Feuerriegel"],"abstract":"Company disclosures greatly aid in the process of financial decision-making;\ntherefore, they are consulted by financial investors and automated traders\nbefore exercising ownership in stocks. While humans are usually able to\ncorrectly interpret the content, the same is rarely true of computerized\ndecision support systems, which struggle with the complexity and ambiguity of\nnatural language. A possible remedy is represented by deep learning, which\novercomes several shortcomings of traditional methods of text mining. For\ninstance, recurrent neural networks, such as long short-term memories, employ\nhierarchical structures, together with a large number of hidden layers, to\nautomatically extract features from ordered sequences of words and capture\nhighly non-linear relationships such as context-dependent meanings. However,\ndeep learning has only recently started to receive traction, possibly because\nits performance is largely untested. Hence, this paper studies the use of deep\nneural networks for financial decision support. We additionally experiment with\ntransfer learning, in which we pre-train the network on a different corpus with\na length of 139.1 million words. Our results reveal a higher directional\naccuracy as compared to traditional machine learning when predicting stock\nprice movements in response to financial disclosures. Our work thereby helps to\nhighlight the business value of deep learning and provides recommendations to\npractitioners and executives.","url_abs":"http://arxiv.org/abs/1710.03954v1","url_pdf":"http://arxiv.org/pdf/1710.03954v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"decision-support-from-financial-disclosures","repo_url":"https://github.com/MathiasKraus/FinancialDeepLearning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"decision-support-from-financial-disclosures","repo_url":"https://github.com/HaiDang9719/MatLabProj","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1710.03954","atlas_url":"https://app.syntology.ai/?focus=1710.03954","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}