Decision support from financial disclosures with deep neural networks and transfer learning

By Mathias Kraus, Stefan Feuerriegel. 2017

299 citations recorded by the source corpus.

Company disclosures greatly aid in the process of financial decision-making; therefore, they are consulted by financial investors and automated traders before exercising ownership in stocks. While humans are usually able to correctly interpret the content, the same is rarely true of computerized decision support systems, which struggle with the complexity and ambiguity of natural language. A possible remedy is represented by deep learning, which overcomes several shortcomings of traditional methods of text mining. For instance, recurrent neural networks, such as long short-term memories, employ hierarchical structures, together with a large number of hidden layers, to automatically extract features from ordered sequences of words and capture highly non-linear relationships such as context-dependent meanings. However, deep learning has only recently started to receive traction, possibly because its performance is largely untested. Hence, this paper studies the use of deep neural networks for financial decision support. We additionally experiment with transfer learning, in which we pre-train the network on a different corpus with a length of 139.1 million words. Our results reveal a higher directional accuracy as compared to traditional machine learning when predicting stock price movements in response to financial disclosures. Our work thereby helps to highlight the business value of deep learning and provides recommendations to practitioners and executives. We apply deep learning for sentiment analysis of financial news.This yields considerable improvements in forecasting the stock price movements.Additional gains stem from applying transfer learning.Long short-term memory performs overall best.Demonstrates the potential for future applications of deep learning in finance

Subfields: Finance, Management Science and Operations Research, Economics & Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Finance

1. M. Ugur Gudelek
2. A. Ozbayoglu
3. Omer Berat Sezer
4. Longbing Cao
5. Dogu Araci
6. Weiwei Jiang

In Management Science and Operations Research

1. M. Ugur Gudelek
2. Omer Berat Sezer
3. A. Ozbayoglu
4. Longbing Cao
5. Dogu Araci
6. Weiwei Jiang

In Economics & Operations Research

1. A. Ozbayoglu
2. M. Ugur Gudelek
3. Dogu Araci
4. Longbing Cao
5. Omer Berat Sezer

Citations in the corpus

• Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019 (2019, background): “Kraus and Feuerriegel [99] implemented LSTM with transfer learning using text mining through financial news and the stock market data.”
• Deep Learning for Financial Applications : A Survey (2020, methodology): “[167] implemented LSTM with transfer learning using text mining through financial news and stock market data.”
• AI in Finance: Challenges, Techniques, and Opportunities (2021, methodology): “Examples are modeling the dependencies between a stock price, market index, foreign currency and derivative market movement and macroeconomic variables such as petrol and gold prices; detecting abnormal market behaviors, anomalies or frauds in corporate finance, accounting, insurance and banking bus”
• FinBERT: Financial Sentiment Analysis with Pre-trained Language Models (2019, methodology): “On of the first papers that used deep learning methods for textual financial polarity analysis was Kraus and Feuerriegel (2017) [7].”
• An Intelligent Approach to Credit Card Fraud Detection Using an Optimized Light Gradient Boosting Machine (2020, background): “Kraus and Feuerriegel [20] utilized deep-learning approaches to support financial decisions.”