TY - JOUR
T1 - Predicting shareholder litigation on insider trading from financial text
T2 - An interpretable deep learning approach
AU - Liu, Rong
AU - Mai, Feng
AU - Shan, Zhe
AU - Wu, Ying
N1 - Publisher Copyright:
© 2020
PY - 2020/12
Y1 - 2020/12
N2 - The detrimental effects of insider trading on the financial markets and the economy are well documented. However, resource-constrained regulators face a great challenge in detecting insider trading and enforcing insider trading laws. We develop a text analytics framework that uses machine learning to predict ex-ante potentially opportunistic insider trading (using actual insider trading allegation by shareholders as the proxy) from corporate textual disclosures. Distinct from typical black-box neural network models, which have difficulty tracing a prediction back to key features, our approach combines the predictive power of deep learning with attention mechanisms to provide interpretability to the model. Further, our model utilizes representations from a business proximity network and incorporates the temporal variations of a firm's financial disclosures. The empirical results offer new insights into insider trading and provide practical implications. Overall, we contribute to the literature by reconciling performance and interpretability in predictive analytics. Our study also informs the practice by proposing a new method for regulators to examine a large amount of text in order to monitor and predict financial misconduct.
AB - The detrimental effects of insider trading on the financial markets and the economy are well documented. However, resource-constrained regulators face a great challenge in detecting insider trading and enforcing insider trading laws. We develop a text analytics framework that uses machine learning to predict ex-ante potentially opportunistic insider trading (using actual insider trading allegation by shareholders as the proxy) from corporate textual disclosures. Distinct from typical black-box neural network models, which have difficulty tracing a prediction back to key features, our approach combines the predictive power of deep learning with attention mechanisms to provide interpretability to the model. Further, our model utilizes representations from a business proximity network and incorporates the temporal variations of a firm's financial disclosures. The empirical results offer new insights into insider trading and provide practical implications. Overall, we contribute to the literature by reconciling performance and interpretability in predictive analytics. Our study also informs the practice by proposing a new method for regulators to examine a large amount of text in order to monitor and predict financial misconduct.
KW - Attention models
KW - Deep learning
KW - Insider trading
KW - Predictive analytics
KW - Text mining
UR - http://www.scopus.com/inward/record.url?scp=85097082200&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85097082200&partnerID=8YFLogxK
U2 - 10.1016/j.im.2020.103387
DO - 10.1016/j.im.2020.103387
M3 - Article
AN - SCOPUS:85097082200
SN - 0378-7206
VL - 57
JO - Information and Management
JF - Information and Management
IS - 8
M1 - 103387
ER -