The research on financial distress and corporate technical strength has always been a hot topic. Financial distress prediction mainly based on accounting features, but these features only provide a snapshot of prior status. The technical strength is seen as a factor with long-term effects on the corporate performance. While most of the existing studies measure the technical strength by a series of technical features from patents, these features mainly focus on statistical features and ignore the rich technical information contained in the patent texts. Using multi natural language processing methods (i.e., Bert, text matching, document similarity calculation), this paper proposes a framework for mining technical features in patent texts for financial distress prediction. The results of empirical evaluation not only confirm that the patent includes incremental information related to financial distress, but also verify the statistical significance of the technical features constructed in this paper.
Jiang, Cuiqing; Zhou, Yiru; and Chen, Bo, "Mine Technical Information for Financial Distress Prediction" (2022). PACIS 2022 Proceedings. 145.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.