Search

• A convolutional recurrent neural network is used to predict firms' default risk. • Both structured and unstructured data of the firms' annual reports are employed. • The unstructured data improves prediction accuracy, especially auditors' reports. • Auditors' reports of large firms are in particular informative. Corporate distress models are central to regulators and financial institutions that need to evaluate the default risk of corporate firms. They are traditionally only based on the numerical financial variables in the firms' annual reports. In this paper we develop a model that employs the unstructured textual data in the reports as well, namely the auditors' reports and managements' statements. Our model consists of a convolutional recurrent neural network which, when concatenated with the numerical financial variables, learns a descriptive representation of the text that is suited for corporate distress prediction. We find that the unstructured data provides a statistically significant enhancement of the distress prediction performance, in particular for large firms where accurate predictions are of the utmost importance. Furthermore, we find that auditors' reports are more informative than managements' statements and that a joint model including both managements' statements and auditors' reports displays no enhancement relative to a model including only auditors' reports. Our model demonstrates a direct improvement over existing state-of-the-art models in the field of distress modelling. [ABSTRACT FROM AUTHOR]

In an attempt to devise new antimicrobial treatments for biofilm infections, the bacterial cell–cell communication system termed quorum sensing has emerged as an attractive target. It has proven possible to intercept the communication system by synthetic non-native ligands and thereby lower the pathogenesis and antibiotic tolerance of a bacterial biofilm. To identify the structural elements important for antagonistic or agonistic activity against the Pseudomonas aeruginosa LasR protein, we report the synthesis and screening of new triazole-containing mimics of natural N -acyl homoserine lactones. A series of azide- and alkyne-containing homoserine lactone building blocks was used to prepare an expanded set of 123 homoserine lactone analogues through a combination of solution- and solid-phase synthesis methods. The resulting compounds were subjected to cell-based quorum sensing screening assays, thereby revealing several bioactive compounds, including 13 compounds with antagonistic activity and 9 compounds with agonistic activity. [ABSTRACT FROM AUTHOR]