Name
Abstract | ||
|---|---|---|
This paper explores the possibility of sharing contemporaneous firm-level information within an audit firm in a privacy-preserving manner. We develop a number of sharing schemes for utilizing contemporaneous accounting information from peer companies without violating clients' confidentiality and observe significant improvements in both estimation accuracy and error detection performance. To satisfy different levels of privacy protection, we propose different sharing schemes by utilizing auditors' self-generated expectations, and the results show that the benefits to auditors from only sharing self-generated estimation residuals (errors) are comparable to that from sharing predicted or actual accounting numbers. To satisfy stricter privacy concerns, we also propose a series of schemes based on sharing categorical information derived from prediction errors. Finally, we use Borda counts to analyze how the choice of the best model changes depending on the cost of errors within different experimental settings. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.2308/ISYS-2020-017 | JOURNAL OF INFORMATION SYSTEMS |
Keywords | DocType | Volume |
audit analytical procedures, data privacy, peer-based approach | Journal | 35 |
Issue | ISSN | Citations |
2 | 0888-7985 | 0 |
PageRank | References | Authors |
0.34 | 0 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Alexander Kogan | 1 | 0 | 0.34 |
| Cheng Yin | 2 | 0 | 0.68 |