The objective of this thesis is to determine if data mining tools can directlyimprove audit performance. The selected test area was the sample selection step of thetest of control process. The research data was based on accounting transactionsprovided by AVH PricewaterhouseCoopers Oy. Various samples were extracted fromthe test data set using data mining software and generalized audit software and theresults evaluated. IBM's DB2 Intelligent Miner for Data Version 6 was selected torepresent the data mining software and ACL for Windows Workbook Version 5 waschosen for generalized audit software.Based on the results of the test and the opinions solicited from experiencedauditors, the conclusion is that, within the scope of this research, the results of datamining software are more interesting than the results of generalized audit software.However, there is no evidence that the data mining technique brings out materialmatters or present significant enhancement over the generalized audit software. Furtherstudy in a different audit area or with a more complete data set might yield a differentconclusion.