Symbolic Concept Acquisition: A New Approach to Determining Underlying Tax Law Constructs.
本文使用符号概念获取方法分析税务法院判决，通过ACLS程序构建规则解释奖学金或助学金资格的判定，并与判别分析和LOGIT模型比较，发现ACLS规则预测更准确。
Abstract This paper describes the use of symbolic concept acquisition to analyze Tax Court decisions. The Analog Concept Learning System (ACLS) computer program Is used to construct rules that explain the behavior of the Tax Court in determining scholarship or fellowship grant status. The results are compared with those produced by discriminant analysis and LOGIT. This comparison indicates the ACLS rules are more accurate at predicting the outcome of Tax Court decisions for this area of tax law.