Using narrative disclosures to predict tax outcomes
研究了财务报告中的叙述性讨论能否帮助预测公司税收结果，发现定性信息能显著提升预测准确性，且分析师常未有效利用这些信息。
Abstract We examine whether narrative discussion in financial disclosures can help corporate stakeholders better predict tax outcomes. To measure qualitative discussion, we use topic modeling analysis to create measures of the thematic content of 10-K disclosures. We find that qualitative discussion in financial disclosures can substantially improve prediction of tax outcomes in in- and out-of-sample tests. We also find that prediction-relevant discussion is distributed throughout the 10-K, supporting that disclosures should be analyzed holistically rather than examining only limited pieces of larger disclosures. Further, we find that analysts often do not use this information effectively, resulting in predictable and economically meaningful forecast errors. These findings illustrate the wealth of qualitative information in 10-K disclosures for stakeholders concerned about tax outcomes and offer a practical approach to examining qualitative disclosures and using them to predict tax outcomes.