Forecasting Earnings Using k-Nearest Neighbors

• 成果类型: Article
• 署名作者: Easton, Peter D.; Kapons, Martin M.; Monahan, Steven J.; Schutt, Harm H.; Weisbrod, Eric H.
• 署名单位: University of Notre Dame; University of Amsterdam; Utah System of Higher Education; University of Utah; Tilburg University; University of Kansas
• 刊物名称: ACCOUNTING REVIEW
• ISSN/ISSBN: 0001-4826
• DOI: 10.2308/TAR-2021-0478
• 发表日期: 2024
• 页码: 115-140
• 关键词: time-series properties; IMPLIED COST; models; performance

摘要

We use a simple k -nearest neighbors algorithm (hereafter, k -NN*) to forecast earnings. k -NN* forecasts of one-, two-, and three -year -ahead earnings are more accurate than those generated by popular extant forecasting approaches. k -NN* forecasts of two- and three-year (one -year) -ahead EPS and aggregate three-year EPS are more (less) accurate than those generated by analysts. The association between the unexpected earnings implied by k -NN* and the contemporaneous market -adjusted return (i.e., the earnings association coefficient (EAC)) is positive and exceeds the EAC on unexpected earnings implied by alternate approaches. A trading strategy that is long (short) firms for which k -NN* predicts positive (negative) earnings growth earns positive risk -adjusted returns that exceed those earned by similar trading strategies that are based on alternate forecasts. The k -NN* algorithm generates an empirically reliable ex ante indicator of forecast accuracy that identifies situations when the k -NN* EAC is larger and the k -NN* trading strategy is more profitable.