ABSTRACT We use machine learning for relative valuation and peer firm selection. In out‐of‐sample tests, our machine learning models substantially outperform traditional models in valuation accuracy. This outperformance persists over time and holds across different types of firms. The valuations produced by machine learning models behave like fundamental values. Overvalued stocks decrease in price and undervalued stocks increase in price in the following month. Determinants of valuation multiples identified by machine learning models are consistent with theoretical predictions derived from a discounted cash flow approach. Profitability ratios, growth measures, and efficiency ratios are the most important value drivers throughout our sample period. We derive a novel method to express valuation multiples predicted by our machine learning models as weighted averages of peer firm multiples. These weights are a measure of peer–firm comparability and can be used for selecting peer‐groups.

We consolidate a large number of mean-significant anomalies into cluster portfolios. More than a third of cluster portfolios remain significant under the Hou et al. (2020) five-factor model — the best performing among six benchmark models tested. A best-first search yields nine factors that subsume all cluster portfolios as well as all significant anomalies, demonstrating the feasibility of a parsimonious description of average realised returns. The expected growth factor (EG) and a cluster portfolio linked to accruals are prominent factors that improve pricing performance. The search-generated model produces a monthly maximum squared Sharpe ratio of 0.51, considerably higher than current benchmark models.