Weighting Analyst Earnings Forecasts to Build Consensus Alpha Factors
Summary
This Chinese-language research summary explains how to estimate consensus net profit from analyst forecasts and turn that estimate into equity-selection signals. It proposes weighting forecasts by report recency and by each analyst’s prior adjusted forecast error. The error measure is regression-adjusted for factors such as forecast horizon, company size, and industry. When a company has issued an earnings preview or flash report, that company disclosure takes precedence over analyst estimates.
Derived signals include forward and rolling earnings yields, expected profit growth, PEG, changes in valuation, and valuation percentiles. The summary reports that backtests across several stock universes found useful selection performance and some incremental independence among signals, citing information-coefficient figures for selected measures. For missing forecasts, it estimates industry growth rank from the company’s prior-year position and uses that to fill expected profit. The supplied text is only a summary; it omits full formulas, test design, and details needed to assess robustness or avoid look-ahead bias.
Key ideas
- Analyst consensus net profit can be weighted by forecast recency and adjusted analyst-specific historical errors.
- Company earnings previews or flash reports are treated as more reliable than analyst estimates when available.
- Expected earnings estimates can generate valuation, growth, PEG, and valuation-change factors.
- For missing forecasts, the method imputes expected growth using the company’s prior industry growth percentile.
- The reported backtest results are summarized without full formulas or enough detail to assess robustness.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.