Ensemble Learning Applied to Quant Equity: Gradient Boosting in a Multifactor Framework

摘要: This chapter proposes to benefit from the advantages of machine learning (ML) in general and boosted trees particular, e.g. non‐linearity, regularization good generalization results, scaling up well with lots data. It gives a mildly technical introduction trees. The introduces construction dataset feature labels engineering, calibration ML applying rigorous protocol established by computer science community. describes data used empirical for model. also concept confusion matrix all related metrics order precisely assess model's quality. provides guidance on how tune, train test an ML‐based model using traditional financial characteristics such as valuation profitability metrics, but price momentum, risk estimates, volume liquidity characteristic.