CAtt is a new method for attributing performance exactly to the signals and constraints that drive optimization-based investment strategies. Quantitative portfolio managers seek this type of attribution because signals, signal weights, and constraints are the essential inputs to the investment process. Catt delivers complete and exact attribution to quantitative management decisions. It achieves this by taking a different approach.
- exploits the manager’s complete knowledge of the quantitative process
- explicitly tracks the dynamics induced by turnover control and prior signals
- and thereby avoids residuals, model error and multi-collinearity