Choosing a research acceptance rule
Question
Design a predeclared rule for deciding whether an ML signal merits a controlled live trial after backtesting.
Short answer
Specify the target, data availability, training procedure, evaluation periods, net-cost model, risk limits and minimum evidence before inspecting final results. Include stability, concentration, capacity and uncertainty criteria rather than a single Sharpe cutoff. Define prospective monitoring and stop conditions, with limits on capital and operational exposure. Record how many variants were tested and who reviews failures. The rule must match the organisation's risk tolerance; no universal numerical threshold is sufficient.
Original question and answer written by SelfMadeQuant.com.
See the hint and the full worked solution in the question bank (free account).
Open the worked solution