Recursive algorithms for trailing stop: Stochastic approximation approach (Q711707)

The purpose of this paper is to study optimal trailing stops. Trailing stops are often used in stock trading to limit the maximum of a possible loss and to lock in a profit. Decision in selling a stock is crucial in successful investing in equity markets where the selling strategy can be determined by either a target level or a stop-loss limit. The authors focus on the stop-loss side of the problem. They develop stochastic approximation algorithms to recursively estimate the optimal trailing stop percentage. Convergence of the algorithm is obtained and interval estimates are constructed. In order to compare this algorithm with Monte Carlo methods, the authors use simulation examples. Finally, to demonstrate the feasibility and efficiency of the algorithms, numerical experiments and real market data are given.