The mean-variance approach to portfolio optimization subject to transaction costs

Transaction costs are a source of concern for portfolio managers. Due to nonlinearity of the cost function, the ordinary quadratic programming solution technique cannot be applied. This paper addresses the portfolio optimization problem subject to transaction costs. The transaction cost is assumed to be a V-shaped function of difference between an existing and new portfolio. A nonlinear programming solution technique is used to solve the proposed problem. The portfolio optimization system called POSTRAC (Portfolio Optimiztion System with TRAnsaction Costs) is proposed. The experimental analysis indicates that ignoring the transaction costs results in inefficient portfolios. It is also shown that there does not exist statistically significant difference in portfolio performance with differnt methods to estimate the expected return of securities, when considering the transaction costs into the portfolio return.