||In this thesis, we combine the stock ranking method with the trading signals generated by Lee et al. and the portfolio redemption scheme proposed by Tsai et al. to form a stock investment method with portfolio management.|
To find significant technical indicators for ranking stocks, we first calculate Pearson's product moment correlation coefficient of several technical indicators and the one-day-ahead returns. We find that the technical indicators RSI, CMO, MOM, BIAS, OSC, TAPI, and MACD are significant.
Three weighting methods W^((1)), W^((2)) and W^((3)) are used to weight these significant indicators. To get stable weight functions, the data of every three years are divided into the weighting interval (first year), aggregating interval (second year) and testing interval (third year). The weighting interval is used for calculating the weights of the indicators within a group; the aggregating interval is used for calculating the aggregative weight of each group of indicators; the testing interval is used to calculate the investment return of the portfolio.
Our weighting interval starts from 1995/1/5 and ends on 2013/12/31, and we start trading from 2002/1/4 until 2015/12/31. The average annualized return of our method is 15.79% with the weight combination (W^((1) ),W^((1) )). Furthermore, if the portfolio size and the redemption threshold are confined to 3 ≤ P ≤ 10 and 40% ≤ T ≤ 80%, respectively, the average annualized return is 18.52%, which is better than the annualized returns of the buy-and-hold strategy (9.26%) and Lee's method (11.05%).
Keywords: technical indicator, correlation coefficient, portfolio redemption, significant, weighting, stock investment