We want to model a Markowitz portfolio opti- mization problem by defining the total return R = 1xR; at the end of the next time period, where x; is the proportion of the investment for the j-th asset (or stock), and R; is the return given by this asset. Here, Rj (j=1,...,n) are random variables, which imply that R is also a random variable. The goal is to maximize the expected return E(R) while minimizing the risk. It leads to the following optimization problem: min f(x)=-1X;B(R;) + Var(R) XER s.t. 1 x = 1, x;0, j=1,,n. Here, > 0 is a tuning parameter (given) to trade-off between two objective terms: the expected return E(R), and the variance Var(R) of R. In practice, we cannot compute E(R) and Var(R). Therefore, we replace them by the sample mean R, and the sample covariance S, respectively for a given dataset. The data set Port Select Data.xlsx contains the data (relative return) of 5 US stocks over year from 1975 to 1994. You are asked to perform the following tasks: (a) Compute and S from Port SelectData.xlsx and form the corresponding QP problem for the above portfolio optimization problem. (b) Solve this problem by using quadprog in Matlab, cvxopt in Python, or any QP solver that you know, and interpret your results. You can try different values of 1, e.g., 1 (2, 1, 0.5, 0.25}. Note that you need to print your code, screenshots of the results you ran, and staple them with the solution.