Solver equivalent function or regression technique

I am relatively new to MATLAB. I have the following problem that I am trying to solve:

I have a matrix of 1000 x 12, comprising of -1,0,1. I have response variable that are % Returns of a stock market. What I would like to do is find the weights of those 12 variables that gives me best explanatory power. The way I perceive it there could be two solutions:

1, ANOVA analysis - given all independent variables are categorical and response variable is continuous. 2, Run a Solver system to find optimal weights that I can assign to those variables to compute "Composite score" and try to minimize the sum of squares between "Composite Score" & Response variable.

I already did the second part in Excel, using Solver, but I am wondering what is similar way to do it in MATLAB.

Please let me know if I need further clarification or would like to look at the data.

Thank you very much