Curve fitting refers to the process of finding an appropriate function that fits a finite set of data points. Representing a set of data points by a function is quite beneficial in data analysis and reapplication, and this technique is often used in engineering and technical problems. Fitting accuracy and computational time are usually the most crucial factors to be taken care of in curve fitting problems. Previous researchers have demonstrated that genetic algorithms can effectively solve curve fitting problems, but the difficulty of parameter coding is also widely encountered in computational processes. Hence, this study addresses on applying real-valued genetic algorithm to deal with curve fitting problems. Detailed discussion is made on the optimization efficiency among various data, and finally, some key parameters to curve fitting results are found and presented.