The invention relates to the technical field of the expansion of the optimal payment channel of users, in particular to a method and a system for expanding an optimal payment channel on the basis of a big-data regression analysis algorithm. The method comprises the following steps: reading stored power utilization department characteristic data from a big-data distributed database; carrying out regression analysis calculation in a Map function to obtain the payment positions and the payment modes, which exist in a numerical value form, of various different users; carrying out numerical value merging normalization calculation on calculation results under a Reduce function; calculating a sum Q value of squares of deviations, comparing the sum Q value of squares of deviations with a given threshold value, and judging whether the sum Q value of squares of deviations is smaller than the given threshold value or not; and if the sum Q value of squares of deviation is smaller than the threshold value, ending. The method and the system utilize the improved regression analysis algorithm of a big-data platform to carry out concurrent analysis on mass user payment data, analysis efficiency is high, the behavior habits of the electric charge payment of the user can be accurately calculated, and the optimal investment analysis of the expansion of the payment channel of power enterprises is realized.