Since fare discounts have been regarded as an effective economical measure to increase passenger flow, it is helpful for local governments and transit operators to understand its impact on ridership. Taking Xiamen, China, as an example, this study uses transaction data to analyze the changes of weekday daily metro ridership after the opening of Xiamen Metro Line 1. At the initial stage of operation of Xiamen Metro Line 1, there are three preferential schemes: discount per trip, money reduced per trip, and discount after reaching the accumulated fare. Therefore, the algorithm of the iterated cumulative sums of squares is introduced to identify structural change points of the time series of daily ridership, which varies according to the type of ticket. The effects of different fare discounts on total ridership and ridership varied by ticket types are analyzed by the regression discontinuity method. The results show that the dates of structural change points are well-matched with the start and end dates of preferential schemes. Each preferential scheme has its own benefited groups. During the fare discount period, the number of passengers gradually increased. But after the cancellation of the favorable preferential scheme, the number of passengers decreased sharply. By understanding the impact of fare discounts on ridership in Xiamen, China, several metro ticketing policy recommendations are put forward, including raising the focus on E-Tickets, formulating more attractive preferential measures to promote the mode conversion of private cars and vehicles to metro, paying attention to high-frequency passengers, and seeking common subsidies from the financial industry to achieve a win-win situation. In addition, the analytical framework proposed in this study can be used to evaluate the effectiveness of other transportation policies in the future.