Abstract When you ride a Citi-bike, the system prompts you with two payment options: buying a one-time pass or pay for a membership. People might think those who have paid the membership are likely to ride longer compared to the one-time users. This study is to find the relationship of riding time between the one-time riders (customers) and the members (subscribers). The result of this study can then be used by the marketing department of the Citi-bike so that they can make more profit by targeting user group with longer riding time. The null hypothesis is that the average travel time of customers is less than equal to that of subscribers. The full analysis can be found in my ipynb here: https://github.com/ace-gabriel/PUI2018_ty1045/blob/master/HW8_ty1045/Assignment2.ipynb. I conducted my studies based on summer time data (2016.7) and winter time data (2016.1) and get similar results. For winter time, with a T-statistcs of 15.3 and p-value of virtually 0, we can safely reject the null hypothesis and favor the alternative hypothesis. The customers stay longer on bike compared to the subscribers. Similarly, summer time data has a T-statistics of 16.87 and p-value 0. Therefore, we can reject the null hypothesis and conclude that the average travel time of customers is greater than that of the subscribers.IntroductionCiti-bike is the largest bike sharing system in the USA. Launched in 2013, it now has a totals of 706 stations and 12,000 bikes (Wiki). Like many company and business, one major concern is how to maximize its profit and revenue by making effective policies against targeted user group. For instance, if Citi-bike knows which group of users tend to ride for a long time, it charge that user group more to increase its revenue. Alternatively, it can also force users from the other group to move to this user group so that they can achieve the similar results. In this case, if subscribers tend to have longer riding time, Citi-bike could charge subscribers more to increase its revenue. Similarly, it can also increase the price for one-time pass and force more people to become members in order to increase its revenue. Accordingly, figuring out whether customers or subscribers tend to rider longer is of vital importance for Citi-bike to increase its revenue. Figure. 1 below shows the null hypothesis and the alpha level.