SM222 Geissler

9/22/14

Introduction:

Bike-sharing allows for easily accessible and affordable ways to commute around the city. As an analyst for CycleShare, I conducted research to try to understand specifically what kinds of apartment-complex locations are going to be the most profitable for a bike-sharing program, and where/whether or not we should open those new locations. Because CycleShare has to raise venture capital funds for each new location, the current shareholders equity stakes in the company have been lowered. We want to ensure that shareholders understand why this happens and we want to be able to show them that by carefully analyzing and comparing data with our competitors we can ultimately bring in even more profit.

Methodology:

To begin, I analyzed information about our competitor’s second year profits in various locations, only focusing on the locations in apartment complexes rather than in universities. I merged two data sets together to make one containing information with the specific location ID’s, bike scores (measuring whether a location is good for biking), whether or not the location has bike storage, the types of residents that live in the specific location and second year profits of each specific location ID. I then used this new dataset to calculate the descriptive statistics (mean, median, variance, standard deviation, etc.), as well as create a histogram to help describe and visualize the distribution of second year profitability for locations in apartment complexes. (Figures 1&2) Next, I created two various pivot tables, which help summarize data. One was used to calculate the number of apartment complexes that have bike storage and the number of apartment complexes with each type of residents. This information was then used to calculate the proportion of apartment complexes that have bike storage and the proportion with each type of residents. The second table was used to see the average second year profit for apartment locations based on whether or not it had storage available and the types of residents. That data was then used to create a bar chart, which would help visualize the profitability based on different types of residents both with and without storage. (Figure 3)

Results:

The results of my analysis come to show that the data concerning second year profitability through all locations follows a normal distribution. If you refer to Figure 1, we can see by the symmetric shape of the histogram that the data was normally distributed. In addition, we can take a look at Figure 2, which shows the table of descriptive statistics. From this, we can see that both the mean and median profit is roughly $16,000, confirming that the distribution of data was normal. We can also see that most locations (211 to be exact) fall in the range between $5,000-$20,000. The standard deviation was roughly $19,000, which falls within the range as well, showing to be an accurate representation of the data. In regards to the information about the apartment complexes, we can refer to the pivot table in Figure 3 to see