The purpose of this analysis is to create a summary DataFrame of the ride-sharing data by city type and also create a multiple-line graph that shows the total weekly fares for each city type so we will be able to visualize how the data differs by city type and how those differences can be used by decision-makers at PyBer.
-
Software:
- Jupyter Notebook 6.4.6
- Python 3.6.1
- Jupyter Notebook 6.4.6
-
Data sources:
- The differences in ride-sharing data among the different city types are:
- The total number of rides in urban cities is about 13 and 2.6 times higher per city than the rural and suburban cities, respectively.
- The total number of drivers in urban cities is about 30.8 and 4.9 times higher per city than the rural and suburban cities, respectively.
- The total fares in urban cities is about 9.2 and 2 times higher per city than the rural and suburban cities, respectively.
- The average fare per ride in rural cities is about 1.1 and 1.4 times higher per city than the suburban and urban cities, respectively.
- The average fare per driver in rural cities is about 1.4 and 3.3 times higher per city than the suburban and urban cities, respectively.
- Overall, urban cities are the most profitable, followed by suburban cities, with rural cities at the bottom. Profits for all city types are especially great around the end of February.
- Based on the results,
- The first thing that I would like to recommend to the CEO is to make more advertisements in suburban and rural areas to encourage more people to become drivers and to encourage more people use our rideshare service.
- Second, I would recommend that the company makes a promotion for a period of time to decrease the fare per ride in rural areas until the number of riders increases.
- Third, since there are more riders in urban areas, we can increase the fare per ride in rush hours.