The Battle of the Neighborhoods - RJTAM/COURSERA-CAPSTONE GitHub Wiki

1. Introduction/Business Problem:

With this study we want to help future investors of the restaurant business about the more valuable land and how to choose the correct place according to what they want to obtain. To help wit tat we will need to analyze population and income from different neighborhoods, the value of the land and the existing business already existing in the area.

2. Data:

We will need to analyze population, for that it will be needed to obtain information from te census and the file. Also we will need information about the land value of the different areas of the city, here is where the Foursquare API becomes important to obtain this kind of data, apart from obtaining information about the existing business in the area, their approximately revenues and some other aspects of how they work. Also continuing with this last step, we will also be able to obtain information about what customers expect and like in restaurants and other business in the area.

3. Methodology:

The data used in this report comes from a few different maps that can help business to decide which is the more valuable land for future investments and what to expect as a return of their possible investment. The data used groups info about population, square foot value, income, existing business and competitors and such. To be able to obtain all this data, what has been used is the Foursquare API plus information about the population, obtained from Toronto's Census information.

4. Results:

Analyzing the obtained data we can see that business related to the food industries tend to group in downtown Toronto where we can assume the number of tourists is higher and as such their revenues can be higher. What can be interesting to analize is why even though the wealthier neighborhoods tend to be in the north of the city the number of restaurants is significantly lower than in other parts of the city continuing this tendencies with population values as it seems that where more people live there are less restaurants, even seemingly following and inverse correlation.

5. Discussion:

As this analysis started I used to imagine that wealthier neighborhood would have clusters of restaurants related to the higher income of its residents. But the final result did not support this hypothesis - even was the opposite

6. Conclusion:

In my opinion this data can help future investors to decide whether or not to invest in determinate neighborhoods of Toronto, but it should be taken with caution as it does not analyze all existing variables.