Week 3 – Listing of Active Businesses

The dataset I chose from the City of L.A. is about registered businesses that are currently still active and have not ceased business operations. This dataset is updated every month and so seems to be maintained pretty well, although there may be slight discrepancies if a business chooses to not report something to the Office of Finance.

There are 16 columns (or data types) including business name, street address, and location start and end date to name a few. Also, there are 496,904 records or rows in this dataset, which will give an ample amount of data to work with and visualise. Examples of how this data can be analysed include looking at trends of business closures, seeing what areas have the most businesses still open, and how long a business will last in a certain location. This information could be useful to someone who is interested in opening a new store in a certain city and seeing if there’s competition or how long the average business stays open in that area.

Since there is so much information to analyse, one can group them into categories of businesses such as “Educational Services”, “Restaurants”, “Health-related”, and more in order to make charts and graphs less crowded. For example, if a pie chart was to visualise everything by name, then it would not provide a lot of value since each business will have a different name and opening/closing date. But if it were grouped by categories of businesses for different cities, perhaps that can show trends in what kind of stores do well in large cities versus small ones. One can also look at the dataset by plotting linear regression over a certain number of years and seeing if there was a period of time with a lot of closures (such as during the Recession many years ago). This could provide data on economic patterns and potentially predict a future slump, and so a business owner would be more careful about taking risks or spending a lot of money in order to account for that.

Some information that was left out include reasons for why a business closed after a certain period of time, and also the size of registered businesses and how many employees or people there were. If the ontology set had information about why a store or restaurant closed, such as bad management or bad location or not enough people visiting, then maybe other business owners who examine the dataset can avoid making those mistakes for their own practices. The size of a business is also important, because smaller businesses or startups will have a harder time remaining open compared to big corporations that already have a lot of funding.

If I was to collect data about registered businesses, I would create a more extensive survey for businesses to report their current status, offering incentives and and perhaps collecting data more frequently if funding so allows. It would also be interesting to see if there are small businesses that do get established quickly and stay open for a long period of time, and see what the reasons for which they can attribute their success.