This article will be the start of a four-part series detailing a small hypothetical project involving a company that wants to use historical data to become data-driven and drive business growth.

That said, in this article, I will introduce the company, talk about its data needs and explore how and why data is important for meeting its objectives.

Cake Works, a fast growing bakery chain, has bakery shops across several major US cities. It is seeking to use its historical data to help drive business decisions, such as inventory management and possible bakery shop expansions. The company is looking to increase its market share and dominate the boutique bakery industry!

The ultimate goal for Cake Works is to become a household name by providing baked sweets to its customers. The company seeks to become a “tradition” and “past-time” for families all across the US!

The core business objective is to create an overview dashboard that contains high-level KPIs and appealing visualizations that answer several business questions at a glance. Ultimately, this dashboard will be used by Cake Works leadership to create and implement policies for its various bakery shops across the US.

The overview dashboard should be able to redirect to a more detailed dashboard, which allows the leadership team to look at the performance of individual bakery shops.

Cake Works has several questions that it hopes its data is able to answer. They are:

1. What type of baked goods are most and least profitable?

2. What type of baked goods are purchased the most and the least overall? What about by region? What about by month?

3. What region has the most or least amount of purchases?

4. Does the frequency of purchases correlate with price? That is, is an item generally purchased more if it’s inexpensive? Are there any noticeable relationships between price and other qualities of a baked good item?

5. What type of baked goods are the most and least caloric? Is there a correlation between calorie count and other qualities, such as customer rating, being vegan friendly, being a seasonal item and so on?

6. Is there a correlation between how a customer rates a baked good item and whether or not the item is seasonal? What about if the item is vegan? What about if the item contains specialty ingredients?

7. Are there any noticeable trends related to time and purchasing behavior? For example, do more purchases tend to occur during holidays or certain days of the week or certain months?

8. How can we determine which baked goods will continue to sell? Can we determine which baked goods to stop selling? Can we develop promotional events, such as discounts, special sales, and reward programs given the data?

9. Are there any other interesting insights from the present data? Can we generate more insights from adding additional fields of data and if so what fields should be added?

Apart from all of this, the leadership team would like to know if their historical data, as is, is sufficient to answer all of the aforementioned core business questions. If not, they would like feedback and instruction as to what additional data may be needed.

Ultimately, this whole process will act as a foundational springboard for Cake Works to become more data-driven. As the company becomes more data-mature and fluent, it hopes to eventually utilize predictive analytics to further drive business impact. Data is needed because it allows people and organizations to make informed and strategic decisions regarding any behavior or process that can be measured and tracked. With Data Analytics, information is carefully collected, stored, processed and visualized so that key business questions can be answered and lead to positive developments in a company.

In the following article, we will explore Mockaroo and learn about how it can create realistic fake data. In that article, I will outline relevant fields, based on Cake Works aforementioned business questions and objectives, that will make up the Cake Works dataset.