Client Goal
To discover data-driven insights that will inform their new business model and launch with success.
Project Summary
Overview
Rockbuster Stealth LLC wanted to transition their business model towards an online video rental service.
To support this venture, management was looking for some data-driven answers to inform their launch strategy.
Purpose and Context
This project was built as part of the Career Foundry “Become a Data Analyst” curriculum. The client, Rockbuster Stealth LLC, is a fictional company. Their challenge, though, is real – how can an established business leverage data to set itself up for success as it moves into the future.
My Role
For this project, I served as business intelligence analyst and storyteller. I worked with the data from start to finish, building a data dictionary, providing the business insights and presentation, as well as sharing insights and recommendations with the executive team.
Tools and Analytical Techniques
This project was created with the following tools:
- SQL in PostgreSQL
- Tableau Public
The skills used to complete this project include:
- Relational databases
- Database querying
- Filtering
- Cleaning and summarizing data
- Joining tables
- Subqueries and Common Table Expressions
- Insight development
- Data visualization
- Presentation development
- Storytelling
Project
Project Scope and Planning
Align requirements, project scope, and desired outcomes of project.
In this project, I set out to analyze historical Rockbuster data regarding the films, rental patterns, customers, geography, and revenue.
Specifically, I aimed to uncover:
- What movies contribute to rentals and revenue
- Where the current customers are located
- Any other helpful insights
Through this analysis, I would be able to make recommendations for a strategic launch of the client’s online video rental services.
Data Prep and Exploration
Determine and collect data for project, then clean, profile, and explore.
As the data was provided by Career Foundry, I was able to start off on the exploration and cleaning right away.
As part of this process, I completed the following steps:
- Loaded the data into PostgreSQL and extracted the entity relationship diagram (ERD)
- Created a data dictionary (linked below)
- Familiarized myself with the data to start thinking about how to answer the business questions
- Began to organize, sort, and filter the data with various SQL queries
- Completed queries to identify any dirty data that could skew analysis – none found so no action taken to clean
- Created a data profile with summary statistics
Challenges and Decisions in this Phase
- During the analysis, it was noted that the dataset timeline was limited in that it only included information from 2006 . This presented a limited view for the analysis as rental trends over time could not be evaluated.
- Had this been a real project, it may have been more critical to access a longer timeframe of rental and customer history. Between this being a fictional project (and this was the only data available) and also considering that most recent history would present the most recent patterns, the analysis continued with this limited dataset.
Analysis, Insights, and Visualization
Interpret data patterns and trends to uncover most impactful elements for project.
Once the initial exploration of the data was complete, it was time to start answering the key business questions and deriving the insights that would help the client form their strategy.
The primary insights and visualizations that were selected for presentation to stakeholders included themes in:
- Rental count and revenue generated by movie genre and rating – to confirm customer preferences
- Current inventory by genre and ratings – to confirm if the current stock supports customer preference
- Current customer base – to confirm which countries have the highest number of and highest value customers
Customer Preferences
Key Observation: The number of rentals and revenue reveal similar patterns in customer preference. For genre, Sports and Animation genres dominate the customer preference. For rating, PG-13 movies are the primary source of revenue and rentals.
Key Insights from Rental Numbers
Most Rented Genre
Sports + Animation
Least Rented Genre
Thriller
Most Rented Rating
PG-13
Least Rented Rating
G
Key Insights from Revenue
Genre
Sports + Animation
Genre
Thriller
Rating
PG-13
Rating
G
Current Inventory
Key Observation: The business is stocked appropriately with the customer’s preferred movie genres and ratings, which supports the goal of using current stock licenses.
Key Insights from Inventory
Most Stocked Genre
Sports + Animation
Least Stocked Genre
Thriller
Most Stocked Rating
PG-13
Least Stocked Rating
G
Customer Base
Key Observation: The countries with the most number of customers provide the most revenue.
Key Insights from Customer Base
Average Spend*
$106
*top 5 customers
Average # Customers*
32
*top 10 countries
Most Customers + Revenue
India, China, USA
Storytelling and Presentation
Assemble actionable recommendations to drive the key outcomes for stakeholder presentation.
A story evolved as I reviewed the most crucial observations from the data. By aligning these findings with Rockbuster’s objectives, I formulated data-informed recommendations to shape their revised business model.
Conclusions
By rental count and revenue:
- the most popular movie genre is sports.
- the most popular movie rating is PG-13.
The most popular movie genres and ratings are stocked appropriately.
The majority of Rockbuster’s customer base exists in India, China, and the USA.
Recommendations
To launch successfully:
- Focus marketing and service towards movies in the most popular genres and ratings.
- Leverage current inventory (and licenses) – particularly in the favored genre and ratings – to transition.
- Use current loyal customer base (top countries) for launch focus.
Next Steps
Define specific strategy with focus on…
- Most popular genres
- Most favored ratings
- Current customer geography
…to maximize success as Rockbuster moves into new online rental space.
Dataset
The data used in this project was provided by Career Foundry and included data tables with information such as film inventory, customers, and payments.
Source
Data was pulled from PostgreSQLtutorial.com.
It was provided as a zip package for our use.
