Massively by HTML5 UP

SQL query-based analyses

Rockbusters Stealth LLC

Rockbuster Stealth LLC is a movie rental company that used to have stores around the world. The management team is planning to use its existing movie licenses to launch an online video rental service in order to stay competitive. These PostgreSQL analyses aim to answer any business questions of the Rockbuster Stealth Management Board and other departments with data-related queries. I provide queries for data-driven answers and Tableau visualizations that they can use for their 2020 company strategy.

Objective:

Supporting the BI department to launch an online video rental service. Loading data into a relational database management system (RDBMS). SQL queries to answer any ad-hoc business questions of other departments.

Key Business Questions:

  • Movies with most/least to revenue gain
  • Average rental duration
  • Spatial customer info
  • Spatial sales info

Find the complete project repository including all Jupyter Notebooks here:

View on GitHub

The Data

Retrieve Data

Contains information about Rockbuster’s film inventory, customers, and payments, etc.
Around 3MB and contains several files with related tables.


Procedures

  • Relational databases
  • SQL
  • Database querying
  • Filtering
  • Cleaning & summarizing
  • Joining, Subqueries, CTE‘s

Analyses & Results:



Recommendations:

  • India, China, USA are the top markets
  • Further analyses and business strategies may target the watching preferences of these countries and aim to include local popular films in the selection
  • The online rental service may first aim at top markets as test markets
  • Combine country-specific knowledge and insights from online rental test markets

Find the Stakeholder Presentation here:

Stakeholder Presentation

Find the complete project repository here:

View on Tableau

Future approach/ improvements with Python-coded Machine Learning algorithms:

Clustering: Create new segments from client database in order to be able to serve customers specific to their needs.

Regression: Predict the customer lifetime value — how much are customers going to contribute towards the business over their time with us?

Classification: Predict which genre of movie a customer is likely to be interested in.