top of page
Mirza Yaqub

Analyzing Online Sports Retail Revenue (SQL, Jupyter Notebook)




Introduction


In this project, I will be using SQL and Jupyter Notebook to analyze a sports database containing 5 tables that include product data such as pricing, reviews, descriptions, ratings, revenue, and website traffic. I am interested to see what recommendations can be provided to improve revenue.


Questions to consider:

  • How do the price points of Nike and Adidas products differ?

  • Is there a difference in the amount of discount offered by these brands?

  • Is there a correlation between revenue and reviews?

  • Is the majority of revenue coming from footwear products?

  • How does the revenue of clothing products compare to footwear products?


Key Insights:

  • Adidas items generate more total revenue regardless of price category than Nike!

  • No discount is offered on Nike products while Adidas products are discounted at an average rate of 33.4%.

  • There is a strong positive correlation of 0.651 between the revenue of a product and reviews of a product.

  • Product reviews are highest in the first quarter of the calender year!

  • Out of 3,117 total products, 2700 are in the footwear category generating a median revenue of over $3000 dollars.

  • Only 417 products are in the clothing category.




Database Schema



  1. How complete is our data?

  • We are missing less than 5% of the values.



2. Nike vs Adidas Pricing!

  • It is very hard to analyze this query since the results include many unique prices. The solution is to group them in different price ranges to better analyze them.



  • As we can see, Adidas's revenue surpasses Nike's regardless of the price category.

  • The "Elite" category for Adidas generates the highest revenue for the company.


3. Average discount by brand

  • Nike offers no discounts while Adidas is discounted while having more revenue than Nike.


4. Is there a correlation between reviews of a product and revenue?

  • Surprisingly, there is a strong positive correlation between reviews of a product and revenue. This means more people are buying products that are generally reviewed more.


5. Reviews by month and brand!

  • Product reviews are highest at the beginning of the year but decrease as we get to the middle of the year.


6. Footwear Products vs Clothing Products!

  • As we know we have a total of 3,117 products. 2700 products are footwear products that generate a median revenue of over $3000.

  • 417 products are clothing products that generate a median revenue of $503.

  • The majority of revenue comes from footwear products.



Recommendations to improve revenue:

  • The company can add more stock to its Adidas "Elite" price category since that is already the highest revenue-generating price point.

  • The company can try to offer a small discount on Nike products since they do not offer anything at the moment. This can increase overall product revenue.

  • The company can offer incentives to customers to leave a review for the product they purchased since there is a strong correlation between revenue and reviews.


Thank you for reading my analysis!










Comments


bottom of page