Navigating Price Elastic Modelling (Part-2): Exploratory Data Analysis

Welcome back to the captivating world of Price Elastic Modelling! In this thrilling sequel, we venture into the next phase of our project, Exploratory Data Analysis (EDA). Following our successful data cleaning expedition, we are now ready to explore the “Electronic Product with category” dataset from Kaggle. Our focus is to uncover valuable insights about product prices, sales trends, and the influence of various factors on product demand. Join me as we dive into the depths of data visualization to unravel the secrets hidden within the dataset.

Recap of Price Elasticity of Products:

Before we dive into EDA, let’s quickly recap the fundamentals of price elasticity of products. In the previous blog, we learned how this economic metric measures the responsiveness of product demand to changes in price. Understanding price elasticity helps businesses optimize their pricing strategies to maximize profitability. If you missed the first part of our journey, catch up here.

Recap of Data Cleaning

In our previous blog, we embarked on a comprehensive data cleaning journey to ensure the accuracy and consistency of our dataset. We applied various techniques, such as categorizing price availability, standardizing product conditions, calculating impression counts, imputing missing merchant values, and converting weight formats. The cleaning process set a robust foundation for our exploratory analysis, enabling us to derive meaningful insights with confidence. If you missed the first part of our journey, catch up here.

EDA

As we delve into the Exploratory Data Analysis, we will focus on several key points to gain a deeper understanding of the “Electronic Product with category” dataset:

Merchant, Availability, and Country Distribution:

We start our analysis by examining the distribution of merchants, product availability, and sales across different countries. Understanding these trends will help us identify the major players and regions in the market.

Insights from the generated charts-

1. As we see Top 5 merchant have covered 99% of the total sales in the data and bestbuy is 1 among them.
2. 95% products are available and 2% products fall in special category.
3. 99.3% products are from USA and <1% from other countries

fig, axes = plt.subplots(1, 3, figsize=(15, 6))
fig.suptitle('Price Distribution')
axes[0].set_title('Merchant distribution')
axes[1].set_title('Product_Availability_Distribution')
axes[2].set_title('Country_Distribution')

sns.barplot(ax=axes[0], x = df['merchant'].value_counts().values,y = df['merchant'].value_counts().index)
sns.countplot(ax=axes[1],x="Product_availability", data=df)
sns.countplot(ax=axes[2],x="Country", data=df)

print((df.groupby('Product_availability')['Product_availability'].count()/df.shape[0])*100)
(df.groupby('Country')['Country'].count()/df.shape[0])*100

Product Condition Analysis:

Next, we explore the distribution of product conditions. By comparing the overall distribution with that of a specific merchant, Bestbuy.com, we can identify any variations in sales patterns.

Based on the charts generated-

1. Based on the charts, it is evident that the “New” product category overwhelmingly dominates the market with an impressive share of over 85%. This significant lead is followed by the categories of “Used” and “Refurbished” items.
2. Interestingly, the sales strategy at BestBuy store seems to be primarily focused on “New” items.

Category and Sub-category Distribution:

Explore the distribution of product categories and sub-categories. Identify the dominant product categories and sub-categories in the market, essential for market segmentation.

The charts provide valuable insights into the product distribution across different categories:

1. Electronics and Electronics Furniture Dominance: The category of “Electronics and Electronics Furniture” commands an overwhelming share, accounting for more than 99% of the total product distribution. This indicates that customers’ preferences are heavily inclined towards electronic products, and within this category, there is a wide variety of items available.
2. Within the “Electronics” category, two subcategories stand out as the most prominent. Firstly, the subcategory of ‘Drive, storage, hard’ demonstrates significant popularity among consumers, suggesting a substantial demand for storage devices such as hard drives, SSDs, and flash drives. Secondly, ‘TV, television, LED’ emerges as another strong subcategory, indicating a high demand for televisions and LED displays. Following closely behind the leading subcategories, ‘Laptops and computers’ holds a noteworthy position.

Price Distribution and Sale Analysis:

Analyzing the distribution of product prices and the impact of discounts on sales can provide valuable insights into consumer behavior, pricing strategies, and overall sales performance.

Bestbuy sales analysis

Overall maximum product are without any sale [chart 1] , but in bestbuy store if price of product is higher or lower it has in no discount [chart 4]

To have a better analysis of sale’s lets consider Walmart data

Insights from the Charts:

1. Chart 1 reveals that the majority of products are currently not experiencing any sales. However, in Walmart stores (as depicted in Chart 4), products with higher initial prices tend to have some discounts applied. This suggests that Walmart might be using discounts strategically to attract customers and boost sales for higher-priced items.
2. Chart 2 shows that the highest number of products going on sale are from the “New” product category, surpassing other product conditions. Similarly, Chart 5 highlights the prevalence of “New” products in sales at Walmart stores. This indicates that new products are more likely to be put on sale, which could be a tactic used to promote fresh inventory and incentivize customers to try the latest offerings.
3. Remarkably, Walmart’s sales strategy seems effective as products on sale receive higher impressions (with one impression assumed equivalent to one quantity sold) compared to products not on sale. This data suggests that customers are more inclined to purchase products that are currently offered at a discounted price, leading to increased impressions and potentially driving higher overall sales for the store.

Top 5 Merchants’ Analysis:

In this segment of our Exploratory Data Analysis, we shift our focus to the top 5 merchants in the market. By closely examining these leading players, we aim to gain valuable insights into their pricing strategies and product conditions. This analysis will allow us to identify key patterns, understand the competitive landscape, and shed light on the major players in the market.

Insights from the Charts:

1. Across all the merchants analyzed, there is a clear preference for selling New Products, as indicated by the majority of products falling under this category.
2. A distinct price differentiation exists between the merchants. Bestbuy stands out as a retailer with a focus on higher-priced products, while Amazon leads in providing more affordable options based on price. This disparity in pricing strategies could be attributed to various factors, such as the target market, brand positioning, or the product selection of each retailer.

Conclusion:

The Exploratory Data Analysis phase of our Price Elastic Modelling project has revealed valuable insights about the dataset. We have explored the distribution of product prices, sales, and key factors influencing product demand. Armed with this knowledge, we are better equipped to build the Price Elasticity Model in our next sequel, where we will uncover the impact of price changes on product demand. Stay tuned for the final part of our journey, where we will unleash the power of data-driven pricing strategies. The world of Price Elastic Modelling awaits — let’s continue exploring together!