How to Explore the Relationship Between Product Price and Consumer Demand Using EDA

Exploring the relationship between product price and consumer demand is a fundamental aspect of understanding market dynamics and optimizing pricing strategies. Exploratory Data Analysis (EDA) plays a critical role in uncovering patterns, trends, and correlations within pricing and demand data. By employing EDA techniques, businesses can make data-driven decisions that align prices with consumer behavior to maximize revenue and market share.

Understanding the Variables

Before beginning EDA, it’s essential to define the key variables involved:

• Product Price: The amount consumers are required to pay for a unit of a product.

• Consumer Demand: The quantity of the product that consumers are willing to purchase at a given price.

These two variables are often interdependent, and their relationship can be influenced by numerous factors including seasonality, competition, product quality, marketing efforts, and consumer preferences.

Preparing the Dataset

Effective EDA begins with clean and well-structured data. The dataset used for this analysis should ideally contain:

• Date of purchase

• Product ID or name

• Unit price

• Quantity sold (or units demanded)

• Promotions or discounts applied

• Customer segmentation data (if available)

Data Cleaning

Perform the following data cleaning steps:

1. Remove duplicates: Ensure each transaction or data entry is unique.

2. Handle missing values: Use imputation techniques or remove rows/columns with excessive null values.

3. Convert data types: Make sure that numerical variables (like price and quantity) are correctly formatted as numerical data types.

4. Filter out anomalies: Identify and handle outliers such as unusually high prices or abnormal demand spikes that could skew the analysis.

Descriptive Statistics

Start the analysis by generating descriptive statistics to summarize the central tendencies and spread of your data:

• Mean, median, and mode of product prices and quantities sold

• Standard deviation and variance

• Minimum and maximum values

This step helps in understanding the general distribution of data and identifying any abnormalities or outliers.

Visualizing the Relationship

Visualization is a cornerstone of EDA and is particularly effective in uncovering the relationship between price and demand.

Scatter Plot

A scatter plot with price on the x-axis and demand on the y-axis can offer immediate visual insight into the nature of the relationship. Typically, this relationship is negatively sloped — as price increases, demand tends to decrease.

Line Charts

Line plots can be used to observe the trend of price and demand over time. This helps detect seasonality or the impact of temporal factors on consumer behavior.

Box Plots

Box plots can reveal the distribution of demand at different price ranges, helping identify ranges where demand is most elastic or inelastic.

Heatmaps

Heatmaps are useful for visualizing the correlation between price and demand, especially when broken down by categories or segments.

Correlation Analysis

Calculating the correlation coefficient (e.g., Pearson correlation) provides a quantitative measure of the relationship between price and demand. A strong negative correlation suggests that higher prices are associated with lower demand, and vice versa.

Segmented Analysis

To obtain deeper insights, perform segmented analysis based on:

• Product Categories: Demand elasticity can vary significantly across categories.

• Customer Segments: Different customer groups may respond differently to price changes.

• Time Periods: Analyze demand-price dynamics during promotional periods versus regular times.

Segmented analysis helps tailor pricing strategies to specific groups, enhancing overall effectiveness.

Elasticity of Demand

Price elasticity of demand (PED) is a key economic metric used to quantify how sensitive the quantity demanded is to a change in price. It is calculated as:

Using EDA, you can estimate this metric across different price bands or product categories to determine:

• Elastic Demand: PED > 1 (consumers are highly sensitive to price changes)

• Inelastic Demand: PED < 1 (consumers are less sensitive to price changes)

• Unit Elastic Demand: PED = 1

Understanding elasticity helps in setting prices that optimize revenue.

Regression Analysis

Simple linear regression or multiple regression analysis can model the relationship between price and demand. In its basic form:

Where:

• $alpha$ is the intercept,

• $beta$ is the slope (how much demand changes per unit price change),

• $epsilon$ is the error term.

More sophisticated models might include additional predictors such as marketing spend, competitor prices, or seasonal indicators.

Time Series Analysis

If your dataset includes time-based data, applying time series analysis can reveal temporal trends and seasonality in the price-demand relationship.

• Decomposition: Break the time series into trend, seasonality, and residuals.

• Moving Averages: Smooth out fluctuations to identify underlying trends.

• Lag Plots: Evaluate the delayed effect of price changes on future demand.

This allows for more strategic timing of pricing decisions.

Outlier Detection

Outliers in either price or demand can distort the analysis. These can be detected using:

• Z-scores

• Interquartile Range (IQR)

• Visual techniques such as box plots or scatter plots

Once detected, decide whether to investigate, remove, or adjust these anomalies depending on their context.

Impact of Promotions and Discounts

Explore how promotional activities affect demand by:

• Creating flags for promotional periods

• Comparing average demand during promotional vs non-promotional periods

• Visualizing spikes in demand aligned with price drops

This analysis helps quantify the effectiveness of promotional pricing strategies.

Using Interactive Dashboards

Building interactive dashboards using tools like Tableau, Power BI, or Plotly in Python can make EDA more dynamic and exploratory. Dashboards allow users to:

• Filter by product, time period, or region

• Drill down into specific segments

• Visualize real-time changes in price-demand dynamics

These capabilities support better communication of findings across business teams.

Key Takeaways

• The relationship between price and demand is typically inverse but varies by segment, time, and product.

• Visualization through scatter plots, line charts, and heatmaps is crucial for identifying patterns.

• Correlation and regression analyses quantify the strength and direction of the price-demand relationship.

• Demand elasticity offers strategic pricing insights to maximize revenue.

• Time series and promotional analysis reveal deeper behavioral patterns and seasonal effects.

EDA provides the foundation for understanding consumer behavior in relation to pricing. With thorough analysis, businesses can set more competitive prices, plan promotions effectively, and ultimately align their pricing strategies with actual market demand.