Price Optimization in E-Commerce

Tarique Akhtar 23 Aug, 2023 • 9 min read


Price optimization is a critical component of e-commerce that involves setting the right prices for products to achieve various business objectives, such as maximizing profits, increasing market share, and enhancing customer satisfaction. In an increasingly competitive e-commerce landscape, effective price optimization can be a significant differentiator.

Learning Objectives

After reading this article, learners will be able to:

  1. Understand the importance of price optimization in e-commerce and its impact on various business objectives.
  2. Comprehend the factors in effective pricing strategies, including costs, competitor pricing, customer demand, and market trends.
  3. Identify common pricing strategies used in e-commerce, such as cost-plus and competitive pricing.
  4. Learn how to implement cost-plus and Competitive pricing using Python and understand its advantages and disadvantages.

This article was published as a part of the Data Science Blogathon.

Understanding Price Optimization

Pricing is more than just a number on a tag. It communicates value, affects customer perception, influences purchasing decisions, and directly impacts the bottom line. An optimal pricing strategy considers various factors, including costs, competitor pricing, customer demand, and market trends.

Pricing Strategies in E-Commerce

E-commerce platforms often employ various pricing strategies, such as:

Cost-Plus Pricing

Cost-plus pricing, or markup pricing, is a straightforward pricing strategy where a fixed percentage (the markup) is added to the total cost of producing a product to set its selling price. This ensures that a company makes a profit over its costs.

The formula for cost-plus pricing is as follows:

Selling Price=Cost of Production+(Cost of Production×Markup Percentage)

Let’s say a company manufactures a widget for $50. If the company decides to use a markup of 20%, the selling price of the widget would be:

Selling Price=$50+($50×0.20)=$60


  1. Simplicity: It’s an easy-to-understand and straightforward method.
  2. Guaranteed Margins: It ensures a consistent profit margin on every product sold.


  1. Ignores Competition: This strategy doesn’t consider what competitors are charging.
  2. Ignores Value: The price doesn’t necessarily reflect the product’s perceived value to the customer.
  3. Inflexible: It might not be responsive to changes in the market or cost structures.

While cost-plus pricing is a common method, especially for businesses that want to ensure they cover costs and maintain a steady profit margin, it’s essential to consider other factors like competition, value perception, and market conditions when setting prices.

Python Implementation for Cost-plus Pricing:

def cost_plus_pricing(cost, markup_percentage):
    return cost + (cost * markup_percentage / 100)

cost = 50
markup_percentage = 20
price = cost_plus_pricing(cost, markup_percentage)




Competitive Pricing

It is often referred to as market-oriented pricing, a pricing strategy where the prices of products or services are determined based on what competitors charge for similar offerings. CP looks outwardly at the market landscape instead of looking inwardly at production costs (as with cost-plus pricing) or customer value (as with value-based pricing).

Key Features:

  1. Market Research: This strategy involves continuously monitoring the prices of competitors. This can be done manually or using specialized software, especially in industries where prices fluctuate rapidly, like e-commerce.
  2. Positioning: Companies decide whether they want to position themselves as offering lower prices than competitors, matching competitor prices, or deliberately pricing higher, signaling a premium product or service.
  3. Flexibility: Prices may be adjusted frequently in response to changes in the competitive landscape.


  1. Simplicity: It’s relatively straightforward to implement, especially with today’s tools to monitor competitor prices.
  2. Market Alignment: Ensures the business remains competitive and avoids over- or under-pricing products.
  3. Reduced Risk: By following market trends and pricing accordingly, there’s a lower risk of pricing products in a way that’s not accepted by the market.


  1. Reactive Approach: The strategy is inherently reactive; businesses are often responding to competitor pricing changes rather than being proactive.
  2. Profit Margins: This can lead to reduced profit margins, especially if the focus is solely on matching or undercutting competitors without considering costs.
  3. Brand Perception: Constantly undercutting competitors might lead to a perception of lower quality or value in the eyes of consumers.
  4. Potential Price Wars: If competitors continue to undercut each other’s prices, it can lead to a price war, which might hurt all players in the industry.

Case Study: Competitive Pricing

The Scenario

The case study involves developing a price optimization solution for a hypothetical company named as “ShopNest” to achieve competitive pricing against its competitor “RetailRoost”(hypothetical name). Both companies sell mobile phones online.

Data Collection and Analysis

Data collection involves creating simulated datasets for ShopNest and RetailRoost, including product name, brand, price, rating, specifications, and inventory.

Code for Data Creation

# Import necessary libraries
import pandas as pd
import random

# List of brands
brands = ["Apple", "Samsung", "OnePlus", "Sony", "Nokia"]

# Function to create standardized product names for a specific brand
def create_product_names_for_brand(brand, models_per_brand=5):
    return [f"{brand} Model {chr(ord('A') + i)}" for i in range(models_per_brand)]

# Function to create dataset for an e-commerce platform
def create_dataset(platform, brands, models_per_brand=5, total_products=100):
    specs = ["6GB RAM, 128GB Storage", "8GB RAM, 256GB Storage", "4GB RAM, 64GB Storage"]
    product_names = []
    # Create a list of product names based on the brands
    for brand in brands:
        product_names.extend(create_product_names_for_brand(brand, models_per_brand))
    product_names *= (total_products // len(product_names))
    product_names += product_names[:total_products - len(product_names)]
    data = {
        "Product ID": [f"{platform[:3]}-{i:03}" for i in range(100)],
        "Product Name": product_names,
        "Brand": [name.split()[0] for name in product_names],
        "Price": [int(random.randint(200, 700)) for _ in range(100)],
        "Rating": [round(random.uniform(1, 5), 1) for _ in range(100)],
        "Specifications": [random.choice(specs) for _ in range(100)],
        "Inventory": [random.randint(0, 500) for _ in range(100)],
    df = pd.DataFrame(data)
    return df
# Create datasets for ShopNet and RetailRoost
shopnest_df = create_dataset("ShopNest", brands)
retailroost_df = create_dataset("RetailRoost", brands)

Data Creation and Overview

The data creation code generates simulated datasets for both ShopNest and RetailRooster. The datasets include the following attributes:

  • Product ID: A unique identifier for each product.
  • Product Name: The name of the product.
  • Brand: The brand of the product.
  • Price: The price of the product.
  • Rating: Customer rating for the product.
  • Specifications: Specific features and configurations of the product.
  • Inventory: Number of units in inventory.

The data represents various mobile phone products from various brands, covering different price points and specifications.

Data Statistics

Let’s explore some statistics related to the data:

  • Number of Products: 100 for each platform.
  • Price Range: From $200 to $700 per unit.
  • Brand Distribution: Distributed among brands such as Samsung, Apple, OnePlus, Xiaomi, Realme, Nokia, Motorola.
  • Rating Distribution: Ranging from 1 to 5.
import matplotlib.pyplot as plt
# Extract metrics
def extract_metrics(df):
    avg_price = df["Price"].mean()
    total_inventory = df["Inventory"].sum()
    brand_distribution = df["Brand"].value_counts()
    return {
        "Average Price": avg_price,
        "Total Inventory": total_inventory,
        "Brand Distribution": brand_distribution

shopnest_metrics = extract_metrics(shopnest_df)
retailroost_metrics = extract_metrics(retailroost_df)
# Comparative visualization
def plot_comparative_analysis(metric_name, shopnet_value, retailroost_value, ylabel=""):["ShopNet", "RetailRoost"], [shopnet_value, retailroost_value], color=['blue', 'green'])
    plt.title(f'Comparative Analysis: {metric_name}')

When you run the above code to compare the Prices and inventories, you will see below output.


A Deep Dive into the Pricing Strategy

As this solution is for ShopNest, the management has the below strategies for pricing.

1. Continually monitor the common product listings between your platform and your competitors. By identifying available products on both platforms, Shopnest ensures it remains competitive for products that customers are most likely comparing between platforms.

2.  Establish a robust costing model. For instance, Shopnest assumes an 80% markup on its products. This markup serves as a foundation for all subsequent pricing decisions.

Businesses can operate clearly on their profitability thresholds by setting a clear margin. This strategy ensures that the business remains profitable and sustainable while competing and potentially reducing prices.

3. Determine a minimum selling price for products. This floor price serves as a safety net, ensuring that no matter how aggressive the pricing strategy becomes, the product will not be sold at a loss.

By setting a minimum price, Shopnest ensures it doesn’t compromise its bottom line in the race to be the most affordable.

4. Dynamically adjust prices based on competitors. If a competitor, like Retailroost, offers a product at a lower price, match their price to stay competitive. However, ensure that this adjusted price never falls below the minimum price.

Now let’s implement these strategies in Python.

import pandas as pd
from data_creation import DataCreation

class PriceOptimizer:
    def __init__(self, brands):
        data_creator = DataCreation(brands)
        self.Shopnest_data = data_creator.create_dataset("Shopnest", price_adjustment_factor=1.0)
        self.Retailroost_data = data_creator.create_dataset("Retailroost", price_adjustment_factor=1.05)

    def optimize_prices(self):
        matched_data = pd.merge(self.Shopnest_data, self.Retailroost_data, on="Product Name", suffixes=('_Shopnest', '_Retailroost'))
        matched_data['Cost (Shopnest)'] = matched_data['Price_Shopnest'] * 0.8
        matched_data['Minimum Price (Shopnest)'] = matched_data['Cost (Shopnest)'] * 1.1
        matched_data['New Price (Shopnest)'] = matched_data.apply(
            lambda row: row['Price_Retailroost'] if row['Price_Retailroost'] < row['Price_Shopnest'] else row['Price_Shopnest'], axis=1)
        matched_data['New Price (Shopnest)'] = matched_data.apply(
            lambda row: max(row['New Price (Shopnest)'], row['Minimum Price (Shopnest)']), axis=1)
        return matched_data[['Product Name', 'Price_Shopnest', 'Price_Retailroost', 'New Price (Shopnest)', 'Minimum Price (Shopnest)']]
    def compare_prices(self):
        # Merge Shopnest and Retailroost data based on product name
        merged_data = pd.merge(self.Shopnest_data, self.Retailroost_data, on='Product Name', suffixes=('_Shopnest', '_Retailroost'))
        # Compute the price difference between Shopnest and Retailroost
        merged_data['Price Difference'] = merged_data['Price_Shopnest'] - merged_data['Price_Retailroost']
        # Determine the competitiveness of each product
        merged_data['Competitiveness'] = merged_data['Price Difference'].apply(
            lambda x: 'Lower' if x < 0 else ('Equal' if x == 0 else 'Higher'))
        # Return the merged data with price comparisons
        return merged_data
    def adjust_prices(self, comparison_data):
        # Define the adjustment factors for different competitiveness levels
        adjustment_factors = {
        'Lower': 1,  # No adjustment if already lower
        'Equal': 1,  # No adjustment if equal
        'Higher': 0.98  # 2% reduction if higher
        # Apply the adjustment factors to Shopnest's prices based on competitiveness
        comparison_data['New Price (Shopnest)'] = comparison_data.apply(
        lambda row: row['Price_Shopnest'] * adjustment_factors[row['Competitiveness']],
        # Compute the price difference after adjustment
        comparison_data['Adjusted Price Difference'] = comparison_data['New Price (Shopnest)'] - comparison_data['Price_Retailroost']

        return comparison_data

    def analyze_impact(self, adjusted_data):
        # Analyze Profitability Impact
        total_price_difference = adjusted_data['Adjusted Price Difference'].sum()
        percentage_price_change = (total_price_difference / adjusted_data['Price_Shopnest'].sum()) * 100

        # Analyze Competitiveness Impact
        competitiveness_summary = adjusted_data['Competitiveness'].value_counts()

        # Analyze Inventory Impact
        inventory_summary = adjusted_data.groupby('Competitiveness')['Inventory_Shopnest'].sum()

        # Combine the analyses into a summary report
        analysis_report = {
            'Total Price Difference': total_price_difference,
            'Percentage Change in Price': percentage_price_change,
            'Competitiveness Summary': competitiveness_summary,
            'Inventory Summary': inventory_summary
        return analysis_report

def main():
    brands = ["Samsung", "Apple", "OnePlus", "Xiaomi", "Realme", "Nokia", "Motorola"]
    optimizer = PriceOptimizer(brands)
    adjusted_prices = optimizer.optimize_prices()

if __name__ == "__main__":


The above module consists of several key functions that collectively achieve the above objectives:

  • Data Integration: It takes the product data from ShopNest and Retailroost and aligns them for comparative analysis.
  • Price Comparison: It compares prices across the two platforms for each product, considering variations in brands and specifications.
  • Price Adjustment Strategy: It applies a predefined strategy to adjust Shopnest’s prices, considering both competitive positioning and internal cost factors.
  • Inventory Consideration: It considers the inventory levels when making price adjustments, allowing for targeted strategies based on stock availability.
  • Analysis and Reporting: It provides detailed analysis and reporting of the price adjustments, including the impact on profitability, competitiveness, and inventory management.

Code Structure

The Price Optimization Module is implemented as a Python class, encapsulating the necessary methods and attributes to perform the optimization. The key methods include:

  • optimize_prices(): The main method that orchestrates the entire optimization process.
  • compare_prices(): A method that compares ShopNest and RetailRoost prices.
  • adjust_prices(): A method that applies the price adjustment strategy based on the comparison results.
  • analyze_impact(): A method that analyzes the impact of price adjustments on various business metrics.


The Price Optimization Module is a vital tool that empowers ShopNest to make informed and strategic pricing decisions in a competitive e-commerce environment. By integrating competitive analysis, price adjustment strategies, and business considerations, it provides a holistic approach to price optimization.

This module exemplifies how data-driven decision-making can be applied in a real-world business, leveraging programming and analytics to achieve tangible business outcomes. It illustrates the potential of computational methods in transforming traditional business processes and enhancing competitiveness in the modern digital marketplace.

Key Takeaways:

After reading this article, readers will gain the following insights:

  1. Holistic Pricing Consideration: Pricing is more than just a number; it communicates value, influences decisions, and impacts profitability.
  2. Diverse Pricing Strategies: E-commerce employs various strategies, such as cost-plus and competitive pricing, each with its benefits and drawbacks.
  3. Python Implementation: The article demonstrates the implementation of cost-plus pricing using Python, making complex pricing calculations accessible to businesses.
  4. Strategic Pricing Decision: Effective pricing requires continuous monitoring, assessment of costs, competitor analysis, and alignment with business objectives.

Frequently Asked Questions

Q1. What is the importance of price optimization in e-commerce?

Price optimization is crucial in e-commerce, impacting profitability, customer perception, and competitiveness. It involves setting optimal prices to achieve business goals while remaining attractive to customers.

Q2. What is cost-plus pricing, and how does it work?

Cost-plus pricing involves adding a fixed percentage markup to the production cost to determine the selling price. It guarantees a consistent profit margin but may overlook market dynamics and value perception.

Q3. How does competitive pricing differ from other pricing strategies?

Competitive pricing sets prices based on competitors’ offerings rather than production costs or customer value. It ensures market alignment but can lead to reactive pricing and potential price wars.

Q4. How does the Python implementation help in pricing optimization?

The Python implementation showcases how to create datasets, compare prices, adjust prices based on competitors, and analyze the impact of adjustments. It demonstrates the practical application of pricing strategies using programming and analytics.

The media shown in this article is not owned by Analytics Vidhya and is used at the Author’s discretion.

Tarique Akhtar 23 Aug 2023

Frequently Asked Questions

Lorem ipsum dolor sit amet, consectetur adipiscing elit,

Responses From Readers

  • [tta_listen_btn class="listen"]