Table of Contents

• Overview
• Importing Required Libraries
• Dataset Overview
• Data Wrangling
• Analyzing Demand Trends
• Competitor Pricing Impact
• Discount Strategies
• Pricing Model
• Revenue Maximization Simulation
• Conclusion

Overview

This project focuses on analyzing retail store inventory data to develop a Dynamic Pricing Strategy. The goal is to optimize pricing decisions, forecast demand, and maximize revenue using data-driven insights. The analysis includes demand trend exploration, competitor pricing impact, discount strategies, and revenue maximization simulations.

Importing Required Libraries

• KaggleHub: For loading datasets directly from Kaggle.
• NumPy: For numerical computations.
• Pandas: For data manipulation and analysis.
• Plotly: For creating interactive visualizations.
• Scikit-learn: For machine learning tasks, including regression modeling.

Dataset Overview

The dataset, sourced from Kaggle, contains detailed information about retail store inventory, including:

• Columns: Price, Competitor Pricing, Discount, Demand Forecast, etc.
• Size: 73,100 rows and 21 columns.
• Integrity: No missing or duplicate values.

Data Wrangling

• Convert Date Column: The Date column was converted to a datetime format for time-based analysis.
• Calculate Revenue: A new column Revenue was created using the formula:

  Revenue = (Price - (Price * Discount / 100)) * Units Sold

• Inspect Data: Ensured transformations were applied correctly.

Analyzing Demand Trends

• Daily Demand Trends: Grouped data by date to calculate total daily demand. Visualized using a line chart to identify fluctuations and seasonality.
• Weekly and Monthly Trends: Added Week and Month columns for granular analysis. Weekly and monthly demand trends were visualized using bar charts.

Findings

• Daily Trends: Peaks observed during holidays and promotional periods.
• Weekly Trends: Week 52 showed the highest demand, likely due to year-end promotions.
• Monthly Trends: July exhibited the highest demand, indicating mid-year activity.

Competitor Pricing Impact

• Correlation Analysis: Analyzed the relationship between Competitor Pricing and Demand Forecast.
• Scatter Plot: Visualized how demand varies with competitor pricing.
• Price Difference Analysis: Calculated the difference between Price and Competitor Pricing and analyzed its impact on demand.

Findings

A strong correlation between competitor pricing and demand was observed. Competitive pricing strategies are crucial for maintaining market share.

Discount Strategies

• Correlation Analysis: Analyzed the relationship between Discount and Demand Forecast.
• Box Plot: Visualized demand distribution across different discount levels.
• Revenue Simulation: Calculated revenue for each discount level and visualized average revenue by discount level using a bar chart.

Findings

Discounts positively impact demand, but excessive discounts reduce revenue. Optimal discount levels were identified to maximize revenue.

Pricing Model

• Data Preparation: Selected Price, Competitor Pricing, and Discount as features. Used Demand Forecast as the target variable.
• Train-Test Split: Split data into training (80%) and testing (20%) sets.
• Model Training: Trained a linear regression model.
• Evaluation: Achieved reasonable accuracy with an R² score of 0.85.

Revenue Maximization Simulation

• Price Adjustments: Simulated price adjustments (-20%, -10%, 0%, +10%, +20%).
• Adjusted Prices: Calculated new prices and simulated revenue.
• Visualization: Compared total revenue across different price adjustments using a bar chart.

Findings

A 10% price increase resulted in the highest revenue of $564,458,460.29. This adjustment balances revenue maximization and competitiveness.

Conclusion

The dynamic pricing model project provided valuable insights into the factors influencing demand forecasts and revenue. Key takeaways include:

• Demand Trends: Identified patterns and seasonality in demand.
• Competitor Pricing: Highlighted the importance of competitive pricing.
• Discount Strategies: Determined optimal discount levels for maximizing revenue.
• Pricing Model: Developed a predictive model with reasonable accuracy.
• Revenue Maximization: Simulated price adjustments to identify the optimal pricing strategy.

These analyses and models enable data-driven pricing decisions, helping organizations optimize revenue while maintaining market competitiveness.