AI-Driven Pricing Optimization (D2C)

📌 Problem Statement

Pricing decisions in D2C businesses are often driven by intuition.
This project evaluates whether the current product price maximizes revenue using an AI-driven demand model.

---

🧠 Approach

• Estimated price elasticity of demand using a regression-based machine learning model
• Simulated multiple pricing scenarios (±10%)
• Predicted demand and revenue for unseen price points
• Built a Power BI dashboard to support pricing decisions

---

📈 Key Insights

• Price elasticity: −1.24 (highly elastic demand)
• Revenue peaked at a lower price point than the current price
• A ~10% price reduction was projected to drive ~3% revenue uplift

---

💡 Recommendation

• Current price: ₹1.47K
• Recommended price: ~₹1.32K

---

🛠 Tools & Technologies

• Python (NumPy, Pandas, scikit-learn)
• Power BI

---

📂 Project Files

• pricing_elasticity_model.ipynb → AI demand modeling & simulations
• d2c_pricing_data.csv → Historical pricing data
• pricing_simulation.csv → Price scenario simulation output
• Power BI.jpeg → Dashboard preview

---

📷 Dashboard Preview