Food Co. Demand & Operations Analysis

Comprehensive exploratory data analysis for a food delivery aggregator, transforming raw transactional data into actionable business intelligence.

Key Metrics

1,898
Orders analyzed
61%
Revenue from top 5 restaurants
21%
Faster weekend delivery
6
Actionable recommendations

The Challenge

Food Co., a food delivery aggregator in New York City, needed to understand demand patterns, optimize operations, and enhance customer experience. Raw transactional data was available but hadn't been systematically analyzed to address strategic questions around revenue concentration, operational efficiency, customer behavior, and peak demand patterns.

Approach & Methodology

Applied a structured EDA framework with four analytical layers:

  1. Summary Statistics: Initial distributions and key metrics
  2. Univariate Analysis: Individual variable distributions, top restaurants, cuisine popularity
  3. Multivariate Analysis: Cross-variable relationships and correlations
  4. Correlation Analysis: Quantitative assessment of numerical variable relationships

Analyzed 1,898 orders across 9 attributes using Python, Pandas, NumPy, Matplotlib, and Seaborn.

Key Findings

Revenue Concentration Top 5 restaurants generate 61% of revenue, with Shake Shack alone accounting for 21%. Bottom 6 restaurants contribute less than 5% each. This concentration presents both opportunity and risk for business strategy.
Interactive Visualization

Revenue by Restaurant

Order Patterns American cuisine dominates with 584 orders, especially on weekends. 29.2% of orders exceeded the $20 threshold. 14 distinct cuisine types served, indicating diverse customer preferences across the platform.
Interactive Visualization

Orders by Cuisine Type

Operational Performance Average food prep time of 27.37 minutes. Weekday deliveries average 28.34 minutes versus weekends at 22.47 minutes. This represents a significant 21% faster weekend performance. 10.53% of orders exceeded 60 minutes total time.
Interactive Visualization

Delivery Time: Weekday vs Weekend

Customer Insights Top customer placed 13 orders, indicating strong repeat behavior. Average platform rating of 4.33/5 demonstrates good overall satisfaction. However, "Not Given" was the most common rating category, revealing a critical feedback gap opportunity.

Recommendations

Six actionable recommendations delivered:

1. Weekend Delivery Optimization Leverage the 21% faster weekend performance by expanding weekend capacity and promoting time-sensitive services. Investigate root causes (staffing, routing, kitchen efficiency) and implement best practices to weekday operations.
2. Tiered Pricing for High-Value Orders Develop dynamic pricing strategies for orders exceeding $20, capturing additional margin from higher-order-value customers while maintaining competitiveness.
3. Loyalty Program Targeting Frequent Customers Create engagement programs for repeat customers (top customer: 13 orders). Focus on retention through personalized offers and exclusive benefits to drive lifetime value.
4. Menu Diversification Promote underrepresented cuisines to balance revenue concentration. Develop partnerships with emerging cuisine categories to attract new customer segments and reduce platform dependency.
5. Kitchen Efficiency Improvements Target 27+ minute average prep time through process optimization, staffing models, and technology. Even 5-minute reductions compound across thousands of daily orders.
6. Targeted Marketing During Peak Periods Implement demand-side pricing and promotions during identified peak periods to maximize utilization, reduce idle capacity, and improve unit economics.

Tools & Technologies

Python Pandas NumPy Matplotlib Seaborn EDA Business Intelligence
← Back to Data Science

Let's Talk

Get in Touch