FoodHub Data Analysis

Course: Statistical Methods for Decision Making

Project Overview

This project analyzes restaurant order data from FoodHub, a food aggregator service in New York. The analysis aims to understand customer preferences, restaurant performance, and delivery efficiency.

Objectives

• Analyze customer order data to identify popular cuisines and restaurants.
• Evaluate food preparation and delivery times.
• Assess customer satisfaction based on ratings.

Data Description

• order_id: Unique ID of the order
• customer_id: ID of the customer who ordered the food
• restaurant_name: Name of the restaurant
• cuisine_type: Cuisine ordered by the customer
• cost_of_the_order: Cost of the order
• day_of_the_week: Indicates whether the order is placed on a weekday or weekend
• rating: Rating given by the customer out of 5
• food_preparation_time: Time taken by the restaurant to prepare the food
• delivery_time: Time taken by the delivery person to deliver the food

Analysis Methodology

• Tools Used: Python, Pandas, Matplotlib, Seaborn
• Statistical Methods: Descriptive statistics, correlation analysis, hypothesis testing
• Data Visualization: Created graphs and charts to visualize findings

Key Findings

• Shake Shack leads in revenue generation.
• Average preparation time is 27 minutes; average delivery time is 24 minutes.
• Most orders are made on weekends, indicating higher demand.
• 89% of orders are delivered within 60 minutes.

Conclusions

• Shake Shack is the most popular restaurant with the highest revenue.
• Delivery times are generally higher on weekdays.
• Customers are willing to wait an hour for quality food.
• Most orders are made on weekends.

Recommendations

• Increase offerings of American, Japanese, Italian, and Chinese cuisines.
• Deploy more drivers and chefs on weekends to meet demand.

This project involved drawing inferences from the FoodHub analysis using various statistical methods. The following concepts were applied:

• Descriptive Statistics: Analyzing data through measures such as mean, median, mode, variance, and standard deviation to summarize and describe the characteristics of the dataset.
• Probability: Understanding the likelihood of events and applying probability rules to interpret data effectively.
• Estimation: Utilizing point and interval estimation techniques to infer population parameters based on sample data.
• Hypothesis Testing: Conducting tests to validate assumptions and claims about the population based on sample data, including Type I and Type II errors, significance levels, and p-values.