Business Report : Statistical Analysis for FoodHub

Contents

1. Introduction:
a. Overview of the rising restaurant trend in New York and FoodHub's role in online food
delivery.

2. Objective:
a. Aim to enhance customer experience by analysing order data for restaurant demand insights.

3. Data Description:
a. Detailed explanation of the data dictionary and its relevance.

4. Data Overview:
a. Exploration of data dimensions - rows and columns.
b. Examination of data types for each column.
c. Identification and treatment of missing values.

5. Statistical Summary:
a. Overview of statistical measures for food preparation time.
b. Analysis of orders without customer ratings.

6. Univariate Analysis:
a. Exploration of variable distributions through visualizations.
b. Identification of top 5 restaurants based on order count.
c. Recognition of popular weekend cuisines.
d. Assessment of orders exceeding $20.
e. Calculation of mean order delivery time.
f. Identification of top 3 frequent customers for discount vouchers.

7. Multivariate Analysis:
a. Exploration of relationships between key variables.
b. Identification of restaurants meeting promotional offer criteria.
c. Calculation of net revenue based on cost percentages.
d. Analysis of orders taking more than 60 minutes.
 e. Comparison of mean delivery times on weekdays and weekends.

8. Conclusions:
a. Summarisation of key findings and insights derived from the analysis.

9. Recommendations:
a. Actionable suggestions for business improvement based on cuisine types and feedback
ratings.

Note: This structured index provides a roadmap for a comprehensive business report,
ensuring clarity and readability.

Introduction:

1. Data Overview Report: Statistical Analysis for FoodHub

The dataset for FoodHub's statistical analysis comprises 1898 rows and 9 columns, providing a

comprehensive insight into various aspects of online food orders. This report aims to offer a brief
overview of the dataset's dimensions and structure.

2. Data Dimensions : The dataset is robust, consisting of 1898 rows, each representing a
unique food order, and 9 columns, capturing diverse information related to customers,

restaurants, and order specifics.

3. Column Information
order_id: Unique identifier for each order.
customer_id: Identification of the customer placing the order.
restaurant_name: Name of the restaurant fulfilling the order.
cuisine_type: Type of cuisine ordered by the customer.
cost_of_the_order: Cost associated with each order.
day_of_the_week: Indicates whether the order is placed on a weekday or weekend.
rating: Customer-assigned rating out of 5.
food_preparation_time: Time taken by the restaurant to prepare the food (in minutes).
delivery_time: Time taken by the delivery person to deliver the food package (in minutes).

4. Significance of Dimensions:
Rows (1898): Represent individual instances of food orders, offering a diverse dataset for
analysis.
 Columns (9): Encompass key variables crucial for understanding customer behavior,
restaurant performance, and overall service efficiency.

5. Implications for Analysis:

Rich Data: The dataset's substantial size allows for meaningful insights and comprehensive
analysis.
Diverse Variables: A varied set of columns enables a multifaceted examination, from customer
preferences to operational efficiency.

6. Conclusion: The dataset's dimensions provide a solid foundation for in-depth statistical
analysis, offering a nuanced understanding of FoodHub's online food ordering dynamics.

Data Types Overview Report: Statistical Analysis for FoodHub

The dataset encompasses diverse data types, including:

1. Integer: order_id, customer_id, food_preparation_time, and delivery_time are represented as

integers, capturing unique identifiers and time-related information.
2. Float: cost_of_the_order is expressed as a float, reflecting the monetary aspect of each order.
3. Object: restaurant_name, cuisine_type, day_of_the_week, and rating are categorised as
objects, signifying textual information, such as restaurant names, cuisine types,
weekdays/weekends, and customer ratings.

This varied data type composition facilitates a comprehensive analysis, considering both numerical
and categorical aspects.

Note : The dataset for FoodHub was meticulously examined for missing values, and I am pleased to
report that no such discrepancies were found. The dataset is complete, ensuring the integrity of our
analysis and affirming the reliability of the insights derived. This absence of missing values fortifies
the foundation for robust statistical and exploratory analyses, underscoring the dataset's quality and
suitability for drawing meaningful conclusions.

Statistical Summary of Food Preparation Time:

The analysis of food preparation time reveals insightful metrics. The minimum time required for food
preparation is 20 minutes, indicating an efficient operational baseline. The average preparation time
stands at 27.37 minutes, showcasing overall promptness. On the upper spectrum, the maximum
preparation time reaches 35 minutes, offering an understanding of the upper limit in cases of
extended preparation requirements. These statistics contribute valuable insights into the efficiency
and timelines of the restaurants associated with FoodHub, facilitating informed decision-making for
operational enhancements.

Analysis of Customer Ratings in FoodHub Orders:

Findings:
Not Rated Orders: A total of 736 orders have not been rated by customers.
Rated Orders: Rated orders are further categorised into 5, 4, and 3-star ratings, with corresponding
counts of 588, 386, and 188, respectively.

For univariate exploration, let's generate visualisations for the variables in the
FoodHub dataset:

order_id (Numeric): Histogram: A uniform distribution, indicating a relatively equal

distribution of order IDs.

customer_id (Numeric): Histogram: A varied distribution, suggesting differing order

frequencies among customers.
restaurant_name (Categorical): Countplot: Varying counts for each restaurant, indicating
differences in popularity.

cuisine_type (Categorical): Countplot: Diverse counts for each cuisine type, highlighting
varied customer preferences.

cost_of_the_order (Numeric): Histogram: A right-skewed distribution, with most orders

costing less and a few higher-cost orders.
Creating Boxplot for the cost of order to understand the Outliers:
day_of_the_week (Categorical): Countplot: Orders are spread across weekdays and
weekends, with potentially higher weekend demand.
rating (Categorical): Countplot: Majority of orders receive high ratings (4 and 5 stars),
indicating overall satisfaction.
food_preparation_time (Numeric): Boxplot: Generally consistent preparation times, with a
few outliers suggesting longer preparation durations.
Histogram on Food Preparation Time :
delivery_time (Numeric): Boxplot: Varied delivery times, with some outliers suggesting
longer delivery durations.
Histogram on delivery time:
The top 5 restaurants with the highest number of orders are as follows:

1. Shake Shack: 219 orders

2. The Meatball Shop: 132 orders
3. Blue Ribbon Sushi: 119 orders
4. Blue Ribbon Fried Chicken: 96 orders
5. Parm: 68 orders

This information is crucial for understanding customer preferences and restaurant popularity,
enabling targeted strategies for business growth and customer satisfaction improvement.

The most popular cuisine on weekends:

The data analysis reveals that on weekends, American cuisine emerges as the most popular choice
among customers, with a count of 415 orders. Followed by Japanese, Italian, and Chinese cuisines,
this insight is valuable for tailoring promotions and optimising offerings to align with customer
preferences during weekends.

The data analysis reveals that 29.24% of the total orders have a cost exceeding $20, showcasing a
substantial portion of the customer base preferring higher-value orders. This insight provides an
opportunity for targeted marketing strategies, promotions, or loyalty programs aimed at maximising
revenue from this segment of customers.

In our dataset, the mean delivery time is calculated to be approximately 24.16 minutes, reflecting the
average duration taken to deliver food orders. This insight aids in understanding the general
efficiency of our delivery process, contributing to a better grasp of customer expectations regarding
order fulfillments speed.

The top 3 most frequent customers:

The analysis reveals the top 3 most frequent customers and their respective order counts. Customer
with ID 52832 has placed the highest number of orders, totaling 13 orders. Following closely are
customers with IDs 47440 and 83287, with 10 and 9 orders, respectively. This valuable information
allows the company to recognise and reward its loyal customers, possibly through exclusive offers or
loyalty programs, fostering continued engagement and satisfaction. Understanding customer
preferences and behaviour is crucial for maintaining a strong and lasting customer-business
relationship.

Multivariate Analysis:

Cuisine vs Cost of the Order: Examining the relationship between cuisine and the cost of the
order provides insights into the pricing dynamics across different cuisines. This analysis helps
identify trends in customer spending based on their culinary preferences.
Cuisine vs Food Preparation Time: Analyzing the relationship between cuisine and food
preparation time helps understand the cooking complexities associated with different cuisines. It
aids in optimizing kitchen processes and improving overall service efficiency.

Day of the Week vs Delivery Time: Exploring the connection between the day of the week
and delivery time sheds light on the impact of weekdays and weekends on delivery efficiency. This
insight is valuable for resource allocation and logistics planning.
Rating vs Delivery Time: Understanding the correlation between customer ratings and
delivery time allows the company to gauge how service speed influences customer satisfaction.
This knowledge can guide efforts to enhance timely deliveries.

Rating vs Food Preparation Time: Analyzing the relationship between customer ratings and
food preparation time reveals the customer's perception of the correlation between food quality
and the time taken to prepare it. Insights from this analysis can guide improvements in culinary
processes.
Rating vs Cost of the Order: Exploring how customer ratings correlate with the cost of the
order provides valuable feedback on the perceived value for money. This information aids in
pricing strategies and customer satisfaction initiatives.

Correlation Among Variables: An overall correlation analysis among variables helps identify
patterns and dependencies within the dataset. Recognising correlations can guide decision-
making processes, informing strategic initiatives to enhance customer experience, optimize
operations, and maximize business profitability.
Observations on Revenue Generated by Restaurants:

1. Shake Shack has the highest revenue, generating $3579.53, indicating it is a popular and high-
grossing restaurant.
2. The Meatball Shop and Blue Ribbon Sushi follow with substantial revenues, $2145.21 and
$1903.95, respectively.
3. Five Guys Burgers and Fries has the lowest revenue among the top 15 restaurants,
suggesting it may have a lower average order cost.
4. Varied revenue across restaurants implies diverse customer preferences and spending patterns.
5. This information aids in understanding each restaurant's economic contribution to FoodHub.

Criteria of Restaurants for the promotional campaign:

The promotional offer for restaurants with a rating count of more than 50 and an average rating
greater than 4 includes the following top-performing establishments:

1. Shake Shack: 133 ratings

2. The Meatball Shop: 84 ratings
3. Blue Ribbon Sushi: 73 ratings
4. Blue Ribbon Fried Chicken: 64 ratings
5. RedFarm Broadway: 41 ratings

These restaurants have demonstrated consistent positive feedback and are eligible for the
promotional offer, enhancing their visibility and potentially attracting more customers.
The restaurants eligible for the promotional offer, considering a rating
count greater than 50 and an average rating above 4, are as follows:

1. The Meatball Shop: Average rating - 4.51

2. Blue Ribbon Fried Chicken: Average rating - 4.33
3. Shake Shack: Average rating - 4.28
4. Blue Ribbon Sushi: Average rating - 4.22

These establishments have both a substantial number of ratings and a high average rating, making
them prime candidates for the promotional offer to boost their visibility and attract more customers.

The net revenue generated by the company across all the orders:

The company employs a revenue model where it charges restaurants 25% on orders exceeding $20
and 15% on orders surpassing $5. The data analysis indicates a commendable net revenue of
approximately $6166.3 generated across all orders. This reveals the company's effective revenue
strategy in capturing a percentage of high-value transactions, contributing positively to its financial
performance.

Percentage of orders take more than 60 minutes to get delivered from the
time the order is placed:

The analysis of total delivery time reveals that approximately 10.54% of orders experience a duration
exceeding 60 minutes from the placement of the order to its final delivery. This insight indicates a
segment of orders that may require optimisation in terms of food preparation or delivery processes to
enhance overall customer satisfaction and delivery efficiency. Addressing this aspect could contribute
to improved service quality and customer experience for the company.

The delivery time of the orders on weekdays and weekends:

The analysis of mean delivery times during weekdays and weekends indicates a notable difference in
the average duration. On weekdays, the mean delivery time is approximately 28 minutes, while on
weekends, it reduces to around 22 minutes. This disparity suggests that the company may experience
more efficient delivery operations during weekends, possibly due to lower demand or optimized
logistics. Considering this observation, the company can explore strategies to streamline weekday
delivery processes and maintain or further improve the efficiency observed on weekends, contributing
to overall service enhancement.
Conclusion and recommendations based on my analysis to help improve
the Business:

Conclusions:

1. Demand Analysis: The data-driven analysis revealed significant insights into the demand
patterns. Popular restaurants like Shake Shack and The Meatball Shop dominate order volumes,
indicating their popularity among customers.
2. Cuisine Insights: American, Japanese, and Italian cuisines are top choices, with American
cuisine leading on weekends. Understanding cuisine preferences aids in tailoring promotional
activities.
3. Customer Engagement: Over 29% of orders exceed $20, providing an opportunity for
targeted promotions or loyalty programs to incentivize higher spending.
4. Operational Efficiency: The mean delivery time of approximately 24 minutes indicates overall
operational efficiency. However, further investigation on factors affecting delivery time may
uncover optimisation opportunities.
5. Revenue Generation: The company's revenue model, charging restaurants based on order
cost, resulted in a net revenue of $6166.3. Adjustments to percentage fees may be considered
based on strategic goals.
6. Rating and Loyalty: Restaurants meeting specific criteria (rating count > 50 and average
rating > 4) are eligible for promotional offers, fostering loyalty and enhancing overall customer
experience.

Recommendations:

1. Promotional Strategies: Focus promotional efforts on popular cuisines and top-rated

restaurants, leveraging the criteria identified for promotional offers.
2. Operational Optimisation: Investigate factors influencing delivery time to identify areas for
improvement. Streamlining processes during peak hours may enhance overall service efficiency.
3. Customer Loyalty Programs: Implement customer loyalty programs to reward frequent
customers, fostering long-term relationships and increasing customer retention.
4. Revenue Model Refinement: Evaluate the impact of adjusting percentage fees on order cost
for restaurants. Consider dynamic pricing strategies based on restaurant performance and
strategic goals.
5. Customer Feedback Integration: Continuously collect and analyze customer feedback to
identify areas for improvement and innovation, ensuring a customer-centric approach in
business decisions.
6. Market Expansion: Explore opportunities to collaborate with new restaurants, diversifying the
cuisine offerings to meet evolving customer preferences and expanding the market reach.
7. Data-Driven Decision Making: Continue leveraging data analytics for informed decision-
making, adapting strategies based on evolving customer trends and market dynamics. Regularly
update the analysis to stay agile in response to changing business landscapes.