Skip to content
0

Predicting Hotel Cancellations

🏨 Background

You are supporting a hotel with a project aimed to increase revenue from their room bookings. They believe that they can use data science to help them reduce the number of cancellations. This is where you come in!

They have asked you to use any appropriate methodology to identify what contributes to whether a booking will be fulfilled or cancelled. They intend to use the results of your work to reduce the chance someone cancels their booking.

The Data

They have provided you with their bookings data in a file called hotel_bookings.csv, which contains the following:

ColumnDescription
Booking_IDUnique identifier of the booking.
no_of_adultsThe number of adults.
no_of_childrenThe number of children.
no_of_weekend_nightsNumber of weekend nights (Saturday or Sunday).
no_of_week_nightsNumber of week nights (Monday to Friday).
type_of_meal_planType of meal plan included in the booking.
required_car_parking_spaceWhether a car parking space is required.
room_type_reservedThe type of room reserved.
lead_timeNumber of days before the arrival date the booking was made.
arrival_yearYear of arrival.
arrival_monthMonth of arrival.
arrival_dateDate of the month for arrival.
market_segment_typeHow the booking was made.
repeated_guestWhether the guest has previously stayed at the hotel.
no_of_previous_cancellationsNumber of previous cancellations.
no_of_previous_bookings_not_canceledNumber of previous bookings that were canceled.
avg_price_per_roomAverage price per day of the booking.
no_of_special_requestsCount of special requests made as part of the booking.
booking_statusWhether the booking was cancelled or not.

Source (data has been modified): https://www.kaggle.com/datasets/ahsan81/hotel-reservations-classification-dataset

# Import the necessary library
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np
from sklearn.linear_model import LogisticRegression

import numpy as np
import seaborn as sns
import pandas as pd
import matplotlib.pyplot as plt
from sklearn import svm
from sklearn.datasets import make_blobs

from sklearn.model_selection import KFold 
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, confusion_matrix, classification_report
from sklearn.ensemble import RandomForestClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.model_selection import cross_val_score

%matplotlib inline
# Read the CSV file into a DataFrame
hotels = pd.read_csv("data/hotel_bookings.csv")
hotels
# Set the style for Seaborn
sns.set(style="whitegrid")

# Plot histograms for numerical columns
numerical_columns = ['no_of_adults', 'no_of_children', 'no_of_weekend_nights', 'no_of_week_nights',
                     'lead_time', 'arrival_year', 'arrival_month', 'arrival_date',
                     'no_of_previous_cancellations', 'no_of_previous_bookings_not_canceled',
                     'avg_price_per_room', 'no_of_special_requests']
plt.figure(figsize=(18, 16))
for i, col in enumerate(numerical_columns, 1):
    plt.subplot(3, 5, i)
    sns.histplot(data=hotels, x=col, kde=True)
    plt.title(col)

# Plot count plots for categorical columns
categorical_columns = ['booking_status', 'type_of_meal_plan', 'required_car_parking_space',
                        'room_type_reserved', 'market_segment_type', 'repeated_guest']
plt.figure(figsize=(18, 16))
for i, col in enumerate(categorical_columns, 1):
    plt.subplot(2, 3, i)
    sns.countplot(data=hotels, x=col)
    plt.title(col)

plt.tight_layout()
plt.show()

# Plot Correlation between Booking Status and Repeated Guest
plt.figure(figsize=(10, 6))
sns.countplot(x='booking_status', hue='repeated_guest', data=hotels)
plt.title('Correlation between Booking Status and Repeated Guest')
plt.xlabel('Booking Status')
plt.ylabel('Count')
plt.legend(title='Repeated Guest', loc='upper right')

plt.show()

The Challenge

  • Use your skills to produce recommendations for the hotel on what factors affect whether customers cancel their booking.
# Plot Correlation between Booking Status and Lead Time
plt.figure(figsize=(12, 8))
sns.boxplot(x='booking_status', y='lead_time', data=hotels)
plt.title('Correlation between Booking Status and Lead Time')
plt.xlabel('Booking Status')
plt.ylabel('Lead Time (days)')

plt.show()

#Plot Correlation between Booking Status and Number of Weekend Nights
plt.figure(figsize=(12, 8))
sns.boxplot(x='booking_status', y='no_of_week_nights', data=hotels)
plt.title('Correlation between Booking Status and Number of Week Nights')
plt.xlabel('Booking Status')
plt.ylabel('Number of Weekend Nights')

plt.show()

#Plot Correlation between Booking Status and Number of Weekend Nights
plt.figure(figsize=(12, 8))
sns.boxplot(x='booking_status', y='no_of_weekend_nights', data=hotels)
plt.title('Correlation between Booking Status and Number of Weekend Nights')
plt.xlabel('Booking Status')
plt.ylabel('Number of Weekend Nights')

plt.show()

#Plot Correlation between Booking Status and Average Price per Room
plt.figure(figsize=(12, 8))
sns.boxplot(x='booking_status', y='avg_price_per_room', data=hotels)
plt.title('Correlation between Booking Status and Average Price per Room')
plt.xlabel('Booking Status')
plt.ylabel('Average Price per Room')

plt.show()

# Define lead_time_values
lead_time_values = hotels['lead_time']

# Plotting the lead time column
plt.figure(figsize=(10, 6))
plt.hist(lead_time_values, bins=30, color='skyblue', edgecolor='black')
plt.title('Distribution of Lead Time')
plt.xlabel('Lead Time (days)')
plt.ylabel('Frequency')
plt.grid(axis='y', alpha=0.75)

plt.show()

#Plot Correlation between Booking Status and Room Type
plt.figure(figsize=(12, 8))
sns.countplot(x='booking_status', hue='room_type_reserved', data=hotels)
plt.title('Correlation between Booking Status and Room Type')
plt.xlabel('Booking Status')
plt.ylabel('Count')
plt.legend(title='Room Type Reserved', loc='upper right')

plt.show()

#Plot Correlation between Room Type and Number of Children
plt.figure(figsize=(12, 8))
sns.scatterplot(x='room_type_reserved', y='no_of_children', data=hotels)
plt.title('Correlation between Room Type and Number of Children')
plt.xlabel('Room Type Reserved')
plt.ylabel('Number of Children')

plt.show()

#Plot Correlation between Number of Children and Average Price per Room
plt.figure(figsize=(12, 8))
sns.regplot(x='no_of_children', y='avg_price_per_room', data=hotels, scatter_kws={'s': 20})
plt.title('Correlation between Number of Children and Average Price per Room')
plt.xlabel('Number of Children')
plt.ylabel('Average Price per Room')

correlation_coefficient = hotels['no_of_children'].corr(hotels['avg_price_per_room'])
plt.text(10, 200, f'Correlation: {correlation_coefficient:.2f}', fontsize=12, color='red')

plt.show()
‌
‌
‌