Professional Documents
Culture Documents
Hotel Recommendation
Hotel Recommendation
Hotel Recommendation
Presented by:
Ashok Poudel (25108/76)
Sabin Bhandari (25154/76)
Sandesh Gyawali (25160/76)
Introduction:
A hotel recommendation system is a software application that
recommends hotels to users based on their preferences.
The system typically uses a variety of factors, such as user
ratings and reviews, to generate recommendations.
Problem Statement:
Finding the right hotel can be challenging, especially for
first-time visitors. There are many factors to consider,
such as location, price, amenities, and reviews.
Hotel recommendation system can help users find the
right hotel for their needs and preferences quickly and
easily.
Proposed solutions:
The proposed hotel recommendation system will use a
combination of collaborative filtering and content-based
filtering to generate personalized recommendations for users.
A study proposed a hybrid hotel recommendation system for the Nepal Tourism
Board's website that combines collaborative filtering and content-based filtering.
The system was evaluated using a survey of tourists, and the results showed that the
system was able to generate accurate and personalized recommendations.
There are a few companies that offer hotel recommendation systems for Nepal, such
as Nepal Tourism Board, TripAdvisor, and Hotel Booking Nepal.
Research Methodology:
ii) Understanding User Requirements: iii) User Profiling: iv) Usability Testing:
a. User Interviews and Surveys a. User Data Analysis a. Prototyping
b. Segmentation b. Usability Testing
b. Market Research
c. Feedback Analysis
c. Data Collection and Processing
d. Data Cleaning and Preprocessing
b. Requirement Collection:
A 5 - 3
B 4 - 5
C 2 3 -
- - - -
Let's say we have a user-item matrix:
User A has rated Hotel A with a score of 5 and Hotel C with a score of 3.
User B has rated Hotel B with a score of 4 and Hotel C with a score of 5.
User C has rated Hotel A with a score of 2 and Hotel B with a score of 3.
The collaborative filtering algorithm thus helps generate personalized hotel recommendations by leveraging
similarities between users' preferences and interactions with hotels.
Algorithms Used:
Content-based Algorithm:
Let's illustrate this with a simple example:
Score for this hotel: The hotels are ranked based on their scores, and the
Score = (4.5 * 0.4) + (3.0 * 0.3) + top- ranked hotels are recommended to the user.
(4.0 * 0.2) + (4.8 * 0.1) = 4.08
Content-based filtering thus focuses on the
characteristics of the items (hotels) and tailors
recommendations to the user's preferences.
Tools Used:
Programming language: Python
Web framework: Django
ML libraries: scikit-learn, TensorFlow
NLP libraries: spaCy, NLTK
Conclusion:
In conclusion, a hotel recommendation system for Nepal is a
feasible and beneficial solution to the challenges of finding the
right hotel in Nepal.