You are on page 1of 15

J. D.

College of Engineering & Management, Nagpur


Department of Artificial Intelligence
Session 2022-23
Presentation
On
RECOMMENDATION SYSTEM

Presented By 1) Aman Ramteke


2) Suyash Wankhede

Prof. Supriya Sawwashere


Head CSE/IT/AI
CONTENTS
 INTRODUCTION
 AREA OF USE / NEED
 TYPES
 TECHNIQUES : 1 . DATA ACQUISITION
 TECHNIQUES : 2 . CONTENT BASED SYSTEM
 CONCLUSION
 REFRENCES
INTRODUCTION
A recommendation system is an information filtering technique ,which
Provides users with information ,which he/she may be interested in.

Example:-
AREA OF USE
NEED

“Getting information off the Internet is like taking a drink


from fire hydrant” - Mitchell Kapor
1. Information overload
2. User experience
Recommended system help in addressing the information
overload problem by retrieving the information desired by user based
on his simillar user preferences and interest
TYPES
TECHNIQUES : 1. DATA ACQUISITION

1. Explicit Data
- Customer rating
- Feedback
2. Implicit Data
-Purchase history
-Click or browse history
3. Product Information
-Product Attributes
-Product description
TECHNIQUES : 1. DATA ACQUISITION
 
Collaborative filtering method finds a subset of users who have
similar tastes and preferences to market user and use this shbset for
offering recommendation.

1. Basic Assumptions :
- users with similar interests have common prefence
- Sufficiently large number of user preferences are available
2. Main approaches
-User based
-Item based
RECOMMENDATION GENERATION
User  Based Collaborative Filtering
• Advantages
-No knowledge about iteam features needed.

• Problems
New user cold start problem :
- Item with Few rating can not easily be recommended.

• Popularity bias :
-Tend to recommend only proper items .E.g. RINGo
Item Based Collaborative Filtering
 
• Advantages
- better scalability because correlation between limited number
of item insted of very large number of users

• Problems
- New user cold start problem.
- New item cold start problem.
E.g Amazon
2. CONTENT BASED SYSTEM
Content based system recommend items similar to
those user has like( browsed/ purchased) in past.

User profiles:
create user profiles to describe the types of items that user prefers.
E.g User likes Action comedy books

Recommendation on the basis of keywords are also classified under


content based .
E.g IMDB
CONTENT BASED SYSTEM
 
• Advantages
- No need for data on other users.
- Able to recommend users with unique taste.
- Able to recommend new and unpopular items.

• Limitations:
- Data should be in structured format.
- Unable to use quality judgement from users.
CONCLUSION

Amazon had more than 29 million customers


and several millions catalog item .
Hence we understand the concept of recommended
System and demand of it .
REFRENCES

1. https://www.researchgate.net/publication/
341941415_Movie_Recommendation_System
2. https://thingsolver.com/introduction-to-recommender-systems.
3. https://ieeexplore.ieee.org/document/7943151
Thank you !

You might also like