Chapter4 - Web Based Personalization Systems - Outline

You might also like

Download as pdf or txt
Download as pdf or txt
You are on page 1of 8

Chapter 4 Web

Personalization System
Lesson objectives

By the end of the lesson, learners will be able to:


 Define what recommendation systems is

 Describe how RS is working

 Discuss various similarity measures

 Demonstrate the types of Recommendation Systems

 Discuss the Recommender Applications

 Practice Hands on Exercise of RS

2
Outline

 Introduction
 Content-based recommendation

 Collaborative filtering based

 K-nearest neighbor ( KNN)

 Association rules

 Matrix Factorization (MF) - SVD

• Hybrid Approach
RS : Summary

Source: https://www.itransition.com/machine-learning/recommendation-
systems#:~:text=Machine%20learning%2Dbased%20recommendation%20systems%20are%20powerful%20engines%20using%20ma
chine,personalized%20product%20and%20content%20suggestions
RS Approaches in nutshell
 Collaborative Filtering
 Give recommendations to a user based on preferences of “similar” users
 Preferences on items may be explicit or implicit
 Includes recommendation based on social / collaborative content

 Content-Based Filtering
 Give recommendations to a user based on items with “similar” content in the
user’s profile
 Rule-Based (Knowledge-Based) Filtering
 Provide recommendations to users based on predefined (or learned) rules
 age(x, 25-35) and income(x, 70-100K) and childred(x, >=3) recommend(x,
Minivan)
 Hybrid Approaches
RS Approaches in a sheet
Hands on practice on Recommendation
1. Content Filtering using tfidf
Use the Source in the link below:
https://github.com/AlexanderNixon/Machine-learning-reads/blob/master/Movie-content-based-recommender-using-tf-idf.ipynb

2. Collaborative Filtering
Use the Source in the link below: https://github.com/AlexanderNixon/Machine-learning-
reads/blob/master/Collaborative-filtering-recommenders.ipynb
3. KNN: Recommendation with KNN
Use the Source in the link below:
Source: https://blog.jaysinha.me/train-your-first-knn-model-for-collaborative-filtering/
4. SVD: Recommendation with SVD
Use the Source in the link below: https://analyticsindiamag.com/singular-value-
decomposition-svd-application-recommender-system/
5. Association Rule: Recommendation rule generation using apriori Use the
Source in the link below: https://stackabuse.com/association-rule-mining-via-apriori-
algorithm-in-python/

6. Hybrid: Recommendation with Weighted


Use the Source in the link below:
Source: https://medium.com/analytics-vidhya/7-types-of-hybrid-recommendation-system-3e4f78266ad8
END of CHAPTER 4

You might also like