Recommender system and big data (design a smartphone recommender system based on hybrid filtering)
Download as PPTX, PDF1 like147 views
This document discusses the design of a hybrid smartphone recommender system based on collaborative and content-based filtering approaches using big data technologies. It begins with definitions of recommender systems and their common approaches. Then it explains how the system will apply a map-reduce algorithm using Hadoop: the map function will apply collaborative filtering to generate user-item pairs, and the reduce function will apply content-based filtering to calculate item scores and select top recommendations. Finally, the document proposes developing a web interface to demonstrate the hybrid recommender system and discusses how big data can help address challenges in recommender systems.
Recommender system and big data (design a smartphone recommender system based on hybrid filtering)
- 1. Jendouba university University of Jendouba Faculty of law, economics and management of Jendouba Design smartphone recommender system based on hybrid filtering Haithem Mezni Supervised by: Siwar Abidi Developed by: Academic year 2017/2018
- 2. ➤ Introduction ➤ Big data characteristics ➤ Recommender system definition ➤ Big data benefits ➤ Recommender system approaches ➤ Hadoop ecosystem ➤ Recommender systems examples ➤ Approach ➤ Big data definition ➤ Conclusion Plan
- 3. Introduction
- 4. Recommender system definition Recommender system is a system able to provide or suggest items to the users. Recommender system
- 6. Collaborative Filtering The collaborative filtering is one of the most RS approaches used. The main idea is to exploit information about the past behavior or the opinions of an existing user community for predicting which items the current user of the system will most probably like or be interested in.
- 7. Content Based filtering Content-based recommendation systems are based on recommending an item to a user based on a description of the item. Furthermore, focus on the current user’s rating history and similarity between items to compute recommendations.
- 9. Hybrid
- 12. What is Big data ? Big data is an evolving term that describes any voluminous amount of structured, semistructured and unstructured data that has the potential to be mined for information.
- 13. The 3VS of big data Volume Variety Velocity Variety is one the most interesting developments in technology as more and more information is digitized. Traditional data types (structured data) include things on a bank statement like date, amount, and time. These are things that fit neatly in a relational database. . The main characteristic that makes data “big” is the sheer volume. It makes no sense to focus on minimum storage units because the total amount of information is growing exponentially every year . Velocity is the frequency of incoming data that needs to be processed. Think about how many SMS messages, Facebook status updates, or credit card swipes are being sent on a telecom carrier every minute of every day, and you’ll have a good appreciation of velocity
- 14. Big data benefits Why is big data important?
- 15. Receive Real-Time Analytics Take Customer Service to the Next Level Personalized Customer Shopping Experience Curating Social Media Feedback E-commerce Big data benefits
- 17. Hadoop
- 19. Approach
- 20. Map In the map function we we applied the CF method which be the output of each map function is a set of similar users together with their positively rated smartphone. This latter as represented in a pair <Smartphone, user>. User3 is more similar to user1 then the others. User5 is more similar to user2. Map function
- 21. Reduce function Reduce we applied a CBF that takes as input every positively rated smartphone and its users list. This latter is obtained by executing the shuffle phase that consists of regrouping the users of each smartphone then we calculate the score of similar smartphones and showing the top rated.
- 22. Web interfaces
- 23. Web interfaces
- 24. Web interface
- 25. Web interfaces
- 26. Conclusion We gave an idea about the recommender systems models and we are showing the issues and problems in the domain also we explained the emerging of recommender systems and how big data can be a challenge to solve those problems and creating insights. The Big Data aim is to improve decisions and competitiveness for companies and the public administrations, which will create a significant growth of the world economy. Furthermore, we are looking to implement RS and big data in era of e-commerce in Tunisia and we are proposing Recommendation by applying the weightage of summarized reviews and opinions on the rating of item as future enhancement in this work.
- 27. Thank you!