Technical Workshop Series - Unlocking the Power of Advanced Recommender Systems: A Hands-On Journey with Python - 3rd in series (2nd Offering) by: Bahareh Rahmatikargar

Thursday, July 11, 2024 - 11:00

Technical Workshop Series

Unlocking the Power of Advanced Recommender Systems: A Hands-On Journey with Python - 3rd in series (2nd Offering)

Presenter:  Bahareh Rahmatikargar

Date: Thursday, July 11th, 2024

Time:  11:00 AM

Location: 4th Floor (Lecture Space) at 300 Ouellette Avenue (School of Computer Science Advanced Computing Hub)


This is a hands-on workshop; please bring your laptop.



This workshop marks the third workshop in a three-part series dedicated to the fascinating field of social network analysis and its application in recommender systems. Step right into the cutting-edge world of advanced recommender systems! After becoming familiar with the well-known types of recommender systems like content-based, collaborative filtering, and hybrid models, it's time to explore more intricate and modern types of recommender systems.

This workshop will dive into the fascinating realm of sequential, session-based, graph-based, and cross-domain recommender systems. These advanced techniques go beyond traditional methods, leveraging complex patterns and relationships in data to provide highly personalized and accurate recommendations.

Sequential recommender systems focus on the order of interactions, predicting what users will do next based on their previous actions. On the other hand, session-based recommender systems aim to provide real-time recommendations within a single session, often used in e-commerce and streaming services. Graph-based recommender systems utilize the power of graph theory to model relationships between users and items, capturing deeper connections and improving recommendation accuracy. Cross-domain recommender systems extend recommendations across domains, providing a holistic and enriched user experience.

Join us for this thrilling workshop, where we'll guide you step-by-step in building robust recommender systems that can handle real-world data's dynamic and intricate nature. Let's dive deep into modern recommendations' magic and unlock these advanced techniques' potential together!


Workshop Outline:

  • Explore practical approaches for building advanced recommender systems:

Through interactive and engaging hands-on exercises using Python, you'll learn to implement state-of-the-art recommender systems. We will start by revisiting fundamental concepts and progressively move towards advanced models such as sequential, session-based, graph-based, and cross-domain recommender systems.

  • Apply advanced recommender systems to real-world scenarios: With the knowledge and skills gained, you'll be able to apply advanced recommender systems to various applications, such as personalized shopping experiences, dynamic content recommendations, and cross-platform user engagement.
  • Prerequisites: Familiarity with recommender systems and Knowing the Python programming language is a prerequisite


Biography: Bahareh Rahmati is an enthusiastic Ph.D. student who started her program at the School of Computer Science in January 2021. Her research is in the field of data science and AI, with a focus on graph-based recommendation systems. She has currently published multiple papers in top-tier venues.


MAC STUDENTS ONLY - Register here

Note: This is a series of three workshops, students are encouraged to attend all, but it is not necessary in order to earn points. Registration in the rest of the series is NOT automatic, students will need to sign up using the link for MAC students. 

Reminder: Workshops marked as 1st Offering and 2nd Offering mean the exact same workshop is running at two different times - DO NOT REGISTER FOR BOTH. Students will not get points for attending the same workshop twice.