Machine Learning TO (MLTO) Monthly Meetup

Agenda
6:00-6:30 PM Arrivals and Networking
6:30-7:00 PM Tech Talk #1
7:00-7:30 PM Tech Talk #2
7:30-8:30 PM Networking & Wrap-up
8:30 PM Tear-down and Departures

Tech Talks
Talk #1 - Optimizing and Scaling Information Retrieval Pipelines - Abhi Anand, Data Scientist @ Wattpad

In the age of AI-driven applications, information retrieval is the backbone of numerous systems, from Retrieval-Augmented Generation (RAG) applications to recommender systems that personalize user experiences. However, scaling these systems effectively while maintaining performance is a significant challenge many organizations struggle to overcome, often resulting in suboptimal performance and increased cost.

In this talk, Abhimanyu will share how the team at Wattpad tackled these challenges. We’ll explore the essential steps in an information retrieval pipeline, discuss the unique difficulties encountered at scale, and delve into the experiments the team at Wattpad conducted to optimize different components of the pipeline. This includes optimizing text-embedding generation at scale, improving their in-house vector database solution, and increasing the relevancy of recommendations using novel graph neural network architectures.

Talk #2 - Building Data Science Product & Teams in the Wild - Jan Scholz, Sr. Director of Data Science at Loblaw Companies Limited

This talk explores the challenges and strategies for building data science product and teams using machine learning (ML) at scale. By discussing challenges faced and lessons learned for structuring teams, integrating ML models with existing systems, and ensuring scalable, robust deployment, real-world examples of doing data science "in the wild" will highlight how to overcome obstacles like data silos, maintaining model performance in production, and providing actionable insights for business stakeholders and business decision making.

About the Speaker
Abhimanyu Anand is a Data Scientist at Wattpad, an online social storytelling platform, where he leads the development of recommender systems and NLP based applications for content recommendation. He holds an M.Sc. in Big Data Analytics from Trent University, with a specialization in natural language processing. He has developed and implemented robust AI solutions throughout his career across diverse domains, including internet-scale platforms, metals and mining, oil and gas, and e-commerce.

Jan Scholz is the Senior Director of Data Science at Loblaw. He is passionate about helping organizations across industries build and scale high-performance ML and data science teams while developing transformative AI strategies, and designing and delivering custom, user-centered machine learning solutions using rapid development practices in the cloud. Jan has worked in machine learning in the consulting space since 2016 and holds a PhD in Neuroscience from Oxford.

Speak or Support MLTO!
We are constantly looking for new speakers and sponsors to share their knowledge and help build the AI community in the GTA! If you are interested please get in touch directly or apply via one of the links below:

• Speaker Application Form: mlto.ca/speak
• Sponsor Inquiry Form: mlto.ca/sponsor
• Volunteer Application Form: mlto.ca/volunteer