Optimizing Recommendations with Multi-Armed and Contextual Bandits for Personalized Next Best Actions
About This Video
In this WiDS Upskill Workshop, Keerthi Gopalakrishnan explores how Multi-Armed Bandit (MAB) and Contextual Bandit algorithms can optimize online recommendations for next-best-action scenarios. These techniques help balance the trade-off between exploration (trying new recommendations) and exploitation (leveraging successful actions) to drive better personalization and engagement.
Keerthi will break down key MAB concepts, including:
- Epsilon-greedy
- Upper Confidence Bound (UCB) & Contextual UCB
- Thompson Sampling
- Real-world applications in recommendation systems
This session is ideal for:
- Data Scientists and Machine Learning Engineers
- Product Managers and Data Strategists
- Researchers and Academics
Prior knowledge: A background in supervised learning and evaluation metrics is recommended. Familiarity with online learning or decision-making algorithms is helpful but not required.
In This Video
Staff Data Scientist, Walmart Global Tech
I’m Keerthi Gopalakrishnan, a data science professional with six years of industry experience. My journey into the world of data began during my time at a startup in Bangalore, where I wore multiple hats, analyzing data to uncover patterns that fueled business growth.
My passion for data science inspired me to pursue a Master’s in Quantitative Analytics from the University of Cincinnati. Following my graduation, I joined Walmart Labs, where I have worked extensively on building and productionizing large-scale data science models. I started my journey with a focus on Time Series Forecasting, Inventory Optimization, and Assortment Optimization.
Currently, I specialize in the field of personalization, developing models that enhance engagement on Walmart’s homepage. My work focuses on building scalable ranking and recommendation systems that cater to millions of users, combining technical rigor with practical industry insights.
Beyond my technical pursuits, I have been passionate about public speaking since the age of eight and enjoy sharing knowledge and experiences with the data science community.
I’m excited to be here today and look forward to discussing the evolving landscape of data science, especially in personalization and recommendation systems. Feel free to connect with me on LinkedIn, and let’s continue the conversation!