Applying AI & Machine Learning to Retail & eCommerce
January 24, 2024
ASHWIN VISWANATHAN
Research Scientist at Amazon
Ashwin is a Research Scientist at Amazon working on understanding causal effects that inform long term customer purchase patterns and intent. He specializes in building dynamic causal and forecasting models using high-dimensional datasets. Prior to joining Amazon, Ashwin did his PhD in Computer Science at OSU under Dr. Johnson Thomas. His primary research interests are in the fields of Machine Learning and bio-inspired decision-making models using Spiking Neural Networks (SNN).
Watch live: January 24
Decision Making using Causal Inference
Causal models are a powerful tool for understanding and predicting the relationships between variables. They can be used to identify the root causes of problems, evaluate the impact of interventions, and make informed decisions. In recent years, there has been a growing interest in using causal models in industry as companies seek to improve their operations and make better use of their data. The discussion will cover some of the fundamental ideas behind building causal models and how these ideas are put to use in practical contexts. Within the causal model framework, we will also touch upon some of the quasi-experimental design paradigms to identify causal effects, namely, difference-in-differences and instrumental variables, to name a few. We will also explore difficulties brought on by erroneous or inconsistent data and the significance of developing on a broad scale while establishing a repertoire of validation procedures using examples drawn from my work as a research scientist.