SDS 617: Causal Modeling and Sequence Data — with Sean Taylor

Startup Journey

Sean Taylor shares his excitement about co-founding Motif Analytics and his role as Chief Scientist. He discusses the transition from large companies like Lyft and Facebook to a startup environment, emphasizing the agility and alignment in smaller teams 1. Sean's responsibilities include channeling customer requirements and ensuring the tool imparts a strong opinion on data science and analytics 2.

It's been really, really tough not to tell people what I'm working on because I always tell people like the, you know, the two joys in work are like doing the fun thing and then telling people about it.

--- Sean Taylor

He aims to build the best tool possible for data scientists and analysts, focusing on answering causal questions with rigor and precision 2.

   

Sequence Analytics

Sean explains the concept of sequence analytics and its significance at Motif Analytics. He highlights how user interactions generate sequences of events that provide rich data, often discarded by traditional tools 3. By focusing on event sequences, Motif aims to unlock valuable insights from this underutilized data format.

When people are using apps and services, they generate sequences of events that capture in a really rich way what they're doing while they're using sites and services.

--- Sean Taylor

Sean also addresses the challenges of working with rare events and the importance of drilling down into specific user behaviors to extract meaningful insights 4.

   

Technology Approaches

Sean discusses the innovative tools and approaches being developed at Motif Analytics. He emphasizes the importance of honest data visualization and the challenge of creating a query language for sequence data 5. The goal is to provide tools that degrade gracefully and convey uncertainty transparently.

We're mainly focused on what I would call hypothesis generation rather than hypothesis testing.

--- Sean Taylor

Sean also highlights the need for tools that support hypothesis generation, helping users identify potential issues and opportunities without making definitive conclusions 6.