Past Meetup

Leveraging Topic Relationships to Improve Recommendations

This Meetup is past

83 people went

Location image of event venue

Details

Dataiku is returning to SF and partnering with Toptal and ACM to present two talks focused on making the most of your data.

Tentative Schedule:
6:30pm: Pizza + Beer mingling
7:00pm: Operationalization: The Last Mile of Successful Data Science by Kenneth Sanford, Lead Architect at Dataiku
7:30pm: Leveraging Topic Relationships to Improve Recommendations by Imeh Williams, Senior Staff Data Scientist at Udemy

Talk Abstracts:

Leveraging Topic Relationships to Improve Recommendations by Imeh Williams, Senior Staff Data Scientist at Udemy:
Recommendations play a critical role in fulfilling Udemy’s mission of improving lives through learning by exposing users to a catalog consisting of over 80,000 courses covering thousands of topics. Using click, enrollment, and consumption data from a user base of 24 million learners, we constructed a topic graph that represents relationships between topics. This structure provides flexible recommendations that allow us to span the exploit-explore continuum. Recommendations powered by the topic graph improved revenue and increased the diversity of user’s purchases. The success of the topic graph spawned additional applications in other parts of the organization.

Operationalization: The Last Mile of Successful Data Science by Kenneth Sanford, Lead Architect at Dataiku:
In data science projects, the derivation of business value follows something akin to the Pareto Principle, where the vast majority of the business value is generated from the final few steps: operationalization of that project. This is especially true of applications such as real-time pricing, instant approval of loan applications, or real-time fraud detection. In this talk, we will address (through real uses cases) why and how proper operationalization framework is vital for businesses to realize the full benefits of their data science efforts.

Speaker bios:

Imeh Williams is a senior staff data scientist at Udemy where he works on improving the discovery experience (search and recommendations) using causal inference, statistical modeling, and machine learning. Before joining Udemy, Imeh served as the first data scientist at IXL Learning. Prior to becoming a data scientist, Imeh spent over a decade as a quantitative researcher studying education policy and youth development. Imeh holds a bachelor’s degree in computer science from Brown University and a PhD in Education Policy from Stanford University.

Ken is the US lead Analytics Architect for Dataiku. He is a reformed academic economist who likes to empower customers to solve problems with data. Ken’s primary passion is teaching and explaining. He likes to simplify and tell stories. Ken has spent time in academia (Middle Tennessee State University, U of Cincinnati, Boston College) consulting (Deloitte) and software development (SAS, H2O). He has a Ph.D. in Economics from the University of Kentucky in Lexington and his work on price optimization has been published in peer-reviewed journals.