Link Search Menu Expand Document
CS8803-MDS

Human-in-the-loop Data Analytics

CS8803-MDS, Fall 2022

Instructor: Kexin Rong

Time: Mon & Wed 5-6:15PM

Location: Clough Rm 131

TA: Kaushik Ravichandran

Course Description: Humans play an important role in almost all stages in the data analytics lifecycle. In turn, data management and analytics can be made more effective when taking into account the people who design and build these processes as well as those who are impacted by their results. This course explores two roles of humans in the analytics life cycle: data scientists and data consumers.

  • The first part of the course focuses on the data scientist role, in which users analyze and explore data in an interactive manner to find patterns. The focus is on building scalable systems to enable interactivity in spite of growing data volumes.
  • The second part focuses on the data consumer role, in which users consume and interpret results produced by the systems to form insights. The focus is on developing novel interfaces and functionalities to enhance understanding of the data.

Human-in-the-loop data analytics is a nascent field at the intersection of Databases, Machine Learning and HCI. Students will gain a deep understanding of cutting-edge research through reading and presenting research papers while performing their own original research through course projects.

Office Hours

  • Kexin: Friday 11AM-12PM, Klaus 3322
  • Kaushik: Thursday 11AM-12PM, Klaus 3319

Prerequisites: Though not required, an undergraduate course in relational database systems and an undergraduate course in machine learning would be helpful.

Grading Policy

This course has no midterm or final exams. You will be graded on the basis of your class participation and course projects. We will read one papers for each class, and discuss them in class. Before class, you are expected to submit a short review of the required readings. Each class will also have one or more presenters who are in charge of leading the dicussions. Another significant portion of the grade comes from a semester-long course project, where you can work in a team of 1-3 people on a research project that is related to the course topics.

The final grade for the course will be tentatively based on the following weights:

  • Participation: 50%
    • Paper Review: 15%
    • Paper Presentations: 25%
    • Class Participation: 10%
  • Project: 50%
    • Project Proposal: 5%
    • Progress Report: 5%
    • Evaluation Plan: 5%
    • Draft Paper + Peer Review: 5%
    • Final Project Presentation: 10%
    • Final Paper: 20%

General Policy

You are encouraged to discuss the required readings with your classmates. However, the paper reviews must be written by yourself. For paper presentations, you are encouraged to reference the authors’ slides, but you can not directly use their slides without any modification. You are expected to abide by the Georgia Tech Honor Code.

Acknowledgements