Big data with temporal dependence brings unique challenges in effective prediction and data analysis. The complex high-dimensional interactions between observations in such data brings unique challenges which standard off-the-shelf machine learning algorithms cannot handle. Even basic tasks of clustering, visualization and identification of recurring patterns are difficult.

The aim of this project is to design techniques for efficient representations of such high dimensional timeseries for exploratory data analysis. Taking financial timeseries data as a test bed, we will examine how one can design effective models in this complex regime.

One selected candidate will receive a stipend via the DSI Scholars program. Amount is subject to available funding.

Faculty Advisor

  • Professor: Nakul Verma
  • Department/School: Computer Science
  • Location: CEPSR 726

Project Timeline

  • Earliest starting date: 3/1/2020
  • End date: 8/15/2020
  • Number of hours per week of research expected during Spring 2020: ~10
  • Number of hours per week of research expected during Summer 2020: ~15

Candidate requirements

  • Skill sets: Machine Learning, Deep Learning, Recurrent Networks, Time Series Modelling, Data Visualization, Python programming
  • Student eligibility: freshman, sophomore, junior, senior, master’s
  • International students on F1 or J1 visa: eligible