CV

Archith Sharma

archiths@cmu.edu
Pittsburgh, PA, , US

Summary

Currently employed at Carnegie Mellon University. Student Developer + Researcher @ CMU :)

Education

  • B.S. in Statistics & Machine Learning
    2028
    Carnegie Mellon University
    GPA: 3.5

Work Experience

  • Research Assistant
    2025 - Present
    CMU Heinz College of Information Systems and Public Policy
    • Ongoing research with Dr. Woody Zhu on deep-learning methods in earthquake detection
    • Developing an extension of CUSUM (Cumulative Sum Statistic for distribution change) to multiple data sources — see the [CUSUM Portal](/projects/cusum-portal/) project page
    • Supported by the CMU Summer Undergraduate Research Fellowship (SURF)
  • Research Assistant
    -
    University of North Texas (UNT)
    • Conducted research with Dr. Junhyeon Kwon on bird population models for conservation action
    • Developed a synthetic simulation framework and ARMA & ARDL time-series tools using R and R Markdown — published as [Modeling American Kestrel Decline Using Spatiotemporal Subsampling to Improve eBird Data Reliability](/publication/2025-01-02-kestrel-decline-ebird-subsampling)

Skills

Technical

  • R
  • Python
  • HTML
  • LaTeX
  • Java
  • C
  • C++
  • C#
  • MATLAB

Software

  • Tidyverse
  • PyTorch
  • Pandas
  • Object-Oriented Programming (OOP)
  • Unity
  • Shiny

Analysis

  • Mathematical Modeling
  • Contextual Thinking
  • Data Wrangling

Soft Skills

  • Public Speaking
  • Organization
  • Building Relationships
  • Mathematical Thinking

Publications

  • Modeling American Kestrel Decline Using Spatiotemporal Subsampling to Improve eBird Data Reliability
    2025
    bioRxiv (preprint)
    Debiases eBird citizen-science data with spatiotemporal subsampling, then uses a time-series model to test whether rising Cooper's Hawk numbers help explain the American Kestrel decline.
  • Stats & Stumps: Using Machine Learning to Predict T20I Matches with Player and Venue Data
    2025
    Wharton Sports Analytics Journal
    Predicts Twenty20 International outcomes from venue-adjusted, player-level impact metrics. Regularized logistic regression reached 70.24% test accuracy on 1,029 matches.

Presentations

  • Speech
    Watch the recording on YouTube.
  • Relationship lessons from the stock market
    2024
    TEDxYouth@TAMS
    Denton, TX, USA
    The similarities between investing in the stock market and success in human relationships.

Projects

  • Allegheny Land Trust: St. John's Citizen Science Analysis
    Projects
    A data-for-good project with CMU Students Using Data for Good, measuring whether citizen-science activity around the Allegheny Land Trust's St. John's project has grown faster than state and county baselines. [Download the write-up (PDF)](/files/allegheny-land-trust-st-johns-analysis.pdf)
  • CUSUM Portal: Spatio-Temporal Earthquake Anomaly Detection
    Projects
    An in-progress anomaly-detection portal that flags abnormal seismic swarms in live USGS earthquake data using spatio-temporal CUSUM change detection. Research with Dr. Woody Zhu, supported by SURF.
  • Geospatial Mobile Application for Emergency Response and Management
    Projects
    A location-based AR app for navigation and emergency response on the UNT campus, built on Google Photorealistic 3D Tiles and Cesium for Unity. Research in UNT's Data Visualization and eXtended Reality (DVXR) Lab.
  • NFL Big Data Bowl 2026: Ball Hawks
    Projects
    Measuring a defender's commitment to the ball when it is in the air and its impact on play outcomes. Submitted to the NFL Big Data Bowl on Kaggle.
  • TAMS Mock Election 2024
    Projects
    A student-run mock election at the Texas Academy of Mathematics and Science: 115 voters, Texas-style ballot ordering, and a look at what ranked-choice voting can and can't fix. [Download the results write-up (PDF)](/files/tams-mock-election-results-2024.pdf)