Data Analyst & Developer

Prastuti
Pokhrel

I build data pipelines, predictive models, and full-stack tools that turn raw data into decisions people can act on. M.S. Computer Science · Python · SQL · ML · Visualization.

01

About Me

I'm a Data Analyst with a background in software engineering, passionate about building end-to-end data solutions from writing optimized SQL queries and cleaning messy datasets, to deploying machine learning models and crafting dashboards stakeholders actually use.

With experience across government, academia, and software, I bring a practical, impact-focused lens to every data problem. I care about making insights accessible not just technically correct, but clearly communicated.

When I'm not wrangling data, I'm building apps, contributing to open-source projects, or exploring new ML techniques.

M.S., Computer Science
Lamar University
Machine Learning · Data Science · DBMS · 2025
B.E., Computer Engineering
Pokhara University
Nepal · 2021
02

Skills & Tools

Data & Analytics
SQLTableauPower BI ExcelStatistical Analysis
Machine Learning
scikit-learnLogistic Regression Predictive ModelingCross-Validation
Programming
PythonPandasNumPy MatplotlibPostgreSQLMySQL
Development
DjangoFlask ReactReact NativeREST APIs
Tools & Platforms
GitAWSPostman NginxGunicorn
Data Engineering
Data CleaningETL Pipelines DB DesignData Validation
03

Experience

Full Stack Data Analyst Developer
Lamar University — Data, Analytics & Reporting
July 2025 — Present · Beaumont, TX
  • Queried, cleaned & validated institutional student data using SQL and Python to support decision-making.
  • Produced IPEDS-sourced benchmarking reports covering degree conferral trends, employment outlook & rankings.
  • Led expansion of Cardinal Clarity web app into Android/iOS, broadening student accessibility.
Graduate Research Assistant
Lamar University — QEP & Digital Learning Center
June 2024 — May 2025 · Beaumont, TX
  • Built & deployed a Django quiz platform (Cardinal Clarity) with Nginx & Gunicorn serving 100+ students.
  • Designed responsive UIs with React; developed secure REST APIs; managed PostgreSQL schema updates.
  • Presented platform design and educational impact at the Digital Ticket Learning Technologies Conference.
Data Systems Lead
Ministry of Land Management
June 2021 — Aug 2023 · Kathmandu, Nepal
  • Led 30-member team converting 500,000+ land records across 40 municipalities at 99% accuracy.
  • Reduced manual processing time by 50% through automated Python workflows for image-based records.
  • Coordinated SQL cross-checks and secure PostgreSQL migration for real-time centralized access.
Backend Developer
Uniaxial Softwares
Sep 2019 — March 2021 · Kathmandu, Nepal
  • Built Django APIs delivering real-time health monitoring for 20+ client servers.
  • Reduced API latency by 30% through query optimization and caching.
  • Built LeafletJS dashboards for geolocation-based server tracking.
04

Projects

ML · Predictive Analytics
Student Dropout Prediction

Logistic Regression classifier predicting university dropout risk on 4,424 students across 36 features. Production-grade sklearn Pipeline with stratified cross-validation and stakeholder-ready odds ratio insights.

0.93AUC-ROC
87.3%Accuracy
0.91CV AUC
Pythonscikit-learnPandasMatplotlib
↗ View on GitHub
Data Viz · Institutional Research
STEM Student Success Dashboard

Interactive dashboard analyzing 10 years of IPEDS data across enrollment, retention, completion & financial aid — benchmarking Lamar University against 5 Texas peer institutions with a radar chart, KPI cards & funnel views.

10yrIPEDS Data
6Datasets
5Peer Schools
HTMLJavaScriptPythonChart.js
↗ Live Demo ↗ Tableau - Dashboard
EdTech · Full Stack
Cardinal Clarity — Learning Platform

University quiz platform serving 100+ students, deployed with Django, Nginx & Gunicorn. Expanded to Android/iOS with React Native. Presented at the 2024 Learning Technologies Conference.

DjangoReact NativePostgreSQLNginx
GovTech · Data Engineering
National Land Record Digitization

Led nationwide initiative digitizing 500,000+ physical land records across 40 municipalities into a centralized PostgreSQL system. Automated Python workflows eliminated manual processing and achieved 99% data accuracy.

500K+Records
50%Time Saved
99%Accuracy
PythonPostgreSQLSQL
05

Get in Touch

I'm open to data analyst roles, ML projects, and interesting collaborations. Whether you have a question, a project idea, or just want to connect , my inbox is open.

Send a Message →