Anmol Anand

UT Austin

Cockrell School of Engineering

Bachelor of Science, Electrical and Computer Engineering

Graduated May 2023

Technical Core

Data Science and Information Processing

Technical Skills

Languages

Python, Java, JavaScript, C++, SQL, HTML

Technologies

React, Node.js, Git, PostgreSQL, MatLab, Tableau, AutoCAD, Fusion360, Blender, MSOffice, GSuite, R

Certifications

SQL for Data Science, Natural Language Processing with Classification and Vector Spaces, Getting started with TensorFlow 2, Excel Fundamentals for Data Analysis, Retrieve Data with Multiple-Table SQL Queries

Work Experience

Magnodata

Magnodata

Data Intern

Manalapan, NJ

May '20 - Jul '20

  • Extracted text from user-generated videos using third-party services.
  • Developed NLP algorithms to perform sentiment analysis and extract product attributes from extracted text.
AT & T

AT&T

Intern

Middletown, NJ

Oct '18 - Jan '19

  • Built a robotic camera system to track the sway of telephone poles in the wind using RoboRealm.
  • Filtered parts of a video to isolate the telephone pole from the rest of the background and utilized Javascript to determine the arc of the sway of the telephone pole.

Projects

AI-Powered Guide To Essential Books For Students

UT Austin October 2023
  • Integrated with ChatGPT to generate age-appropriate recommended books.
  • Extracted insights for every book recommendation along with questions & answers for every topic.

Shading Detection - John Deere (Senior Design Project)

UT Austin Fall 2022 - Spring 2023
  • Analyzed over 10,000 raw data points from an Arduino, an antenna, and a GNSS breakout board to detect and predict signal fading using 25 features based on satellite position.
  • Developed a CatBoost-based ML pipeline using various Python libraries, such as Sklearn and Pandas, to determine an accuracy value of 80% for the model's ability to categorize shade or unshaded.

Can ChatGPT write like a student? - ML Toolbox for Text Analysis

UT Austin Spring 2023
  • Created a dataset of over 25,000+ essays by combining the Evaluating Student Writing Kaggle Data and a list of papers generated with the ChatGPT API to perform NLP techniques, such as perplexity, logistic regression, Naive Bayes, and Decision trees.
  • Implemented n-grams and perplexity to classify if a human or AI wrote a given article with an accuracy of 85%.

What Makes a Song a Hit? - Data Science Principles Final Project

UT Austin Spring 2022
  • Built various machine-learning models to predict song popularity using audio features and popularity indexes of over 5,000 songs from the Spotify API.
  • Utilized linear regression, logistic regression, and KNN models and developed a KNN model that predicts popularity with 72.71% accuracy.

Shopee Kaggle Competition - Data Science Laboratory Final Project

UT Austin Spring 2022
  • Used a Siamese Neural Network and Term Frequency-Inverse Document Frequency to classify images that got a Kaggle score of 0.721.