Skip to content
View dhruvsinha's full-sized avatar
💫
💫
1 follower · 0 following

Block or report dhruvsinha

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
dhruvsinha/README.md

Hi, I'm Dhruv👋

About Me

I am thrilled to be pursuing a Master's degree in Computer Science and Public Policy from the University of Chicago, building on the strong foundation in Economics, Mathematics, and Computer Science that I developed during my undergraduate studies at Ashoka University in New Delhi. Through my coursework in economics, statistics, machine learning, cloud computing, and artificial intelligence policy, I have gained a solid foundation in using technology to solve wide range social and financial problems that our world is facing.

At the University of Chicago, I am learning advanced techniques for modeling and analyzing data to create innovative solutions for important social concerns. I am passionate about leveraging technology to create positive change in society, and I am excited to use my skills to tackle real-world problems.

I am set to graduate in May 2023 and I am actively seeking full-time opportunities in Data Science and Data Engineering. Please feel free to connect with me on LinkedIn to learn more about my experience and research. You can also mail me at 📫 dhruvsinha.09@gmail.com

Current Work

I am currently working part-time as a Machine Learning Researcher at the Data, Infrastructure, Computation, and Environments (DICE) Lab in Chicago. At DICE, I am designed a deep learning model that utilizes bi-directional Long Short-Term Memory Networks (LSTMs) and Graph Convolutional Networks (GCNs) to predict points of errors in the application that fails to complete a test run on containers. By analyzing the sequence of system calls, the model estimates the point of divergence between a successful and an unsuccessful run of the application. This significantly reduces the time complexity for error detection, from exponential to linear.

In addition to my research and academic work, I also run a small initiative called Debate for You. At Debate for You, I teach middle school and high school students critical thinking and debate techniques that can help them navigate the increasingly complex and polarized world we live in. By encouraging students to explore multiple perspectives and form their own opinions on important social and political issues, I believe that we can help create a more engaged and informed citizenry.

Skills

  • Programming Languages- Python, R, STATA, JAVA, Golang, HTML, SQL
  • Cloud: AWS (EC2, DynamoDB, Athena, Lambda, Glacier, Load Balancing, S3), Google Cloud
  • Databases- SQL, Athena, Pandas, Spark Dataframes
  • Machine Learning- Pytorch, TensorFlow, Keras, Computer Vision, Natural Language Processing, Graph Convolution Network
  • Programming Skills- OOP, Algorithms, Parallel Programming, CUDA
  • Big Data- PySpark, HDFS
  • Econometrics and Statistics- Causal Inference, Hypothesis Testing
  • Other- Docket, Git, Linux, Airflow, Flask

Pinned Loading

  1. Reconstructing-Obfuscated-Facial-Images-Using-CNN Reconstructing-Obfuscated-Facial-Images-Using-CNN Public

    I use Convolutional Autoencoder to reconstruct blurred, pixelated, and speckled facial images

    Jupyter Notebook 2

  2. Clustering-approach-to-Stock-Price-Expectations Clustering-approach-to-Stock-Price-Expectations Public

    Using KNN clustering to cluster companies based on 18 different financial parameters

    Python

  3. An-Alternative-to-India-s-Reservation-Policy-RAMSES An-Alternative-to-India-s-Reservation-Policy-RAMSES Public

    A data driven alternative to India's Affirmative Action Policy. Published in COMPASS '20: Proceedings of the 3rd ACM SIGCAS Conference on Computing and Sustainable Societies

  4. Natural-Language-Processing-for-Indic-Languages Natural-Language-Processing-for-Indic-Languages Public

    In this project, we perform standard NLP tasks on Indic languages- Hindi, Bengali, Tamil, Malayalam, and Kannada.

    Jupyter Notebook

  5. Big-Data--Citation-Network-Analysis Big-Data--Citation-Network-Analysis Public

    To analyze citation datasets efficiently, network analysis is done by employing machine learning models such as logistic regression, word2vec, and KNN clustering. Implementing these models in PySpa…

    Jupyter Notebook 1

  6. Generate-Love-Stories-using-LLM Generate-Love-Stories-using-LLM Public

    Using GPT Neo to generate Love Stories!

    2