About Me

Who Am I?

Hi I'm Tathagat Sathe, a Bachelor of Technology graduate in Aerospace engineering from the prestigious Indian Institute of Technology Kanpur. With experience in software development and website development, I have honed my skills in problem-solving and collaboration. I am passionate about leveraging data to gain insights and make informed decisions, and I am excited to transition to a career in data science.

My portfolio showcases a range of data science projects, highlighting my proficiency in statistical analysis, machine learning, and data visualization. I am committed to continuous learning and development, and I am eager to contribute my skills to tackle challenging data problems in the industry.

Data Science

Web Design

Software

Application

My Specialty

My Skills

Python

95%

SQL

90%

Pandas

90%

Numpy

90%

Matplotlib

85%

PyTorch

90%

PySpark

70%

Kafka

70%

OpenCV

70%

Flask

80%
Education

Education

Coursework: Autonomous Navigation, Introduction to Economics, Linear Algebra, Partial Differential Equation, Quantum Physics, Optimal Space Flight Control

Projects:
Visual Odometry and SLAM (Simultaneous Localization & Mapping)

Developed and implemented a Simultaneous Localization and Mapping (SLAM) algorithm on an autonomous robotics platform. The algorithm allowed the robot to navigate around an unknown environment without any prior knowledge, using an Extended Kalman filter to fuse wheel encoder odometry and monocular visual odometry data.

Experience

Work Experience

Assistant Manager at Genpact 2020 - current

  • Designed and implemented an automation system, reducing 80% of manual work, resulting in significant cost savings and increased productivity for the company.
  • Designed and implemented CI/CD pipelines to streamline the deployment process, including automated testing and integration.
  • Revamped and modernized legacy codebases, resulting in significant operating cost reductions and improved functionality, leading to a 500% increase in user base.
  • Contributed to all phases of the systems development lifecycle, from requirements gathering to production releases, collaborating with cross-functional teams to ensure the successful delivery of high-quality products.
  • Received three company-wide recognitions, including awards for innovation, speed to outcome, and teamwork, for spearheading the development of a workflow automation system and web applications.
My Work

Recent Work

Hate speech detection

An end-to-end machine learning pipeline for hate speech detection using BERT classifier and PyTorch, leveraging Hugging Face API for dataset management.

Conversational Document query system

An intuitive PDF document query application using OpenAI’s LLM and Streamlit, allowing users to upload documents and engage in natural language conversations with an AI chatbot.

Finetuning of LLAMA2 model for Financial Advising

Finetuned the LLAMA2 language model on a proprietary financial dataset, enhancing its domain-specific understanding and capabilities. Leveraged PEFT methods to efficiently adapt a pre-trained language model (PLM) for financial advising, significantly decreasing computational and storage costs.

Spotify Recommendation system

Designed a cutting-edge Spotify recommendation system using advanced data mining techniques.

Credit Card Fraud Detection

Designed and Developed a credit card Fraudulent transactions detection system leveraging AWS SageMaker, Kinesis, Lambda functions, and other cloud services. Designed and implemented end-to-end data ingestion, processing, and analysis pipelines.

Investment Portfolio Optimization

Developed and implemented various financial portfolio optimization models, including Modern Portfolio Theory, Mean-Variance Optimisation, Hierarchical Risk Parity, Mean Conditional Value at Risk, and Black Litterman Model, for personal investments.

Stock Price Forecasting

Leveraged cutting-edge technologies and advanced analytical tools to forecast stock prices, using a combination of LSTM, ARIMA, and other models.

Hate speech detection

Article Summarizer using Link

This tool accepts a URL link to a web page containing an article, and it generates a concise and coherent summary of the article's key points.

Hate speech detection

Twitter Sentiment Analysis

A real-time Twitter sentiment analysis system using cutting-edge big data technologies.
Developed a highly scalable data pipeline with Kafka and Spark to handle and process large volumes of streaming data.

Wikipedia Traffic Forecasting

Developed a comprehensive Wikipedia traffic forecasting model to predict traffic for over 145,000 articles.

Certifications

Here are some of my Certifications

IBM Machine Learning

Exploratory data Analysis, Supervised Learning, Unsupervised Learning, Deep Learning and Reinforcement Learning

Deep Learning Specialization

Neural Networks, Hyperparameter Tuning, Regularization, Optimization, Structuring Machine Learning Projects, CNN, Sequence Models

Advanced SQL

JOINs and UNIONs, Anaytic Functions, Nested and Repeated Data, Writing Efficient Queries

Advanced BigQuery

Partitioning, Clustering, Nested Fields, Data Transfer Service, Managing Permissions and Security, Accessing from External Applications

Geospatial Analysis

Coordinate Reference Systems, Interactive Maps, Manipulating Geospatial Data, Proximity Analysis

Mathematics for Machine Learning

Linear Algebra, Vectors, Matrices, Mappings, Eigenvectors

Get in Touch

Contact

tathagatsathe@gmail.com

Aurangabad, Maharashtra, India

+91 9309866077