Madhukar Gomasa

Madhukar Gomasa

Data Scientist
India

About Me

I have 4+ years of work experience in Data Science with a proven ability and history of developing full-stack data science projects. Hands-on experience leveraging machine learning, deep learning, and transfer learning m…

Experience

Data Scientist

MU SIGMA
Jan 2022 - Present · 4 years 6 months

Designed and developed a comprehensive and versatile Data quality and Value assessment module for a US based asset management company.
Developed the module on Jupyter notebook with a Python kernel.
Reduced the time of data quality assessment of more than 500 million rows of data from 60 hours to 50 minutes.
Built compatibility with different types of datasets including transaction, health-care, and geolocation datasets.
Generated 2 reports.
Allowed flexibility for users to tailor conditions and checks according to business needs.
Assessed the quality of data.

Software Engineer

iNeuron Intelligence
Jul 2020 - May 2022 · 1 year 10 months

Analysed a dataset containing data on various customers' annual spending amounts of diverse product categories.
Used PCA and Gaussian Mixture Model clustering algorithm to describe variation in different types of customers.
Provided insight into how to best structure delivery service to meet the needs of each customer.

Software Engineer

Thales
Aug 2020 - May 2021 · 9 months

Worked on one checkout platform for real time streaming application for financial data.
Built a real time streaming platform for different business domains of Expedia including Vrbo, Hotels, Car Rentals, and Lodging.
Captured and processed financial data for accounting.
Helped suppliers track total amount to be paid via Auto Pay or Request Pay model.
Crafted a scalable streaming solution using Flink StateFun to handle approximately 800k booking streams each day.

Project Engineer

Wipro Technologies
Jul 2015 - Aug 2016 · 1 year 1 month

Worked on an investment banking project for Barclays capital as client.

Skills

Python NumPy Apache Spark Microservices Kafka Data Warehousing Event Streaming Machine Learning Deep Learning Azure Data Ingestion Distributed Computing Statistics Hypothesis Testing CI/CD Pipeline Jupyter Notebook Transfer Learning PCA Gaussian Mixture Model Flink Oracle Kafka Connect Docker AWS Airflow Flink StateFun Mixed Integer Optimization Linear Programming Elastic Search
Report this Profile?