Soumyadeep Ray

Hi, I'm

Soumyadeep Ray.

A

Self-driven, quick starter, passionate programmer with a curious mind who enjoys solving a complex and challenging real-world problems.

About

I am currently studying Master of Science in Management Information Systems at Oklahoma State University. I enjoy problem-solving and coding. Always strive to bring 100% to the work I do. Having started coding at an early age, I can say my interest in this field has only grown with time. I gravitate more towards Data Science and Data Analysis. Working in the technology sector of various MNCs like Marriott International and Tata Consultancy Services has helped me gain relevant experience in the industry. As businesses today are becoming more inextricably linked with information technology, I strive to utilize my expertise to bridge the gap between technology and business.

Languages: Python, Java, JavaScript, C, C++, HTML/CSS, Bash
Databases: MySQL, PostgreSQL, MongoDB
Libraries: NumPy, Pandas, scikit-learn, MLlib, matplotlib
Frameworks: Flask, Django, Node.js, Keras, TensorFlow, PyTorch
Tools & Technologies: Git, Docker, AWS, GCP, Airflow, Luigi, Kafka, Heroku, JIRA

Looking for an opportunity to work in a challenging position combining my skills in Data Science, which provides professional development, interesting experiences and personal growth.

Experience

Marriott International

Data Scientist

Built training data pipelines using Spark and Snowflake that consisted of data of 32 million customers having 1000+ features (profile, reservation, digital click, and loyalty information) and stored as parquet files in AWS S3.
Developed Propensity Models to identify the customers that have higher likelihood to book reservations.
Optimized ML models using Gurobi Solver thereby increasing the overall performance of marketing campaigns by 2%.
Tools: PySpark, Python, Snowflake, AWS (EC2, S3), Git, Terraform, A/B Testing

Jun 2022 - Aug 2022 | Bethesda, Maryland

Oklahoma State University

Research Assistant

Extracted and processed data using CDC Wonder API to build a comprehensive MySQL database resulting in 95% accurate result on testing period.
Performed statistical analysis to determine the wheat producing counties in Oklahoma based on the Z scores assigned by comparing it with national average wheat production.
Tools: Python, MySQL, Tableau

Jan 2022 - May 2022 | Tulsa, Oklahoma

Tata Consultancy Services

Software Engineer

Managed an Agile development team of 3 associates in terms of processes, functional and data requirements.
Redesigned the operational process to identify fraudulent claims, enabling a 25% increase in target resolution, using clustering and tree-based models.
Created Tableau Dashboards to present information to stakeholders and visually monitor KPIs and insights.
Practiced end-to-end application development with all stages of Software Development Life Cycle (SDLC): design, analysis, coding, and testing.
Utilized JavaScript to produce high performance, user-friendly web interface reducing user clicks by 20% during navigation.
Automated the data import from excel to MySQL database using Python scripts reducing the manual efforts by 30%.
Created and tuned the ETL workflows in Informatica Power Center that reduced the run time of full data loads from source to target systems by 5 hours.
Tools: Python, Java, Javascript, HTML, Oracle, Tableau, Flask, MongoDB

Dec 2017 - Jun 2021 | Kolkata, India

Projects

                
Music Player Web-App
                  A music streaming web app based on Django
                
AccomplishmentsTools: Django, HTML, CSS, Bootstrap, SQLite, AWS S3, Heroku
Register/login to the web app(with OAuth-based Google Sign-In).
Search and filter songs based on language and singer.
Create multiple playlists and add/remove songs to/from playlist.
Scroll through recently played/viewed songs.

Quiz Web-App
                  A quiz playing web app based on Django
                
AccomplishmentsTools: Django, HTML, CSS, Bootstrap, SQLite, Heroku
Register/login to the web app(with OAuth-based Google Sign-In).
Play Quiz and see the leaderboard

Blog Web-App
                  A simple and extensible blog web-app based on Flask.
                
AccomplishmentsTools: HTML, CSS, Bootstrap, Flask, SQLAlchemy, Postgresql, Python
Users can view posts and contact the admin via Contact Page.
Admin can Add, Delete, Update posts.

Visual Question Answering
                  An attention-based classification model that aims at generating an answer for a given input image.
                
AccomplishmentsIncorporated Convolution Neural Networks (CNN) for extracting image features and Long Short Term
                    Memory for extracting question
                    embeddings.
Tested the model on the COCO dataset, abstract scenes images, and got 69% overall accuracy on the
                    VQA evaluation metric.

Video Summarizer
                  A Seq2Seq model that generates a short summary of the given input video.
                
AccomplishmentsIncorporated CNN to detect and classify objects in the video frames and Long Short Term Memory for
                    generating a summary.
Evaluated the model on MSVD (Microsoft Video Description Corpus) dataset; achieved 0.77, 0.71,
                    0.52 scores respectively on ROGUE,
                    BLEU, METEOR evaluation metrics.

Image Generator
                  An image generator based on the concept of adversarial networks (GANs)
                
AccomplishmentsDeveloped system was tested on a human-face database and loss was calculated by comparing the PCAs
                    of generated and original image.
Calculated difference in PCA was less than 10%, depicting the successful generation of an image by
                    the generator.

Head Counting System
                  A system that calculates the attendance of the class from a panoramic image of a live classroom.
                
AccomplishmentsUsed Singular Value Decomposition for image compression; applied various image processing
                    techniques and morphological operations to
                    detect the number of heads.