ksirohi-blog

[ksirohi-blog]

About me

Who am I? I am an Engineer with passion to work with technology that drives business values. I like working with Programming, Databases, Cloud and other IT Technologies. 

👨🏻‍💻 GitHub  

Badge - AWS Certified Solution Architect - Associate (SAA-C02)

Badge -  Google Cloud Engineer - Associate (ACE)

[ksirohi-blog]

Education

Northeastern University                                                                                                                                          Master’s in Data Analytics (GPA 3.8)                                                                                          August 2020 Coursework: Advance Cloud Computing, Big Data Technologies, Data Warehouse & SQL, Predictive Modeling                                        

GB Pant Engineering College                                                                                                                                         Bachelor’s Computer Engineering                                                                                                  July 2017   Coursework: Data Structures, Database Management Systems, Object Oriented Programming, Software Engineering, Artificial Intelligence   

[ksirohi-blog]

[ksirohi-blog]

Work Experience

Truepill, Inc. (February 2022 - Currently working) DATA ENGINEER

Zartico (September 2020 - February 2022) DATA ENGINEER

Northeastern University (January 2020 - September 2020) TEACHING ASSISTANT

[ksirohi-blog]

Projects

MirrorText (Python, Docker, AWS, Bash, Linux) May (2020) Built a web application that helps the user to measure text similarity between two documents using tf-idf & cosine similarity method. Used Docker for containerization and hosted the service on AWS EC2 with Linux instance. Useful for finding plagiarism, or one can use its API as well.  

Spark Application on Uber Rides Data (Spark, AWS, Bash)  May (2020) Developed a Spark code on AWS EC2 instance to process 14 million rows of uber rides data. Also used bash to automate data collection and to run my scripts. I learned how fast and useful spark is when we have huge amount of data. 

PriceComm (AWS, Database, Data-Pipeline, Web-Scrapping, JSON) March (2020) Developed a comparison platform that shows real-time prices, deals and discounts on multiple products from number of e-commerece websites. It is like tripadvisor, but only for shoes and cloths.

ETL (Wearable Devices) (Spark, AWS, S3, Postgres, Python, OOPS) April (2020) Followed data warehousing best practice to perform ETL, and also designed a star schema. I learned how to combine cutting edge tools and techniques to implement fundamentals of data modeling. 

Quantitative Database Analysis (SQL, MySQL, Power BI, Python) December (2019) Designed a relational database and then calculated following things - (Customer life cycle value, Cross-Segment Analysis, Sales Forecasting). Learned how to deal with OLTP transactional data and perform joins in it. 

Stock Exchnage with Pymongo (NoSQL, Python)  April (2020) Collected real time stock-exchange data by making API calls using python, and then configured the MongoDB database to save results as document-store.

Fraud Detection Using Customer Transaction (Machine Leaning, Python) September (2019) Trained 3 different machine learning models that can detect fraudalent transactions on the usage of credit cards. Biggest challenge I faced was the imbalance class and parameter tuning. 

Lead Score Prediction and Cost Benefit Analysis (GLM, Regression) December (2019) (Blog Post) Implemented logistic regression to perform classification and to calculate probability of possible future customer. Also, calculated cost and benefit of acquiring new customers. 

Cancer Classification Using Gene Expressions (Predictive Mod., Python)

Property Assessment System (R-Shiny, Tableau)

Analysis of Boston Utility Consumption Patterns (Python)

Fake News Classification (R, TF-IDF, RandomForest)

Visualization (Tableau)

Fright Cost Analysis for ConMed Corporation 

Life-Expectancy Data Analysis 

TripAdvisor Reviews Data Analysis (R)