Kamalnath Sathyamurthy
Data Scientist with over 6 years of broad-based experience in ETL (Extract, Transform and Load) testing of data intensive applications, creating and deploying complex user stories to build substantial deliverables as per business requirements | Proficient in creating effective visualizations and developing complex forecast and regression models | Thriving to improve myself by engaging in challenging research areas and business needs.
Master's in Data Science @ The State University of New York, Buffalo
View My LinkedIn Profile
Portfolio
Timeline:
Academic and Professional Experience:
ETL Quality Engineer and Assurance Associate
Cognizant Technology Solutions, India
October 2018 - August 2021
* Oversaw a cross-functional team of 15 in 3 different locations (Chennai, Bangalore and Hyderabad) and collaborated with Clients, Business Analysts, Developers, DevOps and UAT team to deliver quality products.
* Enhanced performance of subscribers' enrollment and processing claims by more than 35% by automating creation of EDI test data by formulating stored procedures in Sybase SQL.
* Initiated account-wide effort to streamline methods of Tableau reporting, resulted in 80% of reports being prepared ahead of schedule, with a 12% increase in accuracy.
* Trained and mentored new and existing account executives and interns on solutions involved in advanced product knowledge and created web portal to integrate collective knowledge repository which resulted in 50% reduction of training new executives individually on every module.
* Enhanced performance of subscribers' enrollment and processing claims by more than 35% by automating creation of EDI test data by formulating stored procedures in Sybase SQL.
* Initiated account-wide effort to streamline methods of Tableau reporting, resulted in 80% of reports being prepared ahead of schedule, with a 12% increase in accuracy.
* Trained and mentored new and existing account executives and interns on solutions involved in advanced product knowledge and created web portal to integrate collective knowledge repository which resulted in 50% reduction of training new executives individually on every module.
Junior ETL Quality Engineer and Assurance Analyst
Cognizant Technology Solutions, India
February 2016 - September 2018
* Worked closely with multi-disciplinary teams to understand the business scenarios and transaction functionality to design test plan, RTM and unit and integration test cases to ensure 100% requirement coverage.
* Performed data analytical testing to validate end to-end data flow from Enrollment module to Finance module.
* Regulated interfacing of metadata repositories, and developed Data stage Jobs to extract data from heterogeneous sources, applying data transformation logics and updating them into databases with less than 1% of defect leakage.
* Tested both backend and frontend features of Web app, Native app in SeeTest for automated mobile testing and ran scripts for multiple devices to achieve 30% increase in usage and 50% increase in performance of Mobile App.
* Validated output of ETL jobs in Tableau dashboards to ensure accuracy and integrity of data within data warehouse.
* Performed data analytical testing to validate end to-end data flow from Enrollment module to Finance module.
* Regulated interfacing of metadata repositories, and developed Data stage Jobs to extract data from heterogeneous sources, applying data transformation logics and updating them into databases with less than 1% of defect leakage.
* Tested both backend and frontend features of Web app, Native app in SeeTest for automated mobile testing and ran scripts for multiple devices to achieve 30% increase in usage and 50% increase in performance of Mobile App.
* Validated output of ETL jobs in Tableau dashboards to ensure accuracy and integrity of data within data warehouse.
Projects
Data Science: R
Credit Card Customer Segmentation
Nowadays, credit cards are the most used tool to pay for services and foods and also to borrow money, and make big purchases using EMI (Equated Monthly Installment), and are also useful in emergency situations.The Motivation behind performing the credit card customer segmentation is that the financial institutions can optimize the marketing strategy based on customer preferences and can reduce marketing costs and stop unnecessary marketing which doesn’t align with customer interests and due to the user-friendly deals the customers are happy and will remain using the company’s services and also it helps in the company to increase the customer base due to customer-tailored services.
This project includes Data preprocessing, Exploratory data analysis, and then we have performed the clustering using different clustering techniques like K-Means Clustering, Hierarchical Clustering along with creating interactive R Shiny dashboard.
Cryptocurrency Price Prediction using ARIMA
Cryptocurrency is a new form of asset which is used for paying or investing digitally. The upsurge in the various cryptocurrency prices over the past 10 years has increased the curiosity of researchers and investors to analyze and forecast its prices in the future. The primary focus of this research is to develop an Autoregressive Integrated Moving Average (ARIMA) model, which is a time-series statistical model, for forecasting the cryptocurrency prices. This research focuses on six different cryptocurrencies – Bitcoin, DogeCoin, Ethereum, Binance Coin, XRP and Cardano due to their popularity, and discusses the price movements and the stability of these cryptocurrencies using various exploratory data analysis techniques and visualization techniques. The dataset for these six coins has been collected from Kaggle datasets and has been merged into a single dataset. In this research, the dataset has a record of the prices of these six cryptocurrencies dated from 2018 to 2021.
Data Science: Python
Predicting Review Scores on Pitchfork
H1B Visa Prediction Analysis
H1-B visas are a type of non-immigrant visa for foreign national professionals who wish to work in the United States. As of FY 2022, there were around 308,613 H-1B registrations from 37,000 prospective petitioners. The visa requires the applicant to have an employment letter which indicates their legal employment in order to file an application to the US immigration service (USCIS). The number of applications approved by USCIS yearly should not exceed 85000 but the non-immigrants who wish to work in United States are outnumbered recently. The selection of the visa process is based on lottery; hence, it is crucial to understand the case status movements from the past years and to analyze which all factors thus affecting the approval of the visa. In this project, we have performed various exploratory data analysis to understand the trends and variation of H1-B visa application certification to help both the employee and the employer.
Database Model Query Language: SQL
Airbnb backend database creation
As the urge of people towards exploring the world keeps on increasing, not only the famous cities but also exotic suburban places are also getting flooded with tourists. Over the past few years (pre-covid), tourism is at boom enabling people to visit and explore the places worldwide. Airbnb has turned into an extremely famous decision among explorers all over the planet for the sort of novel encounters that they give and furthermore to introducing an option in contrast to expensive lodgings. Airbnb does links landlords and tourist visitors by providing an accommodation. The problem that we are going to address is eliminating the inconsistency in Airbnb dataset by creating and normalizing the database system provides efficiency in storing and accessing the huge amount of data and provides hassle free user interface to the users. Normalization using BCNF and query analysis are performed for the dataset.
</span>