| | | 20,000+ Fresh Resumes Monthly | |
|
|
| |
Click here or scroll down to respond to this candidateCandidate's Name
PHONE NUMBER AVAILABLE EMAIL AVAILABLE Candidate's Name shreeStreet Address
EDUCATIONIndiana University Bloomington, Indiana May Street Address
Master of Science, Data ScienceSt Joseph Engineering College (VTU), Mangalore, India May Street Address Bachelors in Computer Science and EngineeringTECHNICAL SKILLSProgramming Languages: Python, R, Java, Scala, C, JavaScript, HTML5, CSS33, Linux Bash Libraries/ Frameworks: NumPy, Pandas, SciKit, NLTK, TensorFlow, Pytorch, SpaCy, OpenCV, Shiny, Streamlit, Shiny Tools and Technologies: Azure Data Factory, DataBricks, SQL Server, Git, Jenkins, Microsoft Power Platform, AWS Data Science Competencies: Statistics, Predictive Analytics, Time Series, Hypothesis Testing, ETL pipelines, NLP, LLMs Certifications: Data Science with Python (Coursera, Authorized by IBM) PROFESSIONAL EXPERIENCEIndiana University Bloomington May 2023 May 2024 Graduate Associate Instructor Indiana, USA Co-designed the coursework for INFO-I399 Data Science with Python, integrating machine learning and data modelling frameworks, and guided over 100 students through the material, culminating in a 92% satisfaction rating Tata Consultancy Services (TCS) Client: CIBC June 2020 July 2022 Data Science Engineer Python, Java, Hibernate ORM, Flask, Oracle SQL Server, Git, Jenkins, Jira,Azure Mumbai, India Leveraged logistic regression and decision tree classification algorithms in Python to precisely evaluate borrower creditworthiness using key financial metrics like credit scores and debt-to-income ratios, enhancing the Lending Case Management System's capacity to handle 38 million records and accelerating credit assessment processes by 15% Enhanced loan processing and approval efficiency by implementing advanced mortgage rules using Java Servlets, J2EE, and JSPX with Hibernate ORM, reducing processing times from 20 days to 17 days and achieving 99% compliance accuracy Restructured REST APIs and optimized ETL workflows in Oracle SQL Server for the Financial Risk Management module, cutting data retrieval times by 20% (from 5 seconds to 4 seconds). Enhanced risk assessments by conducting A/B testing and Monte Carlo simulations, utilizing SciPy and StatsModels for robust statistical analysis Directed a server infrastructure upgrade by configuring and deploying Apache Tomcat and Oracle DB, implementing complex unsecured loan rules in Chordiant (PEGA), utilizing Bash shell scripts and UNIX utilities for health checks and automation, and enhancing CI/CD processes with Git and Jenkins, achieving a 15% reduction in response time (from 200ms to 170ms) Partnered with the CIBC business & OSFI team facilitating data migration to Azure with a 40% increase in data accessibility Just Compile LLP (TrainIT) April 2020 August 2020 Data Science and Engineering Intern Python, SQL, Tableau, Spark, Hadoop Mumbai, India Pioneered a predictive model using Python and SQL, leveraging linear regression and time series analysis to improve forecast accuracy from 75% to 90% and boost investment yields by 10% for a financial services provider Integrated Spark and Hadoop to streamline data processing, reducing data fetch issues and network trips, enhancing processing efficiency by 30%, and elevating visualization clarity by 25% using Tableau PROJECTSAI Investment Advisor with LLM & LangChain IBM Watson, LangChain, Llama_2_70B, Serper API Integrated IBM Watson and LangChain with the Llama_2_70B LLM model to enhance an AI Investment Advisor, offering real-time investment insights to deliver strategic investment insights across 500+ stock tickers Automated financial data collection from Yahoo Finance and Google News through the Serper API, enhancing processing efficiency by 30%, established a secure vector data store and implemented the Retrieval Augmented Generation Assessment System (RAGS) to optimize financial advice accuracy and personalization Impact Analysis of COVID-19 on US Job Market using BLS Data XGBoost, GridSearchCV, Azure Data Factory Conducted a large scale Exploratory Data Analysis (EDA) on a Bureau of Labor Statistics dataset of over 1 million records Employed XGBoost for Decision Trees, leveraging GridSearchCV for hyperparameter tuning and SHapley Additive exPlanations (SHAP) for feature analysis, achieving an F1-score of 0.87 Designed a real-time dashboard using Power BI with an Azure SQL Database backend, integrating data pipelines via Azure Data Factory. Utilized time-series decomposition for data analysis, enhancing decision-making with a 95% confidence interval Real-Time Anomaly Detection in Cloud Systems AWS Lambda, Kinesis, S3, CloudWatch, Elasticache Engineered a cloud-based anomaly detection system on AWS using Lambda, Kinesis, and S3, boosting detection accuracy and effectively categorizing 24.6% of devices as malicious and 75.4% as benign Optimized system architecture employing AWS CloudWatch for monitoring and automated alerts, and Elasticache to enhance data retrieval speeds, improving system responsiveness and reliability in detecting anomalies ACCOMPLISHMENTS Winner of GT-IDEA Spring '24 Case Competition: Anticipating & Addressing Challenges with AI Business Solutions |
