PARESH CHOUDHARI

** ******* **, ******, ** ***** +1-857-***-**** adyrts@r.postjobfree.com LinkedIn EDUCATION

Northeastern University May 2023

Master of Science in Data Analytics Engineering GPA: 3.7 Relevant Coursework: Database Management, Data Mining, Machine Learning, Neural Networks and Deep Learning Nagpur University June 2018

Bachelor of Engineering in Mechanical Engineering

PROFESSIONAL EXPERIENCE

Clustor Computing Data Analyst Intern May 2022 – August 2022

• Data Cleaning and EDA: Cleaned sales & operations data for analysis and identified, analyzed, and interpreted trends and patterns leveraging SQL to boost sales by 10% and used Tableau to build dashboards for stakeholders

• ML Modeling: Established classification and regression models for various business problems and established metrics to measure effectiveness of data-driven decisions to reduce process delivery time by 5% and expand sales

• Model Deployment: Worked with web development team to generate a pipeline, deploy, manage, and granting scalability to ML models on Elastic beanstalk, delivering real-time metrics to management team and customers

• Implementation of Data-Driven Results: Modified existing process for operations team utilizing operation management principles and analysis of operations data, removing bottleneck, and reducing overall operation process delivery by 40%, resulting in increased customer satisfaction and retention Unisys Teleinfra Pvt Ltd. Data Analyst May 2019 – August 2021

• Data collection and cleaning: Fetched data via API from website, cleaned, and normalized it into internal storage format. Utilized Python for data analysis, mining, and metrics analysis, resulting in an 18% boost in overall process efficiency

• Web Scraping: Assessed website content using SEMRUSH to track rankings and accelerate site performance by 10%

• ETL and ML: Designed AWS Glue solution for ETL and business intelligence, improving data integration efficiency by 16% and delivering data to Redshift. Employed sentiment analysis NLP to classify customer feedback

• Dashboard Development: Generated advanced QUICKSIGHT dashboards to maximize customer’s unit KPI by 14%

• Project Management: Involved in administration tasks such as setting permissions, managing ownership, and providing access to users in JIRA resulting in overall increase in work management efficiency by 15%. Collaborated with client to acquire functional business requirements, issues and created complex JIRA workflow integrating Agile methodologies Tirpude College of Social Work Data Research Analyst July 2018 – April 2019

• Data Analysis: Assembled CDS system to predict breast cancer, performed feature engineering, MICE applying decision trees for data imputations, SMOTE to balance data and modeled via XGboost giving unparalleled accuracy rate of 79%

• Metrics Analysis: Obtained best accuracy of 94.82%, sensitivity of 95.41%, specificity of 93.07% and ROC score of 94.64%

• ML Modeling: Proposed Machine learning-based feature selection with Stacking to enhance predictive performance by 18%. Employed PCA to retain more than 95% of whole features variance for data by enacting 11 eigen values ACADEMIC PROJECTS

Sematic content recommendation system using amazon SageMaker: (Skills: Amazon SageMaker, S3) May 2023

• Trained and launched models using SageMaker Neural topic model and K-Nearest Neighbor model (KNN) algorithms

• Initiated data pipeline using SageMaker pipeline to automate the process Hotel Booking Cancellation Prediction in Python : (Skills: Python, R, Microsoft Excel) May 2022

• Reviewed preformation of models and chose the one that best suits dataset based on 70% train data and 30% test data

• Applied Python prediction models on dataset with a 93% prediction accuracy to predict cancellations on bookings Garage Management System in SQL : (Skills: SQL, MS VISIO, BIG Data) December 2021

• Developed RDBMS system using Oracle SQL from scratch; executed Date Modeling using MS VISIO

• Harnessed concepts of Joins, partitions, and PL/SQL Cursors to load data in normalized tables TECHNICAL SKILLS

• Programming Tools : Python, R, SQL query, MS-Excel, Jira Atlassian, Microsoft office, Pytorch, pyspark, tensorflow

• Cloud technologies : AWS (S3, EC2, Glue, Sagemaker, Athena, Aurora, Kinesis, DMS RedShift, EMR), GCP

• BI Tools : Power BI, PowerPoint, Tableau, AWS Quicksight, Semrush, Google Cloud Platform (GCP)

• Database : MySQL, Oracle SQL Developer, Relational database, MongoDB, BigQuery, NoSQL, Neo4j

• Machine Learning : Scikit-Learn, Pandas, Classification, predictive model, artificial intelligence, data visualization

• Other Skills : Innovation, attention to detail, communicate, problem-solving, networking, leadership

Contact this candidate