Data Science Machine Learning

Nithin Raghava Ramachandra Narla

Mobile: 469-***-**** Email: *************@*****.*** GitHub: nithinnarla LinkedIn: nithinraghava Education

University of Illinois at Urbana-Champaign, IL

Master of Science in Information Management — Data Science GPA: 3.96/4.0 (August 2021 – May 2023) GITAM University, Visakhapatnam, India

Bachelor of Technology in Electronics and Communications Engineering GPA: 7.9/10.0 (July 2013 – August 2017) Technical Skills

Languages & Tools: Python, SQL, C#, Java, .NET, C++, PySpark, Tableau, ETL, KNIME, DAX, CPQ, MS Power Platform, GitHub, Jira, Confluence Databases: MySQL, PostgreSQL, Microsoft SQL Server, SQLite, Oracle RDBMS, MongoDB, Cassandra, DynamoDB, Neo4j Machine Learning and NLP: Regression, Classification, Clustering, K-Means, Sentiment Analysis, NLTK, Topic Modelling, Entity Extraction, Stanford NLP Data Science Libraries: Pandas, NumPy, Matplotlib, Seaborn, Scikit-learn, Folium, SciPy, Plotly, XGBoost, PyTorch, TensorFlow Big Data and Cloud Services: Microsoft Azure, Apache Spark, Amazon Web Services (AWS), HIVE, Snowflake, OpenRefine, Salesforce, Microsoft Copilot Work Experience

Data Science Engineer, Oak Technologies, Inc, Dallas-Fort Worth, TX (July 2023 – Present)

• Designed an Agile workflow in Lucidchart that aligned cross-functional teams, boosting sprint efficiency and saving 10+ hours per cycle

• Ingested and profiled a 130,000-record dataset using Azure Data Factory and pandas, improving data accuracy by 10% via automated validation logic

• Architected scalable data pipelines with Azure Data Factory, pandas, and scikit-learn, reducing data preparation time by 30% through automation

• Standardized and enriched unstructured data using regex, and Azure Databricks, ensuring clean, normalized datasets for analysis and reporting

• Imputed missing values and optimized data models using Azure SQL and Python, enhancing schema quality and speeding up query performance

• Devised budget forecasting models on historical data and deployed outputs to Azure Blob Storage, improving financial planning accuracy by 15%

• Wrote analytical SQL queries in Azure Synapse to uncover key business trends and KPIs, supporting proactive decision making across various sectors

• Developed interactive Power BI dashboards connected to Azure sources, reducing manual reporting by 40% and increasing insight accessibility

• Presented insights through trend analysis and reporting, increasing stakeholder engagement by 10% and enhancing cross-departmental decisions Data Science Intern, University of Illinois System, Champaign, IL (August 2022 – July 2023)

• Extracted Legislative Acts of 27,000 records from text data scraped from local news sources using Fuzzy Matching Method and Levenshtein Algorithm

• Utilized Python and web scraping tools for data acquisition from diverse sources such as public schools, geospatial systems, and ingested multi-year university credit card data for analytical modelling

• Engineered 150,000 records of data using Python’s Beautiful Soup to scrape news articles and performed natural language processing, text cleaning, feature extraction, and sentiment analysis

Software Developer Intern, Motorola Solutions, Chicago, IL (May 2022 – August 2022)

• Composed Motorola Solutions’ Employee Portal by leveraging Salesforce’s SOQL and SOSL queries, CPQ flow and Lightning Web components which shaped a pathway for internal employees to manage more than 5,000,000 orders and cases

• Built 3 RESTful API calls to CPQ’s data tables, saving $3,120,000 in revenue or 31,200 working hours per year for sales and pre-sales users and visualized the impact of these API integrations using a QlikView dashboard showing the cost savings and efficiency gains in a comprehensive and accessible way Data Engineer, Accenture (June 2019 – December 2020)

• Architected and deployed a scalable data pipeline framework using Azure Data Factory, consolidating lease incentive data into a centralized warehouse and driving $4.5M in operational savings through improved risk identification and reporting

• Spearheaded data profiling and metadata analysis (data types, lengths, patterns, quality checks) to validate ingested data, achieving a 60% improvement in processing efficiency via optimized Azure SQL functions and procedures

• Refactored ETL workflows, and SSIS packages, enabling weekly validation of 5M+ keys and reducing processing time by 520 hours per week

• Orchestrated a scalable data ingestion pipeline for loading JSON and Parquet files into HIVE tables, leveraging HiveQL queries to enable advanced analytics on a 100GB+ data warehouse

• Integrated Azure Synapse Analytics with ETL pipelines, reducing production database load times by 65% and accelerating executive reporting

• Developed and deployed a Power BI dashboard to monitor search engine KPIs, enhancing visibility and enabling a 90% improvement in client expenditure efficiency via anomaly detection

• Implemented an automated ML-based text mining solution using Azure ML, and Power Apps, cutting non-compliance surcharges by $1.2M annually

• Optimized legacy ETL processes and SQL queries, boosting overall system responsiveness and operational efficiency by 25% Associate Data Engineer, Accenture (May 2017 – June 2019)

• Created 32 SSIS packages to ensure data completeness between the legacy and new system, thereby saving 70% of the manual effort

• Enhanced transparency of networks performance by tracking key performance indicators through 5 visualization dashboards using Power BI; reported insights and anomalies which provided clearer understanding into opportunities Academic Projects

Uber vs Lyft Price Comparison (SQL, Python, MS Excel) (February 2022 – May 2022)

• Examined 6,500,000 records of ride-share data in the Boston area and compared pricing between Uber and Lyft based on distance, weather, and time

• Gathered, cleaned, and prepared the data using python, SQL, and Excel to perform statistical analysis to uncover trends and patterns

• Conducted linear regression, traffic analysis, and hypothesis testing to conclude what factors affect price the most Topic Modelling — World Health Organization (WHO) and Center for Health Informatics (SQL, Python, NLP) (September 2021 – December 2021)

• Analyzed COVID-19 misinformation on twitter data by implementing Topic Modelling and Natural Language Processing

• Applied Word2Vec and LDA algorithms to segregate topics based on English, Spanish tweets and PyLDAvis to visualize the relationship Certifications

• Microsoft Azure Data Engineer Associate (DP-203)

• Microsoft Power BI Data Analyst Associate (PL-300)

• Tableau Analyst and Data Scientist

• Microsoft Power Platform Developer Associate (PL-400)

• IBM Data Science Professional Certification

• AWS for Windows and Cloud Economics Digital

Contact this candidate