Data Analyst Machine Learning

Ritik Naresh Raut

DATA ANALYST

Alabama, USA 205-***-**** *****.*.*****@*****.*** LinkedIn

SUMMARY

• Skilled Data Analyst with 4 years of experience specializing in data ingestion, transformation, and advanced analytics to support data-driven business decisions across healthcare and SaaS domains.

• Proficient in developing robust ETL pipelines and managing large-scale data workflows using modern cloud platforms including AWS Glue, Redshift, and S3 for scalable data processing.

• Experienced in applying statistical methods and machine learning techniques such as logistic regression, survival analysis, and gradient boosting to build predictive models for customer behavior and risk assessment.

• Adept at feature engineering and exploratory data analysis using Python libraries (pandas, NumPy, matplotlib, seaborn) and SQL to derive actionable insights from complex datasets.

• Strong expertise in designing interactive dashboards and visualizations using Tableau and Power BI to communicate analytical findings effectively to business stakeholders and cross-functional teams.

• Skilled in implementing explainable AI frameworks, leveraging tools like SHAP to enhance model transparency and drive trust among users and decision-makers.

• Collaborative team player with experience working in Agile environments, coordinating closely with Data Engineering, Product, and Customer Success teams to translate analytics into impactful business strategies.

• Knowledgeable in data governance, quality assurance, and compliance standards, ensuring data integrity and adherence to organizational policies throughout the analytics lifecycle. SKILLS

Data Analysis & Statistics: Descriptive & Inferential Statistics, Hypothesis Testing, ANOVA, T-Test, Chi-Square Test, A/B Testing, Correlation & Regression Analysis, Time Series Forecasting, Cohort Analysis Programming Languages: Python, R, SQL

IDEs: Visual Studio Code, PyCharm, Jupyter Notebook Packages: NumPy, Pandas, Matplotlib, SciPy, Scikit-learn, TensorFlow, Seaborn, dplyr, ggplot2, Keras Database Technologies: MySQL, PostgreSQL, SQL Server, MongoDB, Cassandra, Snowflake Data Visualization: Tableau, Power BI, Looker, Google Data Studio, Matplotlib, Seaborn, Plotly ETL & Data Pipeline Tools: Apache Airflow, Alteryx, SSIS, Informatica, Talend, dbt (Data Build Tool) Cloud Platforms: AWS (S3, Redshift, Athena, Lambda) Business Intelligence: KPI Design, OLAP, Dashboarding, Ad-hoc Analysis, Funnel Analysis, Root Cause Analysis, Churn Analysis, Marketing Mix Modeling

Machine Learning: Supervised & Unsupervised Learning, Clustering, Decision Trees, Logistic Regression, Random Forests, Model Validation, Feature Engineering Excel & Productivity Tools: Advanced Excel (Power Query, Power Pivot, Index-Match, PivotTables, VBA), Google Sheets, Microsoft Office Suite, Notion, Confluence Data Governance & Security: Data Quality Management, Data Privacy (HIPAA, GDPR), PII Masking, Access Control, Audit Logs, Compliance Reporting

Agile & Collaboration: Agile Methodology, Scrum Framework, Jira, Trello, Azure Boards, Git, GitHub, Bitbucket, Slack, Zoom, Microsoft Teams

Soft Skills: Cross-Functional Collaboration, Problem Solving, Critical Thinking, Stakeholder Communication, Requirements Gathering, Presentation Skills, Documentation, Mentorship WORK EXPERIENCE

Centene Corporation Alabama, USA

Data Analyst Jan 2024 – Present

• Consolidated over 12 million Medicaid and Medicare claim, encounter, and pharmacy records from SQL Server and Snowflake into a single analytical dataset, achieving 99.8% data accuracy through rigorous validation.

• Cleaned and standardized large-scale healthcare datasets using Python (pandas, NumPy) to resolve missing values, normalize diagnosis/procedure codes, and align provider identifiers, reducing preparation time by 35%.

• Designed SQL-based transformation logic to create patient-level timelines, enabling accurate sequencing of claims, pharmacy fills, and care management events for predictive modeling.

• Developed over 25 patient risk indicators, including 90-day readmission counts, chronic disease scores, emergency visit frequency, and medication adherence metrics, significantly improving model input quality.

• Collaborated with data science teams to train and validate XGBoost and LightGBM models, achieving an AUC of 0.87 for predicting 7, 14, and 30-day unplanned readmissions.

• Utilized SHAP (SHapley Additive Explanations) to identify key readmission drivers such as uncontrolled diabetes, recent ER visits, and multiple chronic conditions, translating results into actionable insights for clinical staff.

• Integrated Social Determinants of Health (SDoH) data including housing instability, food insecurity, and transportation gaps into the scoring pipeline, increasing high-risk patient identification recall by 12%.

• Automated daily ETL workflows using SSIS and SQL stored procedures to refresh risk scores and deliver them to the care coordination platform within two hours of claim ingestion, enabling same-day outreach.

• Designed interactive Tableau dashboards displaying patient risk rankings, regional heat maps, and top contributing factors, allowing care managers to target 28% more high-risk members without additional staffing.

• Tracked program impact through KPI monitoring in Tableau and Excel, demonstrating a 6.5% reduction in 30-day readmissions in pilot regions and providing ROI metrics to executive leadership.

• Created comprehensive data dictionaries, transformation documentation, and audit-ready artifacts to maintain compliance with NCQA and CMS quality reporting standards.

Druva Software India

Data Analyst Oct 2020 – Mar 2023

• Ingested multi-source customer data including backup frequency logs, restore activity records, license utilization metrics, billing history, and NPS survey results from Druva’s SaaS platform into AWS S3 using scheduled extraction jobs.

• Designed and maintained AWS Glue ETL pipelines to clean, standardize, and merge telemetry, support ticket histories, and subscription data, loading the processed datasets into Amazon Redshift for modeling and analytics.

• Utilized Amazon Redshift Spectrum to query over 500 million historical records directly from S3, reducing analytical query runtimes by 60% and enabling rapid model retraining

• Conducted detailed exploratory data analysis in Python (pandas, NumPy, matplotlib, seaborn) and SQL to uncover churn indicators such as declining backup success rates, increasing restore latency, and unresolved high-priority support cases.

• Created over 50 engineered features from operational metrics, including backup job failure ratios, license underutilization percentages, and SLA adherence scores, enhancing model input quality and improving predictive accuracy.

• Developed churn prediction models using logistic regression, survival analysis, and XGBoost in Python (scikit-learn, xgboost), achieving an 87% accuracy rate and detecting churn risk 22% earlier than previous methods.

• Implemented SHAP-based model explainability to generate account-level churn drivers, enabling Customer Success teams to apply targeted retention strategies with quantifiable business impact.

• Built interactive Tableau dashboards presenting churn probabilities, customer health scores, retention trends, and upsell opportunities, reducing account review time by 40% for Customer Success Managers.

• Deployed automated churn alerts via AWS Lambda integrated with Salesforce CRM, triggering notifications within 24 hours of risk detection, improving proactive outreach response times by 35%.

• Partnered with Data Engineering, Product, and Customer Success teams to operationalize model outputs, contributing to an 18% increase in renewal rates among high-risk accounts. EDUCATION

Master of Science in Computer Science

University of Alabama at Birmingham, Alabama, USA

Bachelor of Engineering in Computer Science and Engineering Nagpur University, Nagpur, India

Contact this candidate