Learn Data Skills
Beta
Rakesh Raj Sonkamble

Rakesh Raj Sonkamble

Data Analyst

Cigna Healthcare | New Jersey

Technologies

My Portfolio Highlights

My New Course

Introduction to Tableau

My New Course

AWS Concepts

My New Course

Introduction to Python

My New Course

Introduction to Tableau

Data curator, carefully curating insights like precious artifacts.

My Certifications

These are the industry credentials that I’ve earned.

Other Certificates

LinkedIn SQL Essential Training

LinkedIn Using SQL with Python

LinkedIn Machine Learning with Scikit-Learn

LinkedIn Python for Data Visualization

Microsoft Azure Data Engineer DP-203

Amazon AWS Certified Data Engineer – Associate

TrendyTech Cloud Big Data Engineer

DataCamp Course Completion

Take a look at all the courses I’ve completed on DataCamp.

Courses

Introduction to Python
Introduction to SQL
Introduction to Power BI
Intermediate SQL

My Work Experience

Where I've interned and worked during my career.

Cigna HealthCare | Jan 2023 - Present

Data Analyst

• Queried large datasets from Cigna’s Electronic Health Record (EHR) system using SQL to analyze patient admission, discharge, and readmission data, identifying trends, bottlenecks, and opportunities for operational enhancements. • Led a project to streamline the HEDIS reporting process by automating the data extraction from Epic's Clarity database, reducing reporting time by 30%. • Designed real-time Tableau dashboards to visualize critical metrics such as patient flow and readmission rates, empowering hospital administrators and healthcare providers to make timely, data-driven decisions. • Supports internal population based medical management data efforts by performing the clinical and cost based analysis of medical and EPIC data using SAS. Population data include Medicare and Medicaid. • Utilized Python with libraries like Pandas and NumPy for data cleaning, preprocessing, and transformation, ensuring data consistency and quality for further analysis and modeling. • Assist with performing various analyses relating to Medicaid engagements, including the analysis of medical claims data to identify fraud, waste or abuse of Medicaid or other health care system funds. • Leveraged Alteryx to integrate various data sources, including databases, cloud services, and flat files, enabling comprehensive data analysis. • Developed and validated predictive models using machine learning techniques (logistic regression) in Python to forecast patient readmissions, improving discharge planning and follow-up care processes. • Ensured compliance with data privacy laws (HIPAA) by implementing robust data security practices, maintaining 100% compliance during internal audits. • Delivered actionable insights that contributed to a 15% reduction in hospital readmissions over six months, optimizing post discharge care strategies based on model predictions. • Leveraged AWS Glue to automate ETL processes, streamlining data ingestion from multiple sources, including EHR systems, and preparing the data for secure analysis. • Conducted statistical analysis on healthcare data, identifying key factors influencing patient readmissions and aiding in the refinement of care strategies to reduce unnecessary hospital stays. • Ensured HIPAA compliance by implementing secure data handling practices, ensuring proper de-identification of sensitive patient data during analysis. • Analyzed hospital resource allocation and patient flow data, offering operational recommendations that resulted in a 10% increase in efficiency by better aligning resources with patient care needs. • Collaborated with healthcare professionals, including doctors and administrators, to convert data insights into actionable improvements in patient care quality, ensuring alignment with organizational objectives. • Experience with Medicare or Medicaid reimbursement, including cost reports, Medicare DSH and/or Medicare bad debts, is a significant advantage. • Led sprint planning sessions to prioritize tasks related to data extraction, machine learning model development, and dashboard creation, ensuring the timely delivery of valuable insights to enhance healthcare operations.
Show More

Capgemini | Oct 2018 - Dec 2021

Data Analyst

•Developed dynamic, real-time Power BI dashboards to visualize key financial metrics such as credit default rates, fraud detection scores, and customer risk levels, enabling stakeholders to track performance and make informed, data-driven decisions. • Utilized advanced Python techniques to preprocess raw data by addressing outliers, scaling numerical variables, and performing feature engineering, resulting in a 25% improvement in the accuracy and efficiency of predictive models. • Reduced credit defaults by 15% by developing predictive models that provided actionable insights into high-risk customers, enabling more informed decision-making and better risk management strategies. • Improved fraud detection accuracy by 20% by implementing advanced machine learning models that flagged potentially fraudulent transactions in real-time, reducing fraudulent activities and financial losses. • Implemented machine learning algorithms, including logistic regression and random forests in Python, to predict credit defaults and identify high-risk customers, optimizing decision-making for loan approvals and fraud detection. • Automated regular reporting and data extraction processes using SQL, ensuring stakeholders received up-to-date insights on customer credit risk and fraud detection without manual intervention. • Employed R for statistical analysis, applying techniques such as regression analysis, hypothesis testing, and ANOVA to assess factors influencing loan defaults, fraud detection, and customer behavior. • Leveraged Apache Spark to process large-scale transactional and customer datasets efficiently, enabling faster data analysis and forecasting for financial and risk assessments. • Leveraged AWS S3 to store large-scale transactional and customer data, ensuring scalable, secure, and cost-effective data storage for historical financial records and real-time transactional data. • Addressed missing or inconsistent data points during exploratory data analysis (EDA), applying imputation techniques and outlier removal, leading to a 30% improvement in data quality and integrity for further analysis. • Implemented data validation rules in the ETL pipeline to ensure data integrity, reducing data errors by 25% and ensuring that only records meeting quality standards were loaded for analysis. • Conducted A/B testing to evaluate the effectiveness of different fraud detection algorithms, measuring key metrics like false positives and detection rates to select the most accurate model for real-time fraud detection. • Created line charts and time series visualizations using Matplotlib to track financial metrics, such as loan default rates and transaction volumes, enabling stakeholders to quickly identify trends and patterns over time. • Used Excel to analyze large financial datasets, generating summary reports, pivot tables, and charts to monitor key performance indicators (KPIs) like loan defaults, transaction volumes, and credit risk scores. • Provided actionable insights that optimized the client’s operational processes, leading to better resource alignment, more accurate credit evaluations, and overall improvements in financial performance.

My Education

Take a look at my formal education

Master's in Data ScienceUniversity of New Haven | 2023
Bachelors in Information TechnologySreenidhi Institute of Science and Technology | 2016

About Me

Rakesh Raj Sonkamble

• Data Analyst with 5 years of expertise in leveraging Python, R and SQL, and data visualization tools like Tableau and Power BI to extract actionable insights from complex datasets.

Powered by

  • Work
  • Certifications
  • Courses
  • Experience
  • Education
  • About Me
  • Create Your Data Portfolio for Free