Data Analyst Machine Learning

Madhavi Mothe

Data Analyst

TX, USA *******.*****@*****.*** 313-***-**** LinkedIn

SUMMARY

• Data Analyst with over 4+ years of experience in leveraging Python, SQL, and SAS for data analysis, modeling, and predictive analytics.

• Skilled in handling diverse datasets and achieving exceptional data cleanliness through robust pre-processing techniques.

• Developed and implemented cutting-edge machine learning algorithms, resulting in an accuracy rate in predicting customer churn and loan defaults.

• Expert in data visualization using tools like Matplotlib, Seaborn, Tableau, and Power BI to present meaningful insights and drive data-driven decision-making.

• Demonstrated proficiency in time series analysis, forecasting, and regression, enabling precise predictions of customer behavior and market trends.

• Spearheaded a data quality improvement initiative, resulting in a reduction in data errors and enhancing the overall accuracy and reliability of business reports.

• Successfully integrated external data sources and utilized association rules and clustering techniques to enrich customer profiles and identify key factors influencing business outcomes. SKILLS

Programming Language: Python, SAS, Scala, R

Packages: NumPy, Pandas, Matplotlib, Seaborn, ggplot2, SciPy, Scikit-learn, TensorFlow Visualization Tools: Tableau, Power BI, Advanced Excel (Pivot Tables, VLOOKUP) IDEs: Visual Studio Code, PyCharm, Jupyter Notebook Database: MySQL, PostgreSQL, SQL, Oracle

Cloud Technologies: Amazon Web Services (AWS), Microsoft Azure, Google Cloud Platform Methodologies: SDLC, Agile, Waterfall

Tracking Tools: Jira, Microsoft Visio, HP Quality Center, JAD, Rational ClearQuest, RTM, UAT Other Technical Skills: Machine Learning Algorithms, CI/CD, Advance Analytics, Data Mining, Data Visualization, Data warehousing, ETL Processes, Data Integration, Data transformation, Association rules, Clustering, Informatica, Report Generation, Regression, A/B Testing, Forecasting & Modelling, Data Cleaning, Regression, Hypothesis Testing, Time Series Analysis, Data Wrangling, Critical Thinking, Communication Skills, Presentation Skills

Version Control Tools: Git, GitHub, Bitbucket

Operating Systems: Windows, Linux

EDUCATION

Master of Science in Computer Science - Western Illinois University, Macomb, Illinois, USA Bachelor of Technology in Computer Science and Engineering - Lovely Professional University, Punjab, India EXPERIENCE

Data Analyst United Healthcare, TX Aug 2022 - Present

• Worked on the extensive healthcare datasets using Python, employing libraries such as Pandas and NumPy for data manipulation, cleaning, and preprocessing tasks.

• Configured scheduled data refresh in Power BI to ensure that dashboards and reports are updated with the latest healthcare data automatically, maintaining data accuracy and relevance.

• Utilized AWS analytics services such as Amazon Athena and Amazon QuickSight for ad-hoc querying and visualization of healthcare data, enabling self-service analytics and exploration.

• Integrated Spark with various data sources including databases, data lakes, and streaming sources, facilitating seamless data ingestion and processing from multiple healthcare data streams.

• Designed and implemented dimensional data models such as star schemas and snowflake schemas to organize and structure healthcare data for efficient analysis and reporting.

• Quantified the cost savings realized through optimized care interventions and resource allocation, measured as a percentage reduction in healthcare costs compared to previous times.

• Employed Informatica PowerExchange for change data capture (CDC), enabling real-time replication and synchronization of healthcare data between source systems and the data warehouse.

• Conducted A/B testing to optimize messaging and communication strategies with patients or healthcare providers, like testing different versions of patient reminders or notifications to assess their effectiveness in improving appointment attendance or medication adherence. Data Analyst HCL Tech, India Oct 2018 - Aug 2021

• Applied advanced analytics techniques to analyze supply chain data and identify areas for improvement.

• Assisted in machine learning algorithms such as regression and clustering for demand forecasting and inventory optimization and developed models to predict demand patterns and automate inventory replenishment decisions.

• Conducted complex data analysis using SQL queries to identify trends, patterns, and anomalies in supply chain data which involved querying large datasets to derive actionable insights for optimization.

• Automated repetitive tasks and workflows using Python scripts, such as data extraction, transformation, and loading (ETL) processes, to streamline data management and analysis in the project.

• Integrated Kafka with other systems and databases within the supply chain ecosystem, enabling seamless data integration and synchronization across different applications and platforms.

• Implemented robust error handling and logging mechanisms in SSIS packages to identify and handle data integration errors, ensuring data integrity and reliability in the supply chain data pipeline.

• Connected Tableau to various data sources including databases, data warehouses, and flat files to access and analyze supply chain data in real-time, ensuring data freshness and accuracy in visualizations.

• Created subplots using Matplotlib to display multiple charts within a single figure, allowing for side-by-side comparisons of different supply chain metrics or KPIs.

• Applied conditional formatting in Excel to highlight important trends, anomalies, or outliers in the supply chain data, making it easier for stakeholders to identify critical issues and take corrective actions.

• Developed automated tests for data validation, ensuring the accuracy and quality of analysis results and tests could include data integrity checks, validation against business rules, and comparison with expected outcomes.

Contact this candidate