Data Analyst Power Bi

Krushi Hirenbhai Patel

DATA ANALYST

Chicago USA +1-516-***-**** mailto:***************@*****.*** Linkedin SUMMARY

Experienced Data Analyst with a strong background in the financial and healthcare sectors, skilled in providing actionable insights to drive business decisions. Proficient in SQL, Python, and SAS for data analysis, and adept at creating interactive dashboards with Tableau and Power BI. Successfully led projects that reduced fraudulent claims by 15% and optimized financial reporting processes, achieving significant time savings. SKILLS

Methodologies: SDLC, Agile, Waterfall

Language: Python, SQL, R

Packages: NumPy, Pandas, Matplotlib, Seaborn, ggplot2, SciPy, Scikit-learn, TensorFlow Visualization tools: Tableau, Power BI, Advanced Excel (Pivot Tables, VLOOKUP) Cloud Technology: Amazon Web Services, Microsoft Azure, Google Cloud Platform Database: MySQL, SQL Server, PostgreSQL, MongoDB, Oracle IDEs: Visual Studio Code, PyCharm, Jupyter Notebook Other Skills: SSIS, SSRS, Machine Learning Algorithms, ETL Tools, Statistics, ServiceNow, Snowflake, SAS, SPSS, Hadoop, Spark, Alteryx, Probability distributions, Intervals, ANOVA, Advance Analytics, OLAP & OLTP, SAS, MS Office Suite (Microsoft Word, PowerPoint, MS Visio), Hypothesis Testing, Regression Analysis, Linear Algebra, Advance Analytics, Google big query, Data Mining, Data Visualization, Data warehousing, Data transformation, Data Storytelling, Data Integration, Data Interpretation, Data Pipeline, Association rules, Clustering, Classification, Regression, A/B Testing, Forecasting & Modelling, Data Cleaning, Data Wrangling, Git, GitHub Version Control: Git, GitHub

Operating System: Windows, Linux, Mac OS

EDUCATION

Master of Science, Health Informatics – DePaul University, Chicago, USA Bachelor of Science in Microbiology – J.N.M. Patel Science College, India WORK EXPERIENCE

Data Analyst Baylor Scott & White Health Dallas, TX Mar 2024 - Present

• Spearheaded a data analytics project aimed at optimizing the patient appointment scheduling process, addressing the critical issue of no-show rates to improve overall healthcare delivery and patient satisfaction.

• Leveraged SQL to extract, manipulate, and aggregate data from relational databases, writing complex queries that reduced processing time by 30% and ensured high data quality for subsequent analyses.

• Developed dynamic, interactive dashboards using Tableau, allowing stakeholders to easily visualize data trends and insights. This facilitated quicker decision-making and strategy formulation at various management levels.

• Employed Python and libraries such as Pandas and Scikit-learn to create predictive models that analyzed patient behavior patterns, enabling proactive strategies for patient engagement and attendance forecasting.

• Utilized Apache Spark to process and analyze large datasets (over 100,000 records) efficiently, allowing for faster computations and real-time insights compared to traditional data processing tools.

• Developed complex DAX measures to calculate key performance indicators (KPIs) related to patient appointment metrics, such as no-show rates and average wait times, providing stakeholders with actionable insights.

• Used FHIR resources, such as Patient and Appointment, to standardize representation of patient information & appointment details, enhancing data consistency across systems by approximately 30%, which improved data interoperability and reduced discrepancies in patient records.

• Leveraged Snowflake’s elasticity to scale computing resources on-demand, enabling efficient processing of complex queries. Data Analyst Accenture India Aug 2020 - Nov 2022

• Worked on a critical project to enhance the risk assessment framework for a leading financial services client, targeting improvements in credit scoring methodologies to minimize loan default rates and enhance portfolio quality.

• Employed Python for comprehensive data cleaning and preprocessing tasks, implementing techniques such as data normalization, imputation of missing values, and outlier detection to ensure data integrity and enhance model performance.

• Developed custom reports in Power BI that highlighted critical risk indicators and default probabilities, facilitating data-driven discussions among decision-makers and improving the quality of decision-making by approximately 35%.

• Leveraged SQL to efficiently extract and manipulate data from a complex relational database containing over 10,000 loan applications, ensuring precise data retrieval for thorough analysis and reporting.

• Developed and refined predictive models using Scikit-learn, employing various machine learning algorithms such as logistic regression, decision trees, and ensemble methods to accurately predict loan default probabilities based on applicant characteristics.

• Used Amazon Redshift as the primary data warehousing solution to store and manage large volumes of loan application data, ensuring high performance and scalability, which resulted in a 40% reduction in query processing time and improved data retrieval efficiency.

• Utilized Matplotlib to create a variety of static and animated visualizations of loan application data, enhancing interpretability of datasets.

• Designed and implemented A/B testing methodologies to evaluate the effectiveness of different credit scoring models, comparing performance metrics to identify the best approach.

• Set up automated alert systems in Excel using VBA to notify stakeholders of critical changes in risk metrics or data anomalies.

Contact this candidate