Data Analyst Power Bi

SNEHA SURESH SHINDE

**************@*****.*** +1-216-***-**** LinkedIn San Diego, California

Professional data analyst with 3+ years of experience in data mining, analysis and engineering. Proficient in using data analytic tools like Power BI, Tableau, Excel and SQL. Provided data driven solutions to improve the sales of insurance documents by 30%. Have experience working with cross-functional team helping to establish data pipelines and provide ADHOC reports as needed. Education

Cleveland State University 2021-2023

Master’s in Electrical and Computer Science Engineering Mumbai University 2015-2019

Bachelor’s in Electronics Engineering

Technical Skills

• Languages: Python(Pandas,NumPy, SciPy, MatPlotLib), SQL, R

• Tools: Tableau, Microsoft Power BI, Jira, Power point, MS Excel (Pivot Table, VLOOKUP, VBA, Macros, Adhoc Analysis).

• Database: MS SQL Server, Salesforce, My SQL, MS Access Golden. Work Experience

Med impact Healthcare Solutions July 2023 - Present

• Utilized SQL, Python (Pandas) to perform ETL and load data into the target tables which enabled effective reporting and data requirements.

• Automated reporting system using SQL and Excel VBA to streamline data extraction and analysis, improving reporting time by 30%.

• Create ad hoc reports and views on a frequent basis to assist management in understanding, researching and analysing issues.

• Extensively use Time-series analysis in Power BI to predict the sales of insurance documents. Use DAX to transform data to required format, Provide technical support for existing reports and dashboards.

• Cleansed and pre-processed 10,000 rows using Pandas in Python to prepare data for analysis and gain insights on client performance, resulting in a 25% reduction in data processing time.

• Building dashboards and reports using KPIs and metrics to assess business performance and drive daily decisions.

• Adhere to industry best practices in ensuring compliance with HIPAA data policies. My Digital Shelf August 2019 – July 2021

• Implemented and maintained administrative systems and used SQL Server to store, query and manage data of clients. Documented the data requirements and system changes into detailed functional specifications and performed Extraction, Transformation and Loading (ETL) using Oracle SQL Server and Excel Functions.

• Interpret trends in complex data sets by finding correlations between them and visualizing the results using SQL and Tableau.

• Utilized Microsoft Excel functions such as Vlookup, Concatenate, Sumifs, and Pivot Tables for data analysis.

• Developed Pivot Charts to track qualitative and quantitative trends for business decision-making.

• Created 3 KPIs to identify market trends and actionable insights including which customer markets to target based on customer activity.

Academic Projects

House Price Data Analysis and Prediction Model: (Python, Pandas, Numpy, Scikit-learn, Matplotlib, Data Mining)

• Developed Machine Learning Models to predict the final price of each home which would help the potential home buyers to buy their dream house.

• Designed the different stages of machine learning pipeline such as data extraction, data cleaning, and model building, training and testing using different frameworks of Python.

• Evaluated model performance using metric such as accuracy resulting in Random Forest to deliver the highest accuracy of 89% as compared to Linear Regression and Decision Tree.

Customer Churn Analysis Using Python: (Python, ETL, pandas, Seaborn, Numpy, Data Mining, Data Visualization)

• Designed machine learning models to predict how likely will a customer churn by analysing the relevant customer data

• Pre-processed data by applying different feature engineering techniques like one-hot encoding, missing data imputation, variable transformation, outlier engineering and date/time engineering.

• Created varied visualizations in order to identify interesting insights of data using python libraries like seaborn, matplotlib and plotly.

• Evaluated model performance using metrics such as accuracy where Gradient Boosting performed the best producing an accuracy of 80% as compared to other models such as logistic regression, decision tree, random forest, knn. Google Play Store Analysis (Tableau)

• Performed Qualitative Data Analysis on the Google play store data using Tableau to identify the segmentation, correlations or any unique patterns in data.

• Achieved the results showing from 2015 to 2018 that among the category section family, game was most updated.

• Among the genre of app tools and entertainment were the most popular helping the app developers to make meaningful decision.

Contact this candidate