Tanvi Venkatesh

Analytical professional with technical knowledge and critical thinking skills to thrive in data-driven environments. Bringing strong work ethic and excellent organizational skills to any setting. Tackles challenges with positivity and drive to overcome. Works great alone or with others and consistently exceeds expectations.

• Programming Languages: Python, SQL, R. 

• Tools & Frameworks: Excel, Excel Solver, Jupyter Notebook, Power BI, Power Query, Tableau, Oracle Database, MySQL Database, Microsoft SQL Server, DAX, PostgreSQL, PowerPoint, Office 365. 

• Skills: : Data Management, Data Structures and Algorithms, Data Mining, Data Analytics, Machine Learning, Deep Learning, Data Visualization, Database Management, Financial Analysis, MicroStrategy, Time Series Analysis, Data Modeling, Big Data, NumPy, Pandas, Database Design, Supply Chain Analytics, Data Cleaning, Testing, Relational Database Management, ETL Tools, Communication, Teamwork, Decision Making, Data Cleaning, Statistical Methods.

• Certifications: Python Programming [University of Michigan], HTML and CSS [University of Michigan], Data Structures [University of Michigan], Web Designing [University of Michigan], Data Manipulation using SQL [Data Camp], Data analytics [Cisco], Business Analysis and Process Management [Coursera], Mongo DB [Datacamp]. 

Time Series Forecasting  (Sep 2023 - Dec 2023)

• Applied a range of time series techniques on seasonal and non-seasonal data, optimizing forecasting of the data.

• Conducted ARIMA modeling, AD-Fuller test, ACF, PACF, and residual analysis in Python, increasing prediction accuracy by

25% and reducing logistics costs.

Enhanced OCR System (Sep 2023 - Dec 2023)

• Achieved an Automated Check MICR Line Extraction System using OpenCV for image processing and Tesseract for OCR, extracting MICR lines from check images.

• Created a financial document management process by automating extraction of crucial banking information with 82.2%

accuracy.

Graduate Student Admission Prediction (Feb 2023 - Apr 2023)

• Analyzed and explored a machine learning approach to predict students’ likelihood of gaining admission to a master’s degree program, offering advance insights of admission prospects with an efficiency of 84%.

• The machine learning models encompassed linear regression, logistic regression, decision tree, and random forest techniques.

World Happiness Report (Feb 2023 - Apr 2023)

• Conducted a comprehensive analysis of global happiness levels and applied the science of happiness to elucidate variations at both personal and national levels.

• Incorporated a range of statistical techniques, including ANOVA, Tukey’s method, t-test, linear regression, and regularization methods, leading to a compelling conclusion with an R2 score of 85%.