About Me
An analytical and data driven Business Analytics graduate student adept at employing analytical techniques and data-driven methodologies. Experienced in conducting comprehensive data analysis, implementing business intel…
An analytical and data driven Business Analytics graduate student adept at employing analytical techniques and data-driven methodologies. Experienced in conducting comprehensive data analysis, implementing business intelligence solutions, and applying advanced machine learning methods. Proficient in utilizing SQL, Python, R, Tableau, Power BI, SAS, and Adobe Analytics to extract meaningful insights. Skilled in collaborating with cross-functional teams and delivering compelling presentations to stakeholders, showcasing actionable strategies and insights.
Experience
Senior Business Analyst Intern (SQL & Power BI)
Developed a comprehensive forecasting cashflow model in SQL for loan portfolios, incorporating all relevant cash flows
Facilitated cross-functional discussions to develop methodologies for converting organizational costs into individual loans
Created an automated Power BI dashboard that included a comparison of forecasted cash flow to actual cash flow, providing up-to-date information on the loan portfolio and insights for risk management and pricing decisions of the loans
Implemented an automated ETL (Extract, Transform, Load) process for monthly reports, reducing manual effort by 90%
The process involved data extraction and transformation using SQL and running the data into a centralized data model in Power BI
Data Science Intern (Python)
Conducted in-depth exploratory data analysis on 500,000 IT tickets, utilizing data visualization techniques to uncover patterns between various platforms
Gained valuable insights into the nature of breakdowns, resulting in informed decision-making
Optimized a Long Short-Term Memory (LSTM) Recurrent Neural Network forecasting model through hyperparameter tuning, achieving an accuracy of 85%
The machine learning model improved the IT management's incident resolution time
Developed a Neural Network-based classification model to categorize IT incidents into different levels
The incident management team utilized the machine learning model to prioritize incidents and reduce user downtime