Sahil Dubey
Data Analyst
975-***-**** *************@*****.***
Profiles Sahil Dubey
Sahildubey08
GitHub
Summary Eager to apply a unique blend of client-side business acumen and technical data skills to solve challenging analytical problems. Proficient in transforming complex datasets into actionable insights using SQL, Python, Power BI, and Tableau. Experienced in the full data lifecycle—from cleaning and preprocessing to visualization and predictive analytics—with a strong foundation in statistical analysis and machine learning. Experience ICICI PRUDENTIAL
Key Relationship Manager
June 2023 - Present
Aligarh
Performed quantitative and qualitative analysis on a client base of 200+ to assess financial needs, driving data-informed recommendations for investment products that increased policy conversion rates by 15%.
Analyzed client portfolio performance and market trends to develop and present personalized investment strategies, resulting in a 20% increase in customer retention and enhanced portfolio value.
Leveraged data from client interactions and policy reviews to identify cross-selling and up-selling opportunities, boosting revenue from existing clients by 18% and improving client satisfaction scores by 25%.
Education Master in CS AI & ML Woolf University Advance Certification in Full Stack Data Science
May 2025- Present
GLA University
Business Analytics & Marketing
2021-2023
MBA
Projects Amazon Product Case Study May - June 2025
Document link
Conducted research and analysis on order management, inventory, and customer workflows, improving process efficiency by 20% in simulated scenarios. Designed scalable schema structures and ER diagrams simulating operations for 5 Million active users, ensuring efficiency in handling large datasets. Recognized in the top 5 performers for innovative schema design and effective problem-solving approach.
SQL, Schema Design, Database Management, ER Modeling AiR BnB Booking Analysis Tableau Dashboard May - June 2025
GitHub link
Analyzed hotel booking datasets using Tableau, creating an interactive dashboard that increased efficiency by 25% to find insights and diagnose the root cause. Applied Pandas concepts in Google Colab to clean and engineer data, enhancing analysis accuracy by 20% and Utilising Tableau calculated fields to create measures and calculated columns.
Examined hotel performance, including year-over-year booking revenue growth of 10%, room type preferences, and guest stay trends and provided visibility on supply and demand across different regions.
Pandas, Data Cleaning, Data Preprocessing, Python, Tableau Paisabazaar Banking Fraud Analysis August - September 2025
Colab Link
Performed exploratory data analysis (EDA) on 50K+ banking transactions, identifying fraud patterns and anomalies with 92% accuracy.
Applied data wrangling, feature engineering, and statistical techniques, reducing noise and improving data quality by 30%.
Utilized Python (Pandas, NumPy, Matplotlib, Seaborn) to visualize fraud trends, enabling detection of 20% more high-risk transactions compared to baseline. Python, Pandas, NumPy, Matplotlib, Seaborn, Data Visualization, EDA Machine Learning Project: Glassdoor Salary Prediction System October - November 2025
Colab Link
Built comprehensive data pipeline processing 10K+ job listings with feature engineering including salary extraction, experience level categorization, and text analysis of job descriptions
Engineered 100+ features using TF-IDF for job descriptions, one-hot encoding for categorical variables, and numerical feature scaling Implemented and compared 4 ML models (Random Forest, Gradient Boosting, Linear Regression) achieving R score of 0.85 and RMSE of $12,500 on salary predictions Machine Learning, Data Engineering, Deployment, Feature Engineering Skills Technical Skills
Languages: Python, SQL BI & Visualization: Tableau, Power BI, Excel, Matplotlib, Seaborn Data Analysis: Pandas, NumPy, Statistical Analysis, EDA, Predictive Analytics Data Management: Database Management, ER Modeling, Schema Design Data Processing: Data Cleaning, Data Wrangling, Feature Engineering, BeautifulSoup Python, SQL, Excel, Tableau, Power BI, Machine Learning Certifications Machine Learning Project: Glassdoor Salary Prediction System AlmaBetter Edutech Pvt. Ltd.
November - 2025
Certificate link
Paisabazaar Banking Fraud Analysis
AlmaBetter Edutech Pvt. Ltd.
September - 2025
Certificate link
Air BnB Booking Analysis Tableau Dashboard
AlmaBetter Edutech Pvt. Ltd.
June - 2025
Certificate Link
Amazon Product Case Study
AlmaBetter Edutech Pvt. Ltd.
July - 2025
Certificate Link