Subrite Sarker
Dhaka, Bangladesh +880********** *************@*****.*** github.com/Sarker112473 PROFESSIONAL SUMMARY
Aspiring Data Analyst with an academic background in Computer Science and hands-on experience working with data analysis, data preprocessing, visualization, and machine learning projects. Experienced in using SQL, PostgreSQL, Excel, Python, and Tableau to explore datasets, identify patterns, and present meaningful insights. My academic research and projects have strengthened my ability to clean and analyze data, evaluate results, and approach problems in a structured way. I am interested in using data to understand business problems, support decision-making, and develop practical, data-driven solutions. TECHNICAL SKILLS
Languages: Python, SQL
Data Analysis: Excel, NumPy, Pandas, Data Cleaning, Exploratory Data Analysis (EDA), Data Visualization Visualization: Tableau
Databases: PostgreSQL
Web: HTML, CSS
Data ang Analytics: Statistical Analysis, Data Mining, Clustering, Predictive Modeling Tools: GitHub, VS Code, Google Colab, Kaggle
PROJECTS
Occupancy Detection Python, Machine Learning [GitHub] 2026
• Analyzed an occupancy detection dataset containing 20,560 records and 8 features to identify patterns related to room occupancy.
• Performed data preprocessing and exploratory analysis to prepare the dataset for machine learning.
• Implemented and evaluated Random Forest and KNN classification models for occupancy prediction.
• Achieved 99.32% accuracy with Random Forest and 99.37% accuracy with KNN on the evaluated dataset. IMDb–Netflix Analysis Python, SQL, Tableau, Excel [GitHub] 2026
• Cleaned, preprocessed, and merged Netflix and IMDb datasets using Python and performed exploratory data analysis.
• Used SQL to analyze datasets, answer business questions, and identify content trends and patterns.
• Built an interactive Tableau dashboard with KPIs, filters, and visualizations to communicate analytical insights.
• Used Excel for data analysis and supporting data preparation and reporting. Netflix Data Analysis with SQL PostgreSQL, SQL [GitHub] 2026
• Analyzed Netflix data using SQL in PostgreSQL and pgAdmin 4 to answer business and content-related questions.
• Applied JOIN, GROUP BY, CASE, CTEs, and window functions to filter, aggregate, and analyze structured data.
• Identified patterns and trends across Netflix titles and attributes through SQL-based analysis. RESEARCH PROJECTS
Physical Rehabilitation Score Prediction Using Deep Learning: LSTM, 3D-CNN and Conv3D Performance Nov 2022 – Dec 2024 Python, Machine Learning, Deep Learning, LSTM, 3D-CNN, Conv3D [GitHub]
• Collected and organized video data from different groups, building a dataset of 9 exercise types with 80 videos per class and 9 CSV files containing expert assessment scores.
• Applied LSTM, 3D-CNN, and hybrid Conv3D (LSTM+CNN) models to predict rehabilitation assessment scores ranging from 0–100.
• Split the dataset into 80% training and 20% validation/testing sets to evaluate model performance consistently.
• Evaluated models using RMSE, MAD, and MAE; the hybrid Conv3D model achieved the best performance for most exercise classes.
• Tested the models on new data and maintained the project implementation and code on GitHub. EDUCATION
Stamford University Bangladesh Dhaka, Bangladesh
B.Sc. in Computer Science and Engineering (GPA: 3.25/4.00) 2024 Keraniganj Girls’ High School and College Dhaka, Bangladesh H.S.C. (GPA: 3.50/5.00) 2018
Cambrian School and College Dhaka, Bangladesh
S.S.C. (GPA: 4.11/5.00) 2016
CERTIFICATIONS & LANGUAGES
Certification: Deloitte Data Analytics Job Simulation – Forage [Certificate] Languages: English, Bengali (Native)