Shakera Khandaker Sahee
EXPERTISE
BIO
I’m a Data Analyst and Machine Learning enthusiast with 4+ years of experience in data analytics, dashboard development, and database management. Skilled in Python, SQL, Power BI, and machine learning techniques, I’ve worked on real-world projects involving customer segmentation, predictive modeling, and business intelligence. I value clear communication, remote collaboration, and delivering data-driven insights that help clients make smarter decisions.
WORK EXPERIENCE
Database Administrator
Walton Hi-Tech Industries PLC
October 2020 - Present
- Managing and administering mission-critical databases (Oracle, SQL Server, MySQL, MariaDB, PostgreSQL, MongoDB). - Implementing reliable backup and disaster recovery strategies to ensure data resilience. - Performance optimization through advanced indexing, query tuning, and resource management. - Ensuring high availability with clustering, replication, and failover configurations. - Leading seamless database migrations and upgrades with minimal downtime. Now expanding into data analysis and data science, I’m building expertise in extracting insights and building data-driven solutions using: - Python (pandas, scikit-learn, matplotlib, seaborn) - SQL for complex querying and data manipulation - Data visualization and storytelling - Machine learning workflows, from data preprocessing to model deployment
EDUCATION
B.Sc in Engineering
Mawlana Bhashani Science and Technology University, January 2020
Ict
CERTIFICATIONS
Data Visualization and Dashboards with Excel and Cognos
IBM
Issued: 5/1/2025
Credential ID: https://www.coursera.org/account/accomplishments/verify/890E90Q4PBHY
Python for Data Science, AI & Development
IBM
Issued: 5/1/2025
Credential ID: https://www.coursera.org/account/accomplishments/records/HLP63QCKQ25I
Data Science & Machine Learning with Python
Ostad
Issued: 12/1/2024
Credential ID: https://ostad.app/share/certificate/a26201-shakera-khandaker
Informatica Tutorial: Beginner to Expert Level
Udemy
Issued: 3/1/2021
Credential ID: ude.my/UC-f0f46de8-f60e-4980-b3c0-b86720dfc71c
SQL for Data Science
Coursera
Issued: 10/1/2020
Credential ID: https://www.coursera.org/account/accomplishments/certificate/W7MJSBWQLUBU
Data Analyst with Python Track
DataCamp
Issued: 3/1/2020
Credential ID: https://www.datacamp.com/statement-of-accomplishment/track/4a22221b944c8748af0559935b646b256d9a1d74
Data Scientist with Python Track
DataCamp
Issued: 3/29/2020
Credential ID: https://www.datacamp.com/statement-of-accomplishment/track/964f5b7fc9206af8482de815473a2c86f6805e80
PORTFOLIO PROJECTS
Wine Quality Prediction Project
This project focuses on evaluating and comparing multiple machine learning models to predict the quality of white wines based on physicochemical tests. The Wine Quality dataset was analyzed, and several classification models were built and compared to determine the best-performing algorithm.
View Project4/29/2025 -Present
Real World Data Customer Segmentation
This project serves as a practical example of an unsupervised machine learning application in customer segmentation, demonstrating the end-to-end process from data preprocessing to cluster analysis. It provides valuable insights into how businesses can leverage clustering techniques to understand their customer base better and tailor their services accordingly.
View Project3/29/2025 -Present
Time-series-Analysis
This project focuses on forecasting Tesla's stock prices using various time series modeling techniques. The primary objective is to evaluate and compare the performance of different models to determine the most effective approach for accurate stock price prediction. Based on the evaluation metrics, the SVM model outperforms the other models in forecasting Tesla's stock prices, followed by the RF and LSTM models. The ARIMA model, in contrast, underperforms significantly, indicating that it is unsuitable for this particular dataset.
View Project3/29/2025 -Present
Churn Data Analysis
This project focuses on understanding and predicting customer churn using a dataset that includes customer behavior, demographics, and subscription details. The primary objective is to identify key factors contributing to churn and develop predictive models to assist businesses in retaining customers. This project exemplifies a standard data science workflow, encompassing data cleaning, exploratory analysis, and predictive modeling, aimed at providing actionable insights into customer retention strategies.
View Project2/28/2025 -Present
Verified Machine Learning Engineer
3-5 years of experience
Preferred commitment: Full Time
Languages
Skills
Impressed by Shakera Khandaker Sahee's profile?
Take the next step and bring this top talent to your team
Hire Shakera for your team