Binita Roy
IT Specialist | Data Analyst | Machine Learning Engineer
Dresden, Germany
Certified Data Analyst and Data Engineer with expertise in Python, R, SQL, and tools like Snowflake, Airflow, Azure Data Factory, Databricks, Azure Synapse Analytics, Azure SQL Database, CI/CD, dbt, and Power Apps. Skilled in ETL pipelines, machine learning, deep learning, and Power BI. Passionate about leveraging data-driven solutions for impactful business insights and innovation.
Skills
Languages
Data & BI
Machine Learning
Cloud
Professional Experience
Certified Data Analyst and Data Engineer skilled in ETL pipelines, machine learning, and BI platforms (Power BI), contributing to scalable and efficient solutions.
Infineon Technologies
Data Analyst (Part-time)
Germany
- •KNIME: Data preparation (cleaning, joins, transformations) and workflow automation to build repeatable, end-to-end data pipelines.
- •Tableau: Interactive dashboards for KPI tracking, calculated fields, and stakeholder-ready reporting.
- •Change-point statistical analysis: Detecting structural breaks in time series (e.g., shifts in mean/variance) for monitoring, anomaly detection, and regime identification.
- •Jira & Confluence: Agile issue tracking and structured project/technical documentation to support cross-team collaboration and delivery.
Tekscend Photomask (formerly Toppan Photomask)
Application Engineer (Part-time)
Dresden, Saxony, Germany · On-site
- •To support technical customer support engineering by handling daily operational tasks, preparing customer reports, optimizing KPIs, and creating (semi-)automated reporting solutions.
- •To organize and reliable with strong data management skills, experience with XML, and use of Power BI, and Power Apps.
Leibniz-Centre for Agricultural Landscape Research (ZALF)
Master Thesis Student, collaboration with SKW Stickstoffwerke Piesteritz GmbH
Müncheberg, Germany
- •Preprocessed, analyzed, and visualized agricultural datasets using Python, improving data quality and uncovering actionable insights.
- •Increased winter wheat yield prediction accuracy by 30% through machine learning models and used explainable AI to reveal key yield drivers (soil/weather), enabling data-driven fertilization strategies.
- •Key Impact: Optimized nitrogen application strategies, reducing resource waste and boosting crop yields.
Data Mine BD LTD
Data Analyst
Dhaka, Bangladesh
- •Extracted, analyzed, and visualized sales and operational data using SQL, Python, Microsoft Azure and Power BI, driving a 15% increase in regional sales through actionable insights.
- •Automated data pipeline and reporting workflows using Azure Data Factory and Power BI, reducing manual reporting time by 30% and improving decision-making efficiency for energy, textile, retail, pharmaceutical, E-commerce, and other industries.
- •Designed ETL pipelines to integrate and transform data from multiple sources into a centralized Snowflake data warehouse, ensuring data accuracy and enabling seamless analytics for tracking KPIs across energy and other industries.
Featured Projects
Passionate about leveraging data-driven solutions for impactful business insights and innovation. Seeking opportunities in data-focused roles, contributing to scalable and efficient solutions.
Comparing Machine Learning Variable Selection Approaches for Agricultural Prediction in Germany
This thesis is part of the StaPrax-Regio Project, a collaborative initiative that aims to improve agricultural outcomes through innovative fertilization strategies tailored to site-specific soil and conditions.
Modeling Car Insurance Claim Outcomes
Identifies the best predictors of whether a customer will make a car insurance claim using logistic regression by analyzing client demographics, vehicle attributes, and policy data.
Fault Prediction of New Energy Vehicles With Machine Learning and Deep Learning
An end-to-end machine learning pipeline for predicting faults in New Energy Vehicles using Random Forest, Gradient Boosting, and deep learning models, integrated with MLflow for model tracking.
Retail Analytics Pipeline
Implements a full retail analytics pipeline—from data ingestion through cleaning, transformation, and reporting—to generate actionable business insights.
Energy & Sustainability
Leverages machine learning and deep learning techniques to predict energy consumption, emphasizing the incorporation of renewable energy factors to support sustainability goals.
BMW Sales Data Analysis and Insights
Analyzes BMW sales data from 2019 to 2023 to uncover insights into sales trends, channel performance, and regional revenue patterns.
Trends of Covid-19 Outbreaks
Uses T-SQL to analyze trends in COVID-19 outbreaks across regions and over time, providing insights into the progression and impact of the pandemic.
The World Bank's International Debt Data Analysis
Exploratory data analysis of World Bank international debt data stored in a PostgreSQL database, investigating total debt by country and category through SQL queries.
Sales Dashboard
A Power BI project visualizing global sales data from the Global Superstore via an interactive dashboard to derive meaningful business metrics.
Sales and Profit Analysis with Power BI
Develops a dynamic, interactive dashboard in Power BI to visualize sales and profit trends over the years across various locations.
Air Quality Analysis
Examines the effects of CO2, methane, and nitrous oxide on air quality and how exposure varies by region, income group, and development status across 184 countries (1990-2019).
Comparing Machine Learning Variable Selection Approaches for Agricultural Prediction in Germany
This thesis is part of the StaPrax-Regio Project, a collaborative initiative that aims to improve agricultural outcomes through innovative fertilization strategies tailored to site-specific soil and conditions.
Modeling Car Insurance Claim Outcomes
Identifies the best predictors of whether a customer will make a car insurance claim using logistic regression by analyzing client demographics, vehicle attributes, and policy data.
Fault Prediction of New Energy Vehicles With Machine Learning and Deep Learning
An end-to-end machine learning pipeline for predicting faults in New Energy Vehicles using Random Forest, Gradient Boosting, and deep learning models, integrated with MLflow for model tracking.
Retail Analytics Pipeline
Implements a full retail analytics pipeline—from data ingestion through cleaning, transformation, and reporting—to generate actionable business insights.
Energy & Sustainability
Leverages machine learning and deep learning techniques to predict energy consumption, emphasizing the incorporation of renewable energy factors to support sustainability goals.
BMW Sales Data Analysis and Insights
Analyzes BMW sales data from 2019 to 2023 to uncover insights into sales trends, channel performance, and regional revenue patterns.
Trends of Covid-19 Outbreaks
Uses T-SQL to analyze trends in COVID-19 outbreaks across regions and over time, providing insights into the progression and impact of the pandemic.
The World Bank's International Debt Data Analysis
Exploratory data analysis of World Bank international debt data stored in a PostgreSQL database, investigating total debt by country and category through SQL queries.
Sales Dashboard
A Power BI project visualizing global sales data from the Global Superstore via an interactive dashboard to derive meaningful business metrics.
Sales and Profit Analysis with Power BI
Develops a dynamic, interactive dashboard in Power BI to visualize sales and profit trends over the years across various locations.
Air Quality Analysis
Examines the effects of CO2, methane, and nitrous oxide on air quality and how exposure varies by region, income group, and development status across 184 countries (1990-2019).
Languages
Multilingual communication skills enabling global collaboration and diverse project execution.
Bengali
English
German
Deutsch Akademie
Education
Academic qualifications and degrees
Technische Universität Dresden
Master of Science, Computational Modelling and Simulation
2024 - Present
Brandenburgische Technische Universität Cottbus-Senftenberg
Master's Degree, Environmental Resource Management
Oct 2019 - Jun 2024 | Grade: 1.7
Main Subject Fields:
Master's Thesis:
"Development of Machine Learning Models for Predicting Winter Wheat Yield in Germany"
Thesis Grade: 1.1 | 10% accuracy improvement over existing models
University of Rajshahi
Master's Degree, Biochemistry and Molecular Biology
2017 - 2018
Main Subject Fields:
Skills:
R • Data Analysis • Biostatistics • Molecular Biology • Bioinformatics
University of Rajshahi
Bachelor of Science, Biochemistry and Molecular Biology
2012 - 2016
Main Subject Fields:
Skills:
R • Molecular Biology • Bioinformatics • Statistical Data Analysis
Certifications
Professional credentials and industry certifications demonstrating expertise and commitment to continuous learning.
Accredited / Professional Certifications
DataCamp Certified: Data Engineer, Data Analyst, and AI Fundamentals
Oct. 2024, Dec. 2024, Jan. 2025
IBM Data Engineering Professional Certificate
2025
Certifications by Tool or Technology
Let's Build Something Amazing Together
Ready to collaborate on data-driven solutions, cloud architecture, or innovative analytics projects?