Skip to content

Himabindu Kambam

Data Engineer • Chicago, IL • k****************@gmail.com • +16******362 • drivetube.ai/•••••

Career Objective

Data Engineer with 0 years of experience seeking entry-level data engineering roles. Trained in Python and SQL with hands-on projects building data pipelines, preprocessing large datasets (1.3M records), and producing reproducible analytics and model-ready datasets using Pandas, NumPy, and SQL. Skilled in ETL concepts, feature engineering, data visualization (Tableau, Power BI), and collaborating to translate business requirements into data solutions.

Education

DePaul University, Chicago
Master of Science in Data Science • Chicago, IL • Expected December 2026
SRM Institute of Science and Technology, Chennai
Bachelor of Technology in Computer Science (Business Systems) • Chennai, India • 2023
Sri Chaitanya Jr Kalasala, Hyderabad
Higher Secondary (XII) • Hyderabad, India • 2019

Technical Skills

Programming Languages: Python
Frameworks and Libraries: Pandas,NumPy,Scikit-Learn,TensorFlow,Keras,PyTorch,Matplotlib,Seaborn
Databases: SQL,Relational SQL,Query Optimization,Joins and Window Functions
Data and Analytics: XGBoost,EfficientNet,Tableau,Power BI,Plotly,ETL,Data Cleaning,Feature Engineering,Exploratory Data Analysis,Dimensionality Reduction,Data Modeling
Tools and Methodologies: Jupyter Notebook,Git,Microsoft Excel
Statistics & Evaluation: Hypothesis Testing,ANOVA,Chi-Square Test,T-tests and Z-tests,Model Evaluation Metrics

Projects

Credit Card Fraud Detection
Tools Used: Python, Pandas, NumPy, Scikit-Learn, XGBoost, Statistical Testing, Feature Engineering, EDA
  • Processed and engineered features from a 1.3M-record credit card transactions dataset to create a model-ready dataset, handling missing values, outliers, scaling, and encoding using Pandas and NumPy.
  • Performed exploratory data analysis and statistical hypothesis tests to identify key predictors and relationships between transaction features and fraud labels.
  • Applied feature selection techniques and built baseline models (Logistic Regression, Random Forest, XGBoost) to compare performance and identify the best architecture for fraud detection.
  • Tuned and evaluated models using appropriate metrics for imbalanced data; achieved a top model accuracy of 99.78% on the selected evaluation split.
  • Produced cost–benefit analysis and mitigation recommendations tying detection performance to business impact and proposed multi-factor user verification improvements.
Enhancing Brain Tumor Diagnosis (CNN - EfficientNetB3)
Tools Used: Python, TensorFlow, Keras, EfficientNetB3, Image Preprocessing, Data Augmentation, Transfer Learning
  • Built a CNN classification pipeline using EfficientNetB3 and transfer learning to classify brain tumor images, applying preprocessing steps including normalization and augmentation for robustness.
  • Fine-tuned pre-trained weights on the domain dataset to improve sensitivity for early tumor detection while managing overfitting through regularization and augmentation.
  • Optimized model inference for performance to support near-real-time analysis, evaluating latency trade-offs for clinical deployment scenarios.
  • Implemented evaluation using appropriate image classification metrics and confusion analysis to validate clinical-relevant performance characteristics.
  • Outlined clinical integration considerations and ethical controls for patient privacy, fairness, and responsible model use in medical diagnosis workflows.
HR Analytics Dashboard (Power BI)
Tools Used: Power BI, SQL, Python, Pandas, Data Visualization, Employee Analytics
  • Designed and implemented an HR analytics dashboard in Power BI to monitor attrition, engagement, and productivity trends for HR stakeholders.
  • Prepared and transformed HR datasets using Pandas and SQL to compute turnover rates, engagement scores, and performance metrics for visual reporting.
  • Built interactive visuals to segment attrition by reason, tenure, and department enabling HR to identify patterns and target retention interventions.
  • Integrated survey-derived engagement scores and correlated them with performance and retention to highlight drivers of employee satisfaction.
  • Provided actionable visual KPI reports showing project completion rates and task efficiency to support workforce planning decisions.
Pizza Sales Report (Tableau)
Tools Used: Tableau, Data Visualization, SQL, Python, Sales Analysis
  • Developed a Tableau sales report to analyze menu performance, revenue, and customer order behavior across time and locations.
  • Computed KPIs including total revenue, average order value, and pizzas per order using prepared datasets to surface highest revenue-generating items.
  • Visualized temporal sales trends showing higher demand on weekends and evenings to inform staffing and promotion scheduling.
  • Highlighted top five revenue-generating pizzas and recommended focus areas for inventory and marketing optimization.
  • Suggested further analyses (day-of-week, monthly, and location-level decomposition) to support targeted business decisions.

Certifications

Python for Data Science — IBM
Using Basic Formulas and Functions in Microsoft Excel — Coursera
Introduction to Data Science — Cisco Networking Academy
Data Analytics Essentials — Cisco Networking Academy
Introduction to Data Studio — Google
Google Analytics Certification — Google
Getting Started with Google Analytics 360 — Google
Advanced Google Analytics — Google
Data Science Job Simulation — British Airways

Achievements

  • 8th place — Imarticus Learning Hackathon — 2023: Placed 8th in a competitive hackathon demonstrating practical problem-solving and technical delivery.

Powered by Drivetube · Create your own profile at drivetube.ai