NANDA KUMAR G
Email: [email protected] | Phone: 8056252276 | Location: Chennai-600061
SUMMARY
Aspiring Data Scientist with a strong foundation in research and data analysis. Proficient in python, SQL and Machine Learning
algorithms, with hands on experience data analysis and data driven problem solving.
EXPERIENCE
Senior Engineer – Digital Solutions, at Larsen and Tubro (L&T) Chennai Jul,2023 – Present
• Digital twin development- mathematical process models were developed and integrated in python to simulate the STP plant
operation and evaluate efficiency for different plant configurations.
• Developed a regression model to predict the Oxygen/Aeration rate based on inlet parameters and able to reduce the air blower
power consumption by 15% on average for 24 hr operating window.
• Working in a phased manner on building a backend code in Python, to perform process design calculations in designing of
wastewater treatment plants.
PROJECTS
M.Tech Thesis: May,2023
• Developed and optimized Random Forest, and XG Boost models to predict the mechanical properties such as young’s modulus,
yield stress, stress at break of elastomers.
• Data Processing: Cleaned and pre-processed data by handling outliers, imputing missing values, encoding categorical features,
standardizing numerical features, and removing redundancy via correlation analysis. Stratified sampling was used to construct
a strongly representative training and test set.
• Optimized the hyperparameters using hyperopt library and increased the model accuracy score from R2= 0.86 to R2= 0.94
Skills: Python, Libraries- Pandas, Mahine Learning, Scikit Learn, Hyperopt, Matplotlib, EDA, Statistics.
Kaggle Projects:
• Insurance rate analysis
Analyzed the data set and found the customer traits that affect the insurance rates, profiled the customers based on various
categories. Created a multiple linear regression model to predict insurance rates and key drivers are identified.
Insights: Smoking, Age, BMI, and the number of children are statistically significant factors that increase the insurance rate
Skills: EDA, univariate, Bivariate analysis, Box plot, Excel Pivot chart, Regression in excel, Regression output analysis.
EDUCATION
• M.Tech-Chemical Engineering, IIT Kharagpur, CGPA: 8.55/10, 2023
• B.Tech- Chemical Engineering, SASTRA Deemed to be University, CGPA: 7.78/10, 2020
CERTIFICATIONS
• IBM-Data analyst Professional Certificate | Coursera
Gained foundational understanding of data analytics. Obtained hands on experience on data wrangling, statistical analysis and
data visualization by completing the capstone project.
Skills: Python- Pandas, Matplotlib, EDA, Descriptive statistics, Excel-Look ups, Filters, Pivot table, Charts.
• SQL Server And Power BI for Data Analytics | Udemy
Skills: SQL- Joins, Aggregate Functions, Subqueries, Power BI- Report Creation, Interactive Dashboards.
KEY SKILLS
• Analytical: Problem Identification, Problem Decomposition, Exploratory Analysis, Data visualization.
• Technical: Proficient in Python programming, SQL, experienced with Microsoft SQL Server
• Data Tools: Python-pandas, MS Excel, Power point presentation, Reports, Charts
• Machine Learning: Scikit Learn, Model Training Pipelines, HyperOpt, XGBOOST, Random Forest, Mathematics of
algorithms, Feature engineering.
COURSEWORK
• Chemical Engineering: Advanced Fluid Mechanics, Heat and Mass Transfer, Advanced Mathematics.
• Electives: Machine Learning, Optimization Techniques, and Statistics for Data analytics.
AWARDS AND ACHIEVEMENTS
• Received Dean's Merit List Scholarship for top 10% performance, B.Tech Chemical Engineering, SASTRA University, 2018-
19
• Qualified for GATE examination in Chemical Engineering, AIR 1172, 2021
ADDITIONAL LINKS
• Hacker Rank SQL Badge
• ETL Data Pipeline Fundamentals
