(sep 2024 - oct 2024 )
Data Science and Machine Learning
Intern at YBI Foundation.
constcoder={name:'DhanaSekar',skills:['Python', 'Tableau', 'Deep Learning', 'Microsoft Power BI', 'SQL', 'Machine Learning', 'Data Visualization', 'NLP', 'TensorFlow'],hardWorker:true,quickLearner:true,problemSolver:true,hireable:function() {return(this.hardWorker&&this.problemSolver&&this.skills.length>=5);};};ABOUT ME
Who I am?
My name is Dhana Sekar. a skilled Data Scientist passionate about transforming data into actionable insights. I specialize in statistical analysis, machine learning, and data visualization, enabling me to uncover patterns and deliver data-driven solutions to complex problems. With a strong foundation in Python, SQL, and advanced data modeling techniques, I have a proven track record of optimizing processes and supporting strategic decision-making. I am dedicated to continuous learning and innovation, always striving to apply cutting-edge methodologies to drive impactful results
Experiences
(sep 2024 - sep 2024)
Data Scientist
Intern at BCGX Pvt.
(Jan 2024 - Present)
Self Employed
Insightful Data Solutions
Skills
Python
SQL
Pandas
NumPy
Matplotlib
Seaborn
Tableau
Power BI
Scikit-learn
TensorFlow
Keras
PyTorch
MongoDB
MySQL
Google Cloud Platform
Jupyter Notebook
Anaconda
Git
Python
SQL
Pandas
NumPy
Matplotlib
Seaborn
Tableau
Power BI
Scikit-learn
TensorFlow
Keras
PyTorch
MongoDB
MySQL
Google Cloud Platform
Jupyter Notebook
Anaconda
Git
PROJECTS
Bank Customer Chunk Model
constproject={name:'Bank Customer Chunk Model',tools: ['Python', 'Pandas', 'SQL', 'Tableau', 'Scikit-learn', 'Flask],myRole:Data Analyst,Description: I developed a Bank Customer Chunk Model that segments and categorizes bank customers based on shared characteristics, behaviors, and needs. This model allows banks to tailor products and services, improving customer satisfaction and operational efficiency. I utilized demographic, psychographic, and behavioral data to create distinct customer segments, which informed targeted marketing strategies and personalized customer interactions.,};House Price Prediction Model
constproject={name:'House Price Prediction Model',tools: ['Python', 'Pandas', 'NumPy', 'Matplotlib', 'Seaborn', 'Jupyter Notebook],myRole:Data Analyst,Description: Developed a predictive model to estimate house prices based on various features such as location, size, number of bedrooms, and amenities. The project involved utilizing machine learning algorithms to analyze historical housing data and identify patterns that influence pricing. Key steps included data preprocessing, exploratory data analysis (EDA), feature selection, model training, and evaluation. I employed techniques such as linear regression, decision trees, and ensemble methods to achieve high accuracy in predictions. The model was evaluated using metrics like mean absolute error (MAE), root mean square error (RMSE), and R-squared values, leading to actionable insights for real estate stakeholders. This project demonstrated my ability to apply data science techniques to solve real-world problems and inform decision-making processes in the housing market.,};Cancer Prediction Machine Learning Model
constproject={name:'Cancer Prediction Machine Learning Model',tools: ['Python', 'scikit-learn', 'Pandas', 'NumPy', 'Matplotlib', 'Seaborn', 'Jupyter Notebook],myRole:Machine Learning Engineer,Description: Developed a machine learning model to predict the presence or absence of cancer using a set of medical features. The project aimed to assist healthcare professionals in early diagnosis and treatment planning. Key objectives included selecting appropriate algorithms, evaluating model performance with metrics like accuracy, precision, recall, and F1-score, and identifying significant features impacting predictions. Methodology encompassed data preprocessing (cleaning, normalization, and feature engineering), model selection (logistic regression, decision trees, random forests, SVMs, neural networks), and thorough evaluation using metrics and visualizations. Addressed challenges such as data imbalance and overfitting through techniques like oversampling, cross-validation, and model interpretability methods such as SHAP values.,};Creditworthiness Assessment Model
constproject={name:'Creditworthiness Assessment Model',tools: ['Python', 'scikit-learn', 'Pandas', 'NumPy', 'Matplotlib', 'Seaborn', 'Jupyter Notebook],myRole:Machine Learning Engineer,Description: Developed a predictive model to assess the creditworthiness of individuals using historical credit card data. The project aimed to analyze various factors such as credit history, income, and spending patterns to predict the likelihood of customer default on credit card payments. Key objectives included building an accurate machine learning model, identifying influential factors for credit card default, and improving risk assessment for financial institutions. Methodology encompassed data acquisition (gathering relevant datasets), data preparation (cleaning, feature engineering, and splitting), and model development (exploratory data analysis, feature selection, and hyperparameter tuning). Evaluated model performance with metrics like accuracy, precision, recall, F1-score, and AUC-ROC. Addressed challenges such as data quality issues and class imbalance through various techniques.,};Educations
2021 - Present
Bachelor Degree
Anna University ,Chennai
2019 - 2021
Higher Secondary Certificate
Lihannamani Matriculation School -Tiruppattur
2018 - 2019
Secondary School Certificate
Lihannamani Matriculation School -Tiruppattur