Dinesh Ram S

Data Science and Business Analyst with hands-on experience from multiple internships and 2 months of business analyst training. Proficient in Python, SQL, NumPy, Pandas, Power BI, and advanced machine learning techniques using XGBoost, LightGBM, and Deep Learning. Completed 10+ real-world projects, including AI chatbot development and predictive modeling. Skilled at transforming complex data into actionable insights to support strategic business decisions.

Business analyst training - SAT Connections - Salem

(2025-07 - 2025-08)

• Attended structured Business Analyst training focused on requirement gathering, stakeholder communication, and documentation.
• Analyzed different perspectives of Business Analysts and customers to understand user-centric approaches.
• Developed expertise in creating clear and structured business documentation covering functional and non-functional requirements.
• Gained hands-on knowledge of SDLC models, including Agile and Waterfall, to differentiate processes and project needs.
• Practiced business process modeling techniques and applied analytical frameworks to interpret stakeholder workflows.
• Enhanced requirement documentation through simulations, improving clarity and alignment with project goals.

Data science - Technest intern - Ahmedabad

(2025-06 - 2025-08)

Internship (Online mode)

• Data Pipeline Development: Designed and implemented automated data pipelines using Python, Pandas, and NumPy for data collection, cleaning, and transformation
• Exploratory Data Analysis: Conducted EDA on real-world datasets, handling missing values, duplicates, and visualizing trends using Matplotlib and Seaborn.
• Machine Learning Model Evaluation: Explored and evaluated multiple models using metrics like accuracy, precision, recall, and F1-score, improving performance through iterative tuning.
• Hyperparameter Tuning: Applied Grid Search and Randomized Search to optimize model performance, reduce overfitting, and enhance predictive accuracy.
• Optimization Modeling: Built linear programming models using PuLP/SciPy to solve real-world problems by defining objectives and constraints, improving decision-making.
• Deep Learning Projects: Developed neural network models with TensorFlow/Keras, including preprocessing, architecture design, training, and performance evaluation using loss curves and confusion matrices.

Data Science - CodeAlpha - Uttar Pradesh

(2025-05 - 2025-06)

Internship (Online mode)

• Iris Flower Classification: Built a classification model using supervised learning algorithms to predict flower species based on petal and sepal dimensions.
• Unemployment Analysis: Performed exploratory data analysis to identify unemployment trends and patterns using Python libraries like Pandas and Matplotlib.
• Car Price Prediction: Developed a regression model to predict car prices based on features such as mileage, brand, and fuel type.
• Sales Prediction: Built a predictive model to forecast product sales using historical data, improving understanding of business analytics and data-driven decision-making. [Certificate yet to receive].

Data Science intern - Exposys data labs - Bengaluru

(2024-12 - 2025-01)

Internship (Online mode)

• Task 1 – Custom Dataset Creation & Model Training. I created my own dataset using multiple data collection methods like web scraping, manual input, and synthetic data generation. After cleaning and preprocessing the data, I trained and evaluated machine learning models using Python libraries such as Pandas, Scikit-learn, and Matplotlib. This helped me understand the complete workflow from raw data to model development.
• Task 2 – Diabetes Prediction Project I developed a supervised machine learning model to predict diabetes based on medical features like glucose level, BMI, age, etc. Applied classification algorithms, evaluated performance using accuracy and a confusion matrix, and visualized results. This task deepened my understanding of real-world health data and binary classification.

Data Science - ybi foundation - New Delhi

(2024-08 - 2024-10)

Internship (Online mode)

• Data Preprocessing & Exploration: Cleaned and prepared the dataset using Python (Pandas, NumPy), handled missing values, encoded categorical features, and performed exploratory data analysis to identify key trends.
• Model Development & Evaluation: Built classification models using algorithms like logistic regression and random forest. Evaluated performance using accuracy, precision, recall, and a confusion matrix.

B.Tech - Information Technology - Knowledge Institute Of Technology (2025-01)