I am currently pursuing my M.Sc in Computer Science from Annai Vailankanni Arts and Science College, Thanjavur, affiliated with Bharathidasan University, and I am set to graduate in 2026. I have built several projects in machine learning and deep learning, including a housing price prediction model, a product categorization system, and a medical image segmentation project using PyTorch and OpenCV. My strongest skills include Python, SQL, Pandas, XGBoost, Lightgbm, Seaborn, NumPy, Matplotlib, and Visual Studio Code. I am aiming to become an ML Engineer and contribute to impactful AI solutions.
Education
Annai Vailankanni Arts and Science College, Thanjavur | Bharathidasan University
M.Sc in Computer Science
2024 – 2026 · Grade: 76%
Maruthupandiyar College of Arts and Science College, Thanjavur | Bharathidasan University
Developed a regression workflow to predict continuous housing sale prices from property-related features. Performed data cleaning, preprocessing, exploratory data analysis, correlation analysis, and outlier inspection. Built and compared Linear Regression and Ridge Regression models to study regularization, multicollinearity, and overfitting. Applied feature scaling and used GridSearchCV / cross-validation to tune the Ridge regularization parameter (alpha). Evaluated model performance using R², MAE, MSE, and RMSE and interpreted the comparative results.
Multi-Class Product Categorization Using Random Forests
Python
Pandas
NumPy
Scikit-learn
TF-IDF
Random Forest
Matplotlib
Seaborn
Developed a machine learning model to classify e-commerce products into multiple categories using product titles, descriptions, prices, and brands. Implemented text vectorization using TF-IDF and categorical feature encoding for data preprocessing. Trained a Random Forest classifier and evaluated its performance using accuracy, precision, recall, F1-score, and a confusion matrix. Visualized category distribution and feature importance to analyze model behavior. Saved the trained model using Joblib for future product category predictions.
Collaborative Learning of Augmentation and Disentanglement for Semi-Supervised Domain Generalized Medical Image Segmentation
Python 3.9
Visual Studio Code
PyTorch
Torchvision
OpenCV
Albumentations
NumPy
Matplotlib
Development of a 2D medical image segmentation system. Training with limited labeled datasets. Multi-domain learning simulation. Evaluation using Dice coefficient and IoU metrics. Applicable to MRI, CT, and ultrasound imaging.
Jaison Samuel Raj J
Final-year M.Sc Computer Science student at Annai Vailankanni Arts and Science College, Thanjavur | Bharathidasan…
Chennai · https://www.linkedin.com/in/jaison-samuel-raj-j-4b06332bb?utm_source=share_via&utm_content=profile&utm_medium=member_android
About
I am currently pursuing my M.Sc in Computer Science from Annai Vailankanni Arts and Science College, Thanjavur, affiliated with Bharathidasan University, and I am set to graduate in 2026. I have built several projects in machine learning and deep learning, including a housing price prediction model, a product categorization system, and a medical image segmentation project using PyTorch and OpenCV. My strongest skills include Python, SQL, Pandas, XGBoost, Lightgbm, Seaborn, NumPy, Matplotlib, and Visual Studio Code. I am aiming to become an ML Engineer and contribute to impactful AI solutions.
Education
Annai Vailankanni Arts and Science College, Thanjavur | Bharathidasan University
2024 – 2026
M.Sc in Computer Science · Grade: 76%
Maruthupandiyar College of Arts and Science College, Thanjavur | Bharathidasan University
Developed a regression workflow to predict continuous housing sale prices from property-related features. Performed data cleaning, preprocessing, exploratory data analysis, correlation analysis, and outlier inspection. Built and compared Linear Regression and Ridge Regression models to study regularization, multicollinearity, and overfitting. Applied feature scaling and used GridSearchCV / cross-validation to tune the Ridge regularization parameter (alpha). Evaluated model performance using R², MAE, MSE, and RMSE and interpreted the comparative results.
Multi-Class Product Categorization Using Random Forests
Python, Pandas, NumPy, Scikit-learn, TF-IDF, Random Forest, Matplotlib, Seaborn
Developed a machine learning model to classify e-commerce products into multiple categories using product titles, descriptions, prices, and brands. Implemented text vectorization using TF-IDF and categorical feature encoding for data preprocessing. Trained a Random Forest classifier and evaluated its performance using accuracy, precision, recall, F1-score, and a confusion matrix. Visualized category distribution and feature importance to analyze model behavior. Saved the trained model using Joblib for future product category predictions.
Collaborative Learning of Augmentation and Disentanglement for Semi-Supervised Domain Generalized Medical Image Segmentation
Development of a 2D medical image segmentation system. Training with limited labeled datasets. Multi-domain learning simulation. Evaluation using Dice coefficient and IoU metrics. Applicable to MRI, CT, and ultrasound imaging.
Skills
Python
HTML
SQL
Pandas
XGBoost
Lightgbm
Seaborn
NumPy
Matplotlib
Visual Studio Code
Microsoft Office Suite
Scikit-learn
TF-IDF
Random Forest
PyTorch
Torchvision
OpenCV
Albumentations
Joblib
Dice coefficient
IoU metrics
GridSearchCV
R²
MAE
MSE
Mock interviews on readyforhires
SQL & Databases (Beginner)Best 25%
20 questions answered on readyforhires in the past year, 1 active day, longest streak 1 day.
