At SmartKnower, I worked on classification modeling and predictive analytics, applying machine learning techniques to analyze structured datasets and extract meaningful insights.
🔹 Data Preprocessing & Feature Engineering – Cleaned and prepared a large dataset, handling missing values, encoding categorical data, and selecting relevant features to optimize model performance.
🔹 Exploratory Data Analysis (EDA) – Conducted statistical analysis and visualized key trends using Seaborn, Matplotlib, and correlation heatmaps to identify patterns in the dataset.
🔹 Machine Learning Model Development – Implemented and evaluated multiple classification algorithms, including Decision Trees, Random Forest, Logistic Regression, K-Nearest Neighbors (KNN), and Support Vector Machine (SVM) to predict income levels based on various demographic and occupational factors.
🔹 Model Evaluation & Performance Metrics – Assessed model effectiveness using confusion matrices, precision-recall scores, F1-scores, accuracy scores, and misclassification rates. The Decision Tree Classifier achieved the highest accuracy (85.5%) compared to other models.
🔹 Hyperparameter Tuning & Validation – Optimized models by fine-tuning hyperparameters and validating performance through train-test splits and cross-validation to ensure generalization.
This experience strengthened my skills in data preprocessing, feature engineering, supervised learning, and model evaluation, while enhancing my ability to translate data into actionable insights and predictive solutions.
