Data Science with less than a year in Machine Learning & Statistical Analysis
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Data Science Intern with hands-on experience building end-to-end machine learning pipelines for classification and regression problems. Proficient in Python, SQL, and scikit-learn with strong foundation in statistical analysis, feature engineering, and model optimization. Delivered predictive models achieving 97.79% accuracy and ROC-AUC scores exceeding 0.85 on real-world datasets.
Basaveshwar Engineering College
Bachelor of Engineering · Computer Science
August 1, 2021 – June 30, 2025
DataMites
Data Science Intern
January 1, 2026 – Present
Bengaluru, Karnataka, India
Home Loan Default Prediction
June 19, 2026 – Present
Built a classification model to predict loan default risk using structured financial and demographic data. Performed extensive data preprocessing including missing value imputation, categorical encoding, and feature scaling. Engineered features from income, credit history, and loan attributes; applied class imbalance handling techniques (SMOTE/class weights). Trained and compared Logistic Regression, Random Forest, and XGBoost models with hyperparameter tuning. Achieved ROC-AUC of 0.87, improving model performance and recall on default class.
Flight Price Prediction
June 19, 2026 – Present
Developed a regression model to predict flight ticket prices using historical airline data. Conducted EDA to identify key pricing factors such as airline, duration, number of stops, and departure timing. Performed feature engineering including journey duration extraction, time-based features, and categorical encoding. Trained and optimized models including Linear Regression, Decision Tree, and Random Forest. Achieved RMSE of 1,847 and R2 of 0.81 with Random Forest.
MNIST Handwritten Digit Classification
June 19, 2026 – Present
Built an end-to-end image classification pipeline using the MNIST dataset (70,000 images). Preprocessed image data through normalization and flattening to improve model convergence. Implemented and compared Logistic Regression, KNN, and Feedforward Neural Network models. Evaluated performance using accuracy, precision, recall, and F1-score. Achieved 97.79% test accuracy with optimized neural network model.
Walking vs Running Activity Classification
June 19, 2026 – Present
Developed a classification model to distinguish walking vs running using accelerometer sensor data. Applied signal preprocessing including noise filtering, normalization, and feature extraction from time-series data. Extracted statistical features (mean, variance, frequency-based features) to capture motion patterns. Trained models including KNN and Random Forest, selecting best model based on evaluation metrics. Achieved 95%+ accuracy, enabling reliable activity recognition.
Cultural Fit Analysis
The candidate's projects demonstrate a strong interest in diverse data science applications, from image classification to financial risk and activity recognition. This breadth of interest aligns well with a dynamic, learning-oriented culture. The current internship at DataMites further indicates a commitment to practical application of data science skills. However, the candidate is still early in their career, and their cultural fit would benefit from further assessment during interviews to understand their preferred working environment, collaboration style, and adaptability.
Soft Skills & Operational Fit
The candidate's project descriptions indicate a structured approach to problem-solving and a focus on achieving measurable results. The internship experience suggests an ability to work within a professional data science context. However, without direct assessment data on collaboration, stress handling, or communication in a team setting, a comprehensive evaluation of soft skills and operational fit is limited.