Shrutika Paradkar

Rajiv Gandhi College of Engineering and Research

B.E. · Computer Science

August 1, 2019 – June 30, 2023

Nandanwan Arts, Commerce and Science College

HSC

N/A – May 31, 2019

Shahu's Garden Convent and High School

SSC

N/A – May 31, 2017

Edverciity by Livetechskills

Data Engineer

September 1, 2024 – Present

Nagpur, Maharashtra, India

Rubixe AI Solutions Company

Data Science Intern

October 1, 2023 – August 1, 2024

Bengaluru, Karnataka, India

Smart Lead Scoring System

June 20, 2026 – Present

Designed and deployed an end-to-end ML system for lead conversion prediction, achieving 85%+ accuracy and improving sales prioritization by 40%. Developed an interactive Streamlit dashboard supporting single and bulk CSV-based predictions with real-time Plotly visualizations. Implemented secure authentication using streamlit-authenticator with bcrypt hashing, eliminating unauthorized access risks. Engineered complete data pipelines including data cleaning, EDA, and feature engineering on 30K+ synthetic leads, improving model performance by 25%. Trained and evaluated Logistic Regression, Random Forest, and XGBoost models using ROC-AUC and precision-recall metrics for optimal model selection. Integrated SQL-based logging to store prediction results, confidence scores, and metadata ensuring 100% traceability. Automated PDF and CSV report generation, reducing manual reporting effort by 70%. Utilized Python, Pandas, NumPy, Scikit-learn, PySpark, Streamlit, Plotly, SQL, and Joblib for scalable ML deployment.

AI Job Market Insights

June 20, 2026 – Present

Developed an end-to-end machine learning system to predict AI/ML job growth trends using multiclass classification for strategic workforce planning. Performed data preprocessing on mixed-type datasets using OneHotEncoder, feature scaling, and train-test splitting, improving model stability by 20%. Conducted exploratory data analysis to evaluate salary distributions, role demand, and class imbalance, generating actionable market insights. Implemented ML pipelines with Logistic Regression, Random Forest, and XGBoost using Pipeline() and GridSearchCV() for hyperparameter optimization. Applied StratifiedKFold cross-validation to maintain balanced class distributions and reduce model bias by 15%. Achieved highest performance with XGBoost (41% accuracy), outperforming baseline models by 5%. Evaluated models using accuracy, precision, recall, F1-score, and confusion matrix to ensure robust performance validation. Extracted and visualized XGBoost feature importance to identify key predictors driving AI job market growth.

Digital Wellbeing Pattern Analyzer

June 20, 2026 – Present

Developed a machine learning-based Digital Wellbeing Pattern Analyzer to predict digital burnout risk using behavioral and smartphone usage data. Preprocessed and engineered features from multi-dimensional datasets including screen time, sleep duration, mood, and anxiety metrics, improving model performance by 22%. Created derived behavioral features such as social_media_ratio to enhance burnout risk classification accuracy. Trained and evaluated classification models using Scikit-learn with hyperparameter tuning via GridSearchCV for optimal performance. Selected and serialized the best-performing model as burnout_model.pkl using joblib for production deployment. Built and deployed an interactive Streamlit web application enabling real-time burnout prediction and confidence scoring. Implemented a rule-based recommendation engine to generate personalized digital wellbeing suggestions based on user behavior. Utilized Python, Pandas, NumPy, Scikit-learn, Streamlit, Joblib, Git, and GitHub for end-to-end ML deployment.

NASSCOM Certified Data Scientist

NASSCOM

June 1, 2026 – Present

IABAC Data Science Foundation Certification

IABAC

June 1, 2026 – Present