VIKAS RAYALA

Meticulous Data Scientist accomplished in compiling, transforming and analyzing complex information through software. Expert in machine learning and large dataset management. Demonstrated success in identifying relationships and building solutions to business problems.

Used Car Price Prediction Model Using Regression Models: 

• We collected used car listing data from different web sources.
• Cleaned and processed raw data in R, handled missing values, parsed text fields, and engineered new features for modeling.
• Developed a single & multiple linear regression model using preprocessed data to predict used car prices based on attributes like make, model, mileage, number. of users, etc.
• Evaluated model performance using training and validation splits; optimized hyper parameters to improve accuracy and prevent overfitting
• Containerized end-to-end data collection, cleaning, and modeling pipeline for easy re-training and deployment. Improved accuracy by 60%.

Loan Status Classification Using Machine Learning Models:

• Collected lending data from LendingClub (10K rows, 152 features) and preprocessed it by cleaning, splitting, encoding, and imputing missing values.
• Developed and evaluated multiple classification models, including KNN, Naive Bayes, XGBoost, random forest, GLM, and logistic regression, to predict loan default.
• Tuned hyperparameters and compared models using accuracy, confusion matrix, and ROC curve.
• Logistic regression achieved the highest accuracy of 89% on test data, outperforming baseline and other models.
• Identified key correlations between borrower income, loan amount, credit history, and default rate through a logistic regression model.

Netflix Analysis: 

• Performed exploratory data analysis on the Netflix movies and TV shows dataset with over 8,000 observations to uncover insights into content types, production trends, ratings, duration, and keywords.
• Utilized R and data visualization libraries to wrangle data and create informative graphs showing the dominance of movies over shows (70% vs. 30%), growth in production over time, and prevalence of adult content.
• Identified key statistics like the US producing 50% of titles, average movie duration fluctuating between 90and120 minutes, and most common words in descriptions, quantifying Netflix priorities.

• Pioneered Drug Free Campaign at Lovely Professional University campus; organized educational activities to inform students about dangers of drug use.
• Served as Chief - Coordinator for Mind Spark, Buss Masters, SWAT Club at Lovely Professional University; organized and led club activities and events.
• Led as Team Leader for capstone project at GDMM and LPU; spearheaded project strategy and guided team members.

• Contributed to team's championship victory as key player in Cricket Tournament organized at the university level, showcasing teamwork and athletic skills.
• Played an instrumental role as Event Lead in organizing Mechanical Engineering Technical Fest, leading team to 2nd place finish in competition out of 15 teams.
• Earned 2nd place in Inter Department Soft Skills competition organized by the university; exhibited strong communication and presentation abilities.