Varanasi Bikash Patra

To secure a challenging position in a reputable organization to expand my learnings, knowledge and skills while making significant contribution to the growth and success of the company. With a Data Scientist skill over 2 years of hands-on experience in delivering valuable insights via data analytics and advanced data-driven methods for in house product development. Experienced electrical design engineer with 9 years of experience in R&D, product development, overseeing the successful completion of the electromagnetic designs within the prerequisite manufacturing settings.

• Project 1: Machine learning solution to predict friction & windage losses in Induction Motors
• Tech Stack: Python, Sci-kit learn, Pandas, NumPy, sklearn, SQL, Support Vector Regression
• Work: Developed a Machine learning model that predicts Friction and Windage losses in induction motors
• Project 2: Vibration and Noise analysis of industrial Motor
• Tech Stack: Python, Sci-kit learn, Pandas, NumPy, sklearn, SQL, Support Vector Regression
• Work: Accomplishment of vibration data analysis for grade – B vibration level (Expanding the addressable market)
• Flight Price Prediction using Machine Learning
• Tech stack: Python, Machine learning, jupyter notebook
• Objective: Created a regressor model to predict the fare of a flight ticket
• Solution: Did data preprocessing, did EDA, did hyper-parameter tuning, built 6-7 models based on different parameters
• Achievements: Random Forest Regressor having r2 score of 83 and cross validation score of 82
• Census Income Project using Machine learning
• Tech stack: Python, Machine learning, jupyter notebook
• Objective: Prepared a classification model to predict whether a person makes over $50K a year
• Solution: Did data preprocessing, treated outliers, did hyper-parameter tuning, built 6-7 models based on different parameters
• Achievements: AdaBoostClassifier having f1 score of 86 and cross validation score of 85 and AUC score of 88
• HR Analytics Project -Understanding the Attrition in HR
• Tech stack: Python, Machine learning, jupyter notebook
• Objective: Building a classification model to predict Employee Attrition
• Solution: Did data preprocessing, did EDA, did hyper-parameter tuning, built 6-7 models based on different parameters
• Achievements: AdaBoostClassifer having f1 score of 86, cross validation score of 85 and AUC score of 83.