VAIBHAV KUMAR

Dallas, Texas 469-***-**** adwcm5@r.postjobfree.com www.linkedin.com/in/vaibhavkumar09 EDUCATION

The University of Texas at Dallas May 2024

M.S Business Analytics GPA: 3.7

Coursework-NLP,Applied Machine Learning, Business Analytics with R, Advance Statistics for Data Science, Prescriptive analytics, Programming for Data Science, Big Data, Database Foundation for Business Analytics. Indian Maritime University Dec 2013

Bachelor of Technology-Marine engineering GPA: 3.6 CERTIFICATIONS AND TECHNICAL SKILLS

Certifications: Python for Data Analysis, Data Analysis & Visualization in Tableau, Data Manipulation in SQL, Alteryx Machine learning Certification, Six Sigma Green Belt Programming: Python, R, C++, SQL, MongoDB, MATLAB, Appian, SaaS, UiPath Analysis Tools & Packages: Big Data Analytics, Hive, Impala, Spark, Adobe Analytics, Tableau, MS Excel, Power Point, Power BI, Pandas, NumPy, Scikit-Learn, Matplotlib, TesnorFlow Machine Learning Algorithms: NLP, K-nearest Neighbors, Random Forests, Naive Bayes, Regression Models, PyTorch ACADEMIC PROJECTS

● Text Classification using Deep Learning: Developed a deep neural network using TensorFlow to classify news articles into categories. Achieved an accuracy of 90% on the test dataset.

● Stock Market Prediction using Machine Learning: Used Scikit-Learn to train an ML model to predict stock prices. Achieved an RMSE of 2.5 on the test dataset.

● Sentiment Analysis of Movie Reviews: Used NLTK and Scikit-Learn to perform sentiment analysis on movie reviews. Achieved an accuracy of 85% on the test dataset.

● House Price Prediction (JAN 2023): Python, Excel-Carried out data cleaning, feature engineering, scaling and exploratory data analysis on the Melbourne housing data. Implemented various machine learning algorithms (Linear Regression, Ridge, Lasso, SVM Regression, Decision Tree Regression, KNN Regression) to predict the house price based on the features engineered to get 0.72 R^2 on the test data.

● Customer Churn Prediction (Nov 2022): R, Excel-Analyzed customer banking data to predict churn and conducted exploratory data analysis (EDA). Created a balanced dataset using various methods like SMOTE, realized 94% F1-score using Random Forest.

● Financial Credibility Analysis (Oct 2021): Python, Excel -Performed feature engineering and descriptive analysis of data and calculated the maximum repayment capability of customers to grant them the desired loan amount. Applied linear regression, decision tree and random forest. Achieved score of 86% using Random Forest. WORK EXPERIENCE

Mediterranean Shipping Company, Limassol, Cyprus Oct 2019 - Jul 2022 Data Analyst

● Used MySQL and Python to analyze data from ships and optimized energy consumption, resulting in $1M in savings per year. Presented findings to stakeholders.

● Conducted statistical analysis and built predictive models using machine learning algorithms to optimize maintenance schedules for marine engines, resulting in a 30% reduction in downtime and $2M in savings per year.

● Developed Tableau dashboards to analyze the impact of marine fuels on air pollution, resulting in 20% reduction in emissions and compliance with IMO 2020 regulations.

● Managed large datasets of sensory data for marine engines (MAN B&W) and used advanced SQL queries to identify trends and anomalies, creating a PMS for critical machinery that reduced breakdowns by 45% ($350K).

● Collaborated with data engineering team to build ELT pipelines using Spark, resulting in 20% reduction in operational costs and $500,000 annual savings.

Mediterranean Shipping Company, Limassol, Cyprus Dec 2014 - Oct 2019 Assistant Project Manager

● Worked with cross-functionals team for the installation of Exhaust gas cleaning system on Ship($500K), designed emission control module to monitor and record data when EGCS is in use, used Agile methodologies for the project.

● Designed an Excel program for inventory management based on real-time usage data from ERP, reducing overstocking by 32% and saving $0.6M in quarterly inventory budge

● Collaborated with multi-national team of 30 in 5 locations (Mumbai, Durban, Dubai, London, Jeddah) to understand the process variance, revised KPIs to analyze processes using analytics tools and increased savings by 10%.