ASHI CHOUDHARY

Boston, MA, ***** • 571-***-**** • adhdb5@r.postjobfree.com

EDUCATION

Boston University, Boston, MA Sep 2019 - Current

Candidate of Masters of Science

Major: Computer Information Systems

Relevant Courses: Python, Data Analysis and Visualization with R, SQL, Database Design and Processing, Data Analytics, Data Mining, Computation and Visualization for Analytics, System Analysis and Design, Web Analytics and Mining, Data Science with Python

Galgotias College of Engineering and Technology, Greater Noida, India Aug 2015 – May 2019 Relevant Courses: Linear Algebra, Probability and Statistics, Multivariate Calculus, Operating Systems, Object-Oriented Development and Design, C, C++

TECHNICAL KNOWLEDGE

Languages: Python, SQL, R, C++

Databases: MySQL Workbench, Microsoft SQL Server, PostgreSQL BI Tools: Tableau, Advanced Excel(pivots, macros, lookups), Power BI, Google Analytics Machine Learning: Supervised, Unsupervised Learning, NLP Statistical Techniques: Statistical Inference, Regression Modeling, Experiment Design, Sampling, Hypothesis Testing, A/B Testing

PROFESSIONAL EXPERIENCE

Graduate Teaching Assistant, Boston University, Boston Sep 2020 – Cont.

• Teaching Assistant for the graduate-level course CS 521 Information Structures with Python under Prof. Eugene Pinsky, Boston University

• Graded assignments and provided extensive feedback to students on their work which included concepts of the object-oriented approach to software design and development using the Python

• Guided students with programming concepts data types, control structures methods, classes and proceeded to advanced topics such as inheritance and polymorphism, creating user interfaces, exceptions and streams Graduate Student Researcher, Boston University, Boston May 2020 – Sep 2020

• Research conducted under Prof. Eugene Pinsky, Boston University and Dr. Sidney Klawansky, Harvard School of Public Health.

• Conducted a mathematical study to develop an algorithm to gauge similarity between two groups of data by utilizing the Cumulative Density Function (CDF) plot

• Experimented with Serum Creatinine data in the Male and Female populations using tools such as Python and R libraries, to build the paradigm for the same

ACADEMIC PROJECTS

Revenue Generation Analysis (Tableau, SQL developer)

• Developed ER diagrams and business models while implementing several business rules to make the business sustainable

• Integrated tableau desktop with SQL developer to prepare dashboards for data visualization for better analysis

• Implemented SQL queries to create a database ad to load sample data into the database

• Derived different parameters and graphs using Tableau to make the analysis accurate and precise Machine Learning with Energy Dataset (Python, Machine Learning)

• Conducted an exploratory data analysis using Python packages (plotly, seaborn, matplotlib) to understand the dataset.

• Conducted a thorough feature analysis and used pre-processing techniques to make the data usable for further analysis

• Applied Linear Regression, Random Forest algorithms and Neural Networks to build prediction model in python using sklearn libraries to recommend the best model. Applied feature selection algorithms like Tpot,Boruta,tsfresh to compare and contrast feature engineering in each approach Wisconsin Breast Cancer Research Project (Python, Machine Learning Algorithms)

• Trained model for Random Forrest, Linear SVM and Extra Tree Classifier where each algorithm was used to determine malignancy, survivability and recurrence of cancer respectively

• Prevented over-fitting of each model by using Recursive Feature Elimination to determine appropriate attribute for each dataset and cross-validated model to tune hyper-parameters by employing Grid Search CV Linear Regression Project (Python, EDA)

• Cleaned data by checking for nulls, inconsistent values and outliers in dataset to process it for Exploratory Data Analysis

• Fit a linear regression model to predict “Price” of diamonds based on “depth” and “carat” features

• Validated model’s accuracy (85%) by 5-fold cross - validation. Implemented Variance Inflation Factor technique to prevent over-selection of feature variables

• Validated for not over-fitting the model using Regularization methods (Ridge Regression) CERTIFICATIONS

AWS Data Analytics Fundamentals

Coursera: Python for Everybody, Data Science: Foundations using R specialization, SQL for Data Science LinkedIn Learning: Advanced Excel for Data Visualization, Tableau, Microsoft Power BI

Contact this candidate