Charlie Ao

Eager and diligent Data Science Intern with an academic focus on statistics and computer science, seeking a summer internship opportunity at EMC Research, Inc. Proficient in Python, R, and key data visualization techniques, with a demonstrated ability to work effectively in both team and independent environments to meet project objectives and deadlines. Highly skilled in critical thinking, problem-solving, and communication which enables efficient collaboration across multidisciplinary teams. Passionate about employing data-driven methodologies to tackle real-world challenges and ready to contribute to an innovative organization while advancing expertise in the field of data science and market research.

Time Series Analysis of Geomagnetic Pole Position - Independent Research Project 

• Conducted time series analysis using R, preprocessed data for quality analysis and applied data transformation techniques to isolate trends, seasonality, and residuals.
• Performed diagnostic tests, residual analysis, and model performance evaluation.
• Successfully identified ARMA models for predicting future pole positions, aiding in data-driven decision making.

Advanced Predictive Modeling - Kaggle Prediction Competition 

• Developed predictive models using regression and machine learning techniques in R.
• Processed training and test datasets, implemented multiple models including decision trees and lasso regression.
• Tuned model parameters, evaluated performance using cross-validation and MSE, and submitted results for a Kaggle competition.
• Enhanced skills in data analysis, model selection, parameter tuning, performance evaluation, and R programming.

Statistical Analysis Project - Impact of Student Habits on Test Scores

• Studied data from 110 students to see how various factors influence their test scores.
• Conducted exploratory data analysis and developed a regression model, iteratively refining it to highlight significant predictors.
• Validated the model using assumptions of linearity, independence, constant variance, and normality of errors.
• Provided data-driven insights on student habits' influence on academic performance, supporting educational strategies.