Data Analyst Science

LONGNU (ECHO) ZHOU

+1-626-***-**** longnuzhou**25[at]u.northwestern.edu

EDUCATION

Northwestern University Evanston, Illinois

M.S. in Machine Learning and Data Science Sept. 2024 – Dec. 2025 University of California, San Diego San Diego, CA

B.S. in Mathematics/Economics, Highest Distinction, Major GPA: 3.83/4.0 Sept. 2020 – Jun. 2024 PROFESSIONAL EXPERIENCE

Center For Community Energy San Diego, CA

Financial Data Analyst Intern Jun. 2024 – Sept. 2024

• Developed a financial model in Microsoft Excel to estimate solar installation costs in California, enhancing cost analysis and decision-making.

• Analyzed data on tax incentives and grants for solar energy and electric vehicle charging, evaluating financial impacts and investment feasibility in clean energy projects. EDF Renewables La Jolla, CA

Portfolio Data Analyst Intern, Digital Transformation Team Jun. 2023 – Sept. 2023

• Developed a software spending tracking report using 9000+ entries extracted from SAP.

• Optimized data cleaning and preparation for financial analysis and balanced company budget through cost- benefit analysis with Excel pivot tables.

• Streamlined operational data tracking with the Malbek contract management platform Malbek. RESEARCH EXPERIENCE

Income Effect of Electric Vehicle Adoption Mar. 2023 – Dec. 2023

• Used entity & time-fixed effects to estimate the correlation between income levels and the adoption of electric vehicles (EVs) across ZIP codes in California using 19,389 zipcode data and 188,276 EV data.

• Merged multiple time-series datasets from various online sources using STATA.

• Findings: An increase in income level 1% is correlated with an increase of 4. 04% in the adoption of electric vehicles per 1,000 individuals.

Economics Research on Monetary Policy Impact Mar. 2023 – Jun. 2023

• Investigated the causal relationship between Real GDP Growth and Unemployment Rate in Vermont.

• Applied ARMA and ARIMA models, ACF and PACF analyses, Granger causality tests, VAR models, and impulse response functions in R.

• Performed robustness checks using correlation and covariance matrix as well as Akaike Information Criterion

(AIC) and Bayesian Information Criterion (BIC) to select the best-fit machine leaning model. PROJECT EXPERIENCE

Kavi Global-Industrial Practicum(Data Science) Project Sep. 2024 – Present

• Develop an AI-driven Analytics Copilot with LLMs for natural language analysis.

• Automate data pipelines and enhance visualization efficiency.

• Use RAG and RLHF to improve AI insights and reporting. Churn Analysis:Predicting Customer Retention-Machine Learning I Sep. 2024 – Dec. 2024

• Conducted data cleaning and feature engineering and scaling for model readiness.

• Applied logistic regression, Lasso regression, and Random Forest to predict churn, achieving 89. 6% precision using cross-validation and ROSE oversampling.

• Identified key churn drivers and retention factors to provide actionable business recommendations. Optimizing Pricing Strategies for Dillard’s-Everything Starts with Data Sep. 2024 – Dec. 2024

• Optimized pricing by comparing models (Linear Regression, Lasso, XGBoost, Random Forest).

• Cleaned and scaled data, checked multicollinearity (VIF), and encoded categorical variables.

• Conducted EDA, evaluated models (R-squared, MAE, MSE), and analyzed ROI. Classification of Email Messages -Data Analysis and Inference Jan. 2023 – Mar. 2023

• Utilized R studio to apply standardization, log transformation, discretization to both the training set of 3076 observations and test set with 1534 observations.

• Applied and compared various classifiers including logistic regression, LDA&QDA, SVM, Tree-based and Random Forest, concluding Random Forest as the most efficient with the lowest error rate of 0.00326. SKILLS

Technical: SQL, Python, R, MATLAB, STATA, Time-Series Analysis, PowerBI, Microsoft Excel, SAP

Contact this candidate