Post Job Free

Resume

Sign in

Data Scientist Risk Manager

Location:
New York, NY
Posted:
October 06, 2023

Contact this candidate

Resume:

Meng (Gina) Li

** **** **** **, *** York, NY 1-646-***-**** adz7di@r.postjobfree.com www.linkedin.com/in/meng-gina-li EDUCATION

Columbia University New York, NY

MS in Operations Research (STEM) 3.8/4.0 Expected Dec. 2023

• Business School Research Assistant: Compiled Python, SQL queries, and Excel to work with relational databases Southwestern University of Finance and Economics Chengdu, China BS in Finance, Minor in Economics 4.0/5.0 (WES 3.9/4.0) Aug. 2018 - May. 2022

• Awards: 2022 Mathematical Contest in Modeling-MCM (Top 1% Outstanding Nomination)

• Certified Financial Risk Manager (FRM)-GARP level1 EXPERIENCE

Quarre - Real Estate New York, NY

Data Scientist Intern May. 2023 - Aug. 2023

• Developed an AI communication model with Python and OpenAI to interact with potential customers, sending human-like voices and summarizing key information; it increased transaction quantities by 30% and reduced costs by 20%.

• Implemented an ETL pipeline with SQL in BigQuery to automate 200k+ rows of property data collecting and processing.

• Stored codes in Google Cloud Platform (GCP) and GitHub; collaborated with sales representatives and PM to develop and implement automated systems to streamline processes, improving working efficiency by 60%.

• Ran an A/B testing on 1201 leads to find whether the new landing page can make more leads sign up; designed and completed the whole process, including power analysis/statistical analysis; recommended rolling out the feature. Tianfeng Securities Shanghai, China

Data Analyst Intern Feb. 2022 - Apr. 2022

• Managed a relational database with Excel and Bloomberg; consolidated and streamlined the metals data update and retrieval process for weekly market trends analysis reports to monitor macro-risks for the portfolio; visualized trends with Tableau.

• Calculated default adjusted bond return with Excel (VBA) and Markov Model for equity valuation adjustment.

• Conducted cost analysis on new energy vehicles to quantify impacts of rising nickel prices on downstream price prediction, leading to the conclusion that demand for lithium would increase. Deloitte Shenzhen, China

Data Scientist Intern Oct. 2021 - Dec. 2021

• Assisted bank clients with quantitative analysis of personal and company loans to make risk assessment and lending decisions.

• Established ML models (SVM) on imbalanced data-sets to help Webank identify the potential customers who are more likely to purchase the loan, which could increase sales quantity by 40% while selling costs are the same.

• Innovated large-scaled data sets automatic collection methods by Python web scraping, promoting working efficiency by 63%; built a policy-vocabulary database including 100K+ entries with labeled quantitative metrics.

• Conducted risk drivers analysis on 14 industries, mainly focusing on market structures of different industries, industry features, and sensitivities, to label keywords and quantify policy risk impacts. PROJECTS

Mortgage Loan Approval with Machine Learning (ML) Mar. 2023 - Apr. 2023

• Collected 460k+ rows of data from HDMA Washington State Home Loans; conducted data processing, such as removing missing values, filling in null values, and dropping unnecessary data.

• Visualized exploratory data analysis (EDA) on variables; selected 28 variables (loan_type, income, loan_amount etc.) fromoriginal 47 variables to establish models; adopted log transform, normalization, and OneHotEncoder on chosen variables.

• Conducted hyper-parameter tuning in four machine learningmodels;measured and compared performance of predictionmodels based on accuracy (85.3% for XGBoost); important variables are ’applicant_income’, ’loan_amount’, and ’loan_purpose’. University of California Los Angeles, Covid In-Custody Project Los Angeles, CA Data Analyst Intern (unpaid) Jul. 2022 - Jan. 2023

• Implemented an ETL pipeline with Python Web-scraping to automate 20GB Covid related data collecting and cleaning; administered and managed a large database and implemented SQL queries for analysis.

• Adopted parameter-tuning optimization and error-parameter amending in Python code structures, achieving a 71.2% improvement in data processing speed from 139s to 40s; stored codes in GitHub.

• Visualized geographical distribution of Covid-19 infection cases in jails with Power BI; conducted statistical analysis to quantify the correlation/patterns between virus-data exposure level and urbanization level with Excel and Python. SKILLS

• Tech Stacks: Proficient in Python and SQL, Microsoft Excel/Word/Powerpoint, R, Matlab, Tableau, Spark, Stata

• Expertise: Statistics (A+), Probability (A+), Time Series Forecasting, Data Analytics, Optimization, Machine Learning, A/B Testing, Stochastics, Large data sets Analysis, Natural Language Processing (NLP)

• Language: Bilingual in Chinese Mandarin and English



Contact this candidate