LINYAN(Candice) XIONG

Ithaca, NY (Willing to Relocate) 949-***-**** adjkl5@r.postjobfree.com linkedin.com/in/linyanxiong/ EDUCATION

Cornell University Ithaca, NY Dec 2020

M.S in Applied Statistics Specialization: Data Science GPA:3.88 University of California, Irvine Irvine, CA Jun 2018 B.A in Quantitative Economics Minor in Statistics Deans Honors List for 6 quarters Core Coursework: Machine Learning and Data Mining, Big Data Management and Analysis (Linux and Hadoop), Python for Data Science, Monte Carlo Simulation, Financial Engineering with Stochastic Calculus, Operations Research PROFESSIONAL EXPERIENCE

Energy Codes Optimization Capstone Project with 2050 Partners, LLC Orinda, CA Jan – May 2020

• Statistical Modeling: Performed Logistic Regression on the correlation between occupancy patterns and energy saving levels; applied time series analysis to estimate key parameters involved in lighting control practices; created a forecasting model with R for energy saving to improve the building energy codes and reduce the energy cost

• Experimental Design: Designed A/B testing and cleaned data and build data frames for 1 million observations and 20 variables in Python; created Tableau visualization dashboards of energy saving rankings for environmental engineers to establish optimal energy-consumption plan

• Application: Translated data and model results into tactical and meaningful insights to support strategic planning, providing a reliable prediction tool for clients’ business decisions making; delivered insights from quantitative analyses to technical and non-technical audiences

Data Analyst China Foreign Exchange Trade System Shanghai, CN Jan – Jul 2019

• Data Management: Designed ETL process to load newly issued bond data and incorporated 2 million historical data sets into relational database using SQL, and load data to visualization dashboards using Tableau, improved working efficiency by 80%; monitored critical elements to identify data issues and provided insights about their potential impact

• Risk Analytics: Conducted research into possible defaulted bonds based on the changes of their credit-rating and the issuers’ level of debt; built low-bias prediction models for national bond market trends with high accuracy; developed bond pricing and valuation models and released benchmarks for more than 30,000 trading members

• Data Quality: Performed data quality validations and built internal control reports by Excel Pivot Table; collaborated with data warehouse team to update database and maintained data integrity; standardized key spreads and optimized yield curves for various credit-ratings bonds by leveraging statistical packages in R Financial Analyst Chuancai Securities Co., Ltd Beijing, CN Jul – Dec 2018

• Financial Analytics: Analyzed debt documentation and financial statements to assess relevant risks with auditing team and identified profitable revenue growth opportunities for enterprises; completed cash flow analysis and capital tracking on a quarterly basis; supported highly consultative and solutions-based discussions with existing and prospective investors; prioritized multiple tasks and addressed ad hoc requests within a cross-functional group PROJECT

Big Data Analysis: Text Analysis with MapReduce, SQL, and Hadoop Jan – May 2020

• Wrote Map and Reduce functions with Python on Linux and used Hadoop Streaming to process keywords extraction and words frequency statistics; connect SAS with Oracle relational database and performed correlation and regression analysis, queried in SQL to create views, procedures, and triggers to reduce manual processing time by 70% Python Programming: Data Analysis with Gene Sequences Database Jan – May 2020

• Designed a database-driven dynamic webpage that allowed users to upload raw data file and extracted right gene sequences; used Python-Oracle integration approach to process and store structured data in an Oracle database table; categorized gene data into different nucleotide types by K-means clustering and calculated the relative frequencies of each nucleotide; created a Python program that supported user query against the Oracle table of the gene sequences and displayed the statistics of each nucleotide and the visualized clustering results in that webpage Machine Learning: Marital Status Classification Sep – Dec 2019

• Utilized machine learning algorithms with R, including logistic regression, random forest, and penalized LASSO and Nearest-Neighborhood techniques, to conduct predictive data analysis and response models; examined the fitness of each model and to provide modeling technique recommendation; did forward stepwise model selections with the criterion of 5-fold cross validation error and model achieved 92.35% accuracy rate SKILL

Programming and Tools: R, Python, SAS, SQL, Oracle, Hadoop, Stata, VBA, Tableau, Microsoft Office, Google Suite Statistical Analysis and Machine Learning: Regression, Classification, Clustering, A/B Testing, Neural Network