Data Mining, EDA, Predictive Models, Business Analytics

Yixuan Chai

**** ******* **** **. *** * Ann Arbor MI; 517-***-****; *********@*****.***

Summary

• Energetic, result-driven analytical thinker with expertise in Data Analysis, Business Analysis, Risk Management, Data Management, Data Manipulation / Visualization, Team / Project Management.

• 4+ years Strong programming skills in R, SQL, Stata, Excel, Python, and Tableau.

• Strong communication skills and team player

Education

University of California Santa Cruz Santa Cruz, CA Master in Applied Economics and Finance Aug.2016 – Jun.2017 Focus: Programming language and applied econometrics Michigan State University East Lansing, MI

Bachelor in Environmental Economics and Policies Jan.2012 – Dec.2015 Work & Research Experience

Peltast Partners, Chicago

Data Analyst Consultant Intern Aug 2017 - Present

• Scraped over 30,000 data from Philippines real estate listing websites, completed the data mining process and an exploratory data analysis.

• Drew two heat maps using ArcGIS on both commercial and residential average land prices in the country and forecasted the real estate market trend in Philippines with findings.

• Created a yearly chart on palm oil pricing and market share data, used the pricing data to conduct a time series analysis and forecast its future price (2017-2020).

• Made graphs and lists on historical value and trend of bitcoin, total market size and total value of the crypto market, top tier companies that support blockchain technology and returns of a basket of top performing cryptocurrencies, benchmarked against traditional equity and PE/HF returns. HydroChina HuaDong Engineering Limited

Assistant Analyst Feb 2016-May 2016

• Collected survey data regarding public willingness of energy plant construction and built a database based on the 20,000+ observations in a day.

• Conducted an exploratory data analysis including visualizing the correlation matrix among 20+ variables and built a logistic regression to predict the propensity of public willingness.

• Concluded that people are more likely to oppose the proposal, defined three key components that mostly likely affect the independent variable, and provided two constructive insights and finally earned additional 30% approval from local residents.

Human Resources Analytics Apr 2017-Jun 2017

Project Leader

• Conducted data analysis on a human resources database with 149,999 observations to conclude significant factors affecting the dismissal rate with Python.

• Built two predictive modeling (Logistic Regression and Random Forest) to predict the propensity of the employees leaving their companies, and used the k-means clustering approach to analyze key features of the dismissal group.

• Identified three clusters of left employees, and provided three constructive insights to help companies decrease dismissal rate.

Contact this candidate