Lingchen Kong

Experience

• 

  National Institute of Education Sciences

  Jul 2016 - Aug 2016

  Assistant Research Fellow

  • Collected raw data with research team by distributing over 1500 investigation questionnaires and conducted face to face interviews with middle school students in Suzhou; cleaned data for further statistical analysis;• Explored underlying factors affecting students’ innovation qualities by adopting Independent-Sample T-Test, ANOVA, Pearson Correlation and Multiple Regression models in R programming and SPSS;• Analyzed results of significance testing; wrote the report and prototyped solutions to cultivate the innovative mind Show less

• 

  Asiainfo

  Jun 2017 - Aug 2017

  Business Analytics Intern

  • Investigated customers’ potential preferences for China Telecom’s cellphone data plan with marketing department; • Collaborated with IT department to pull over 300,000 customers’ historical data from API, performed data wrangling and sorted out key variables by feature engineering to identify 2 targeted customer groups; • Built forecasting models (C5.0 Decision Tree, Logistic Regression), respectively to outline potential clients; • Evaluated models and developed strategies resulting in a 41% increase in recognition accuracy Show less

• 

  City78

  Jan 2019 - May 2019

  Geospatial Data Scientist Intern

  • Led a project scraping google reviews from 91 metro stations in the D.C. area to analyze commuters’ perception of local metro service; utilized ArcGIS, Tableau and Python to visualize geocoded data and generated final report; • Applied multi-class text classification (NLP) using SVM/Naïve Bayes; optimizing topic extraction by ~30%; • Enhanced google review scraper by constructing new language detection code with 99.4% accuracy; • Interacted with 2 local business leaders and worked with teammates on North Shore (Massachusetts) project to realize neighborhood business potential Show less

• 

  Data Society

  May 2019 - Dec 2019

  Data Scientist Intern

  • Restructured 5 data science training courses related to Python, MS SQL and Power BI; • Built multiple web scrapers using selenium and request to extract 8,600+ federal procurement solicitations; • Customized R Shiny web app to help 620+ small business owners discover potential federal business opportunities

• 

  NYC Department of Education

  Jan 2020 - Jan 2021

  Data Scientist

  • Streamlined Ad hoc data requests & analysis from internal/external researchers; • Automated Python scripts and dashboard design (Panel, Altair, hvPlot) to feed EduStat daily reporting; • Coordinated with a cross-functional team of analysts contributing to identification, evaluation, as well as refinement of remote learning metrics based on 1.5 million students’ activities on Google classroom; • Adopted ML algorithms (SVC, Random Forest, Xgboost, etc.) to predict potential dropout students (AUC: 0.81, Recall: 0.6); collaborated closely with stakeholders to establish an early warning system to improve graduation rate Show less

• 

  Takeda

  May 2021 - Aug 2022

  People Analytics

  • Enhanced employee engagement survey analysis by utilizing LDA topic modeling and K-means clustering• Built ETL pipelines with PySpark, Databricks, and AWS S3 to automate reporting and dashboard data ingestion• Evaluated WeCelebrate program using propensity score matching and Chi-squared test to assess turnover rate• Conducted predictive analysis and social network analysis on employee experience and performance data• Passionate storyteller, excels at telling a story with data to both expert and nonexpert audiences Show less

• 

  University of Florida

  Aug 2022 - now

  PhD Student and Research Assistant