Tools: MySQL, PyCharm, RStudio, Tableau, Hadoop, Spark, Eclipse, AWS, NetBeans, Axure, Visio, Dreamweaver, Access.
Confidential, Bethesda, MD
Information System Intern
- Performed data cleansing of 300K property trial balance data and 9 - year monthly budget data using Excel and MRI (accounting information system).
- Designed SQL scripts to extract, collect and combine financial data from Argus by using Microsoft Query Editor, produced technical document for non-technical people, resulted in reducing project delivery time by 50%.
Confidential, College Park, MD
- Led team of three to gather functional and non-functional requirements, re-designed ER diagram for application.
- Designed reward system to incentivize mentoring of new employees, analyzed data of 50+ new employees.
- Contacted across 20+ branches of company and operated and maintained database of over 2000 employee profiles, assessed progress of 50+ new employers to produce a status report ahead of stipulated time, reduced time of assessment by 10%.
Employee Retention Strategy (Spark, Python, R, Hive, PHP)
- Performed data cleansing by converting data, used R and Python to handle missing data and predicted the potential important factors that may affect an employee’s decision to choose to leave or stay using Spark to run multiple prediction models (Decision Tree/Nai've Bayes/Radom Forest), achieved model of accuracy of 92%.
- Delivered importance score of each factor and generated four important factors including satisfaction rate, average working hours, time spend to company and the number of projects, demonstrated fully-functional strategy to group of 30+.
Expedia Hotel Recommendations (R, SQL, Python, Tableau)
- Performed data cleansing of 4.07 GB Expedia hotel data set by using SQL and Python to turn mess data into actionable data.
- Developed machine learning models (Regression/Neural Network/Naive Bayes) and analyzed which hotel cluster user will book using R, performed data visualization of variables and designed user-friendly interface, co-presented to group of 30+.
Smart City Web App Development (Agile Methodology, Python, Django, ArcGIS, AWS, MySQL, HTML/CSS)
- Developed water quality monitoring system applied Django, Python, AWS and MySQL in agile development method across eight sprints, integrated with ArcGIS to visualize location and flow details of each pipe, delivered functional system on time.
Competitor Ranking App Development (SQL server, Java, Lucidchart)
- Led team of four to designed system to rank and sort university using SQL and Java to display the ranking of three majors among different universities from four different sources, designed ER diagram for system using Lucidchart.
- Produced good school potential for customers by using different queries (JOIN/GROUP BY/ORDER BY).