ShaDong
Sha(Andrea) Dong
Los Angeles, CA | ------------ | ------------
Education
University of Southern California 05/2019
Master of Science in Computer Science
Capital University of Economics and Business 06/2015
Bachelor of Science in Computer Science
Relevant Courses: Data Mining, Machine Learning, Database Systems, Analysis of Algorithms, Web Technologies
Skills
? Programming Language: Scala, Python, C/C#, Java, HTML/CSS, JavaScript, PHP
? Databases&Tools: MySQL, Microsoft SQL Server, Apache, 3DMax, Eclipse, Flash
Academic Project Restaurant Recommender System (Apache Spark, Scala) 11/2018
? Predict user rating to restaurants on Yelp Challenge dataset with 6 million records
? User-based collaborative filtering approach: Leveraged term frequency-inverse document frequency in users’ review and implemented the K-mean algorithm to find the similarly behaved users of the target user. Based on the Pearson correlation within the filtered group, computed the weighted average rating. Given MSE 1.08.
? Item-based collaborative filtering approach: Applied the SON algorithm to find the set of similar restaurant and leveraged A – Priori algorithm to improve efficiency. Calculated weighted average rating based on the Pearson correlation of similar restaurants. Reduced the MSE to 1.05.
Spam Email Filtering with Decision Tree (Python) 03/2019
? Calculate the entropy and split the tree nodes to build the whole tree structure; Use the validation set to prune the tree in order to prevent overfitting.
? With the decision tree model, the spam emails can be filtered according to the attributes.
Ticket Search Web (Javascript, PHP, JSON, HTML) 10/2018
? Built a responsive website with low latency to retrieve real time event-ticket on Google API and Ticketmaster API.
? Implemented server script to process JSON data with PHP on Google Cloud App Engine.
? Using HTML and CSS to integrate the front-end.
Hospital Pharmacy Management System (SQL) 12/2017
? Use SQL Server to build the relative database for a pharmacy management system to supervise the real-time usage of the drugs.
? Design the business flow chart, the data flow chart, the E-R diagram and build the database on SQL Server.
? Cooperate as a team to connect SQL Server and realize the live transmission of data.
Work Experience
Beijing Transportation Research Center 09/2015-11/2015
Software Developer Internship Beijing, China
? Use python to clean data and to get line data set.
? Use Java to analyze the real-time traffic in Beijing’s major roads, and to compute the heatmap with SuperMap iObjects Java Jar package and give some suggestion to reduce traffic congestion.
Publications & Patents
? Dong Sha, On Evolutionary Algorithms, Fujian Computer, Journal No: Pages: 92-94, 11/2013
Sha(Andrea) Dong
Los Angeles, CA | ------------ | ------------
Education
University of Southern California 05/2019
Master of Science in Computer Science
Capital University of Economics and Business 06/2015
Bachelor of Science in Computer Science
Relevant Courses: Data Mining, Machine Learning, Database Systems, Analysis of Algorithms, Web Technologies
Skills
? Programming Language: Scala, Python, C/C#, Java, HTML/CSS, JavaScript, PHP
? Databases&Tools: MySQL, Microsoft SQL Server, Apache, 3DMax, Eclipse, Flash
Academic Project Restaurant Recommender System (Apache Spark, Scala) 11/2018
? Predict user rating to restaurants on Yelp Challenge dataset with 6 million records
? User-based collaborative filtering approach: Leveraged term frequency-inverse document frequency in users’ review and implemented the K-mean algorithm to find the similarly behaved users of the target user. Based on the Pearson correlation within the filtered group, computed the weighted average rating. Given MSE 1.08.
? Item-based collaborative filtering approach: Applied the SON algorithm to find the set of similar restaurant and leveraged A – Priori algorithm to improve efficiency. Calculated weighted average rating based on the Pearson correlation of similar restaurants. Reduced the MSE to 1.05.
Spam Email Filtering with Decision Tree (Python) 03/2019
? Calculate the entropy and split the tree nodes to build the whole tree structure; Use the validation set to prune the tree in order to prevent overfitting.
? With the decision tree model, the spam emails can be filtered according to the attributes.
Ticket Search Web (Javascript, PHP, JSON, HTML) 10/2018
? Built a responsive website with low latency to retrieve real time event-ticket on Google API and Ticketmaster API.
? Implemented server script to process JSON data with PHP on Google Cloud App Engine.
? Using HTML and CSS to integrate the front-end.
Hospital Pharmacy Management System (SQL) 12/2017
? Use SQL Server to build the relative database for a pharmacy management system to supervise the real-time usage of the drugs.
? Design the business flow chart, the data flow chart, the E-R diagram and build the database on SQL Server.
? Cooperate as a team to connect SQL Server and realize the live transmission of data.
Work Experience
Beijing Transportation Research Center 09/2015-11/2015
Software Developer Internship Beijing, China
? Use python to clean data and to get line data set.
? Use Java to analyze the real-time traffic in Beijing’s major roads, and to compute the heatmap with SuperMap iObjects Java Jar package and give some suggestion to reduce traffic congestion.
Publications & Patents
? Dong Sha, On Evolutionary Algorithms, Fujian Computer, Journal No: Pages: 92-94, 11/2013