Biography

Hey! I’m Xinyuan and you can also call me Skyla.

Welcome to My Portfolio!

I am friendly, sincere, meticulous, dedicated, have a strong sense of responsibility, learning ability and adaptability, like to talk with others, love life. The most prominent character label is seriousness, with the characteristics of calm and introverted, good at thinking and research. Have good communication and coordination skills, be good at responding, be able to quickly adapt to the new environment, be good at execution and have a team spirit, and can withstand high-intensity work.

Resumé

Interests
  • Artificial Intelligence
  • Software Development
  • Information Retrieval
Education
  • MS in Data Science, 2025

    Northeastern University

  • BS in Computing Science, 2022

    University of Alberta

Skills

SQL
Java
Machine Learning
Python
MATLAB
C#
MongoDB
Linux
Git

Work Experience

 
 
 
 
 
Intern Data Analyst (Internship)
Oct 2022 – Dec 2022 Toronto(Canada) · Hybrid

➢ Implemented credit scoring models to evaluate the creditworthiness of loan applicants and predicted loan default possibility based on user demographics with decision tree and random forest, achieving an AUC of ~0.8

➢ Utilized SQL aggregate functions and advanced database querying techniques to extract, manipulate and analyze banking and financial data; visualized the patterns and trends from risk assessment in Excel

➢ Used Tableau Story to tell data narratives on key risk management metrics, such as portfolio diversification

Responsibilities include:

  • Decision Trees
  • Random Forest
  • SQL
  • Modelling
 
 
 
 
 
Data Scientist (Internship)
Jul 2022 – Sep 2022 New York(United States)

➢ Developed a web scraper with Python to extract JSON data; utilized Pandas, Numpy and Matplotlib to perform exploratory data analysis, summarize the data extraction results and clean the stock data for modeling

➢ Built pivot tables and wrote SQL common table expressions to aggregate and analyze stock data efficiently

➢ Perform in-sample and out-of-sample forecasting at different frequencies using linear regression as baseline; evaluated the performance of ARIMA, SVM, and Holt-Winter machine learning models w/ MSE & R-Squared

➢ Built a daily running ETL to integrate new stock data into the time series, clustering & classification models

➢ Coordinated with research and engineering to document machine learning knowledge and use guide

Responsibilities include:

  • Python
  • Modelling
  • Machine Learning
 
 
 
 
 
Majorel  China
Business analyst (Internship)
May 2021 – Aug 2021 Shanghai(China)

➢ Responsible for data collection, cleaning, preprocessing, exploration and analysis for FMCG industry; used SWOT and Porters’ Five Forces to analyze industry & market conditions

➢ Designed A/B testing by defining a clear hypothesis, selecting a representative sample to randomly divide into control and treatment groups; measured the impact of pricing and promotion on sales and customer behavior

➢ Conducted funnel analysis to identify bottlenecks in customer journey and improve the overall conversion rate

➢ Designed a Tableau dashboard with single metric, bar charts, heat maps and scheduled delivery to stakeholders

➢ Diagnosed sales volume metric drop with SQL to analyze root cause and provide data-driven recommendation

Responsibilities include:

  • Analysing
  • Modelling
  • SWOT analysis
  • A/B Testing

Courses

Computer arithmetic and errors. The study of computational methods for solving problems in linear algebra, non-linear equations, optimization, interpolation and approximation, and integration. This course will provide a basic foundation in numerical methods that supports further study in machine learning; computer graphics, vision and multimedia; robotics; and other topics in Science and Engineering.
An introduction to algorithms and theory behind computer programs that solve puzzles (mazes, peg solitaire, etc.) or play games (chess, Go, Hex, etc.). This course is intended for a general audience.
When making decisions in games, computers rely on three main ideas: search, knowledge and simulations. Knowledge can be created by machine learning techniques and encoded in deep neural networks. Search and simulations help to understand the short and long-term consequences of possible actions. This course leads from basic concepts to state-of-the-art decision-making algorithms.
Object-oriented design and analysis, with interactive applications as the primary example. Topics include: software process; revision control; Unified Modeling Language (UML); requirements; software architecture, design patterns, frameworks, design guidelines; unit testing; refactoring; software tools.
This course provides an introduction to reinforcement learning intelligence, which focuses on the study and design of learning agents that interact with a complex, uncertain world to achieve a goal. Topics include multi-armed bandits, Markov decision processes, reinforcement learning, planning, and function approximation (online supervised learning). The course takes an information-processing approach to the concept of mind and briefly touches on perspectives from psychology, neuroscience, and philosophy. The course uses a recently created MOOC on Reinforcement Learning.
See certificate
Introduction to artificial intelligence focusing on techniques for building intelligent software systems and agents. Topics include search and problem-solving techniques, knowledge representation and reasoning, reasoning and acting under uncertainty, and machine learning (including neural networks). Recent applications such as planning and scheduling, diagnosis, decision support systems, and data mining.
The first of two courses on algorithm design and analysis, with emphasis on fundamentals of searching, sorting, and graph algorithms. Examples include divide and conquer, dynamic programming, greedy methods, backtracking, and local search methods, together with analysis techniques to estimate program efficiency.
An introduction to the tools of set theory, logic, and induction, and their use in the practice of reasoning about algorithms and programs. Basic set theory; the notion of a function; counting; propositional and predicate logic and their proof systems; inductive definitions and proofs by induction; program specification and correctness.
Basic concepts in computer data organization and information processing; entity-relationship model; relational model; SQL and other relational query languages; storage architecture; physical organization of data; access methods for relational data. Programming experience (e.g., Python) is required for the course project. Prerequisites: CMPUT 175 or 274, and 272.
Introduction to the principles, methods, tools, and practices of the professional programmer. The lectures focus on the fundamental principles of software engineering based on abstract data types and their implementations. The laboratories offer an intensive apprenticeship to the aspiring software developer. Students use C and software development tools of the Unix environment.
A continuation of CMPUT 174, revisiting topics of greater depth and complexity. More sophisticated notions such as objects, functional programming, and Abstract Data Types are explored. Various algorithms, including popular searching and sorting algorithms, are studied and compared in terms of time and space efficiency. Upon completion of this two course sequence, students from any discipline should be able to build programs to solve basic problems in their area, and will be prepared to take more advanced Computing Science courses.
CMPUT 174 and 175 use a problem-driven approach to introduce the fundamental ideas of Computing Science. Emphasis is on the underlying process behind the solution, independent of programming language or style. Basic notions of state, control flow, data structures, recursion, modularization, and testing are introduced through solving simple problems in a variety of domains such as text analysis, map navigation, game search, simulation, and cryptography. Students learn to program by reading and modifying existing programs as well as writing new ones. No prior programming experience is necessary. Prerequisite: Math 30 or 30-1. See Note (1) above. Credit cannot be obtained for CMPUT 174 if credit has already been obtained for CMPUT 274 or 275, except with permission of the Department.

Contact