My Portfolio

Background


Results-oriented data and finance professional graduated with a Master of Science in Applied Data Science and strong knowledge of machine learning and Python. Skilled in interpreting data, analyzing results using statistical techniques, and providing ongoing reports. Adept at developing and implementing data collection systems and other strategies to optimize statistical efficiency and data quality. Strong track record of collaborating with stakeholders and contributing to teams. Expertise assessing Economic Value Added Metrics, monitoring trading investment portfolios models, and maximizing equity income. Excellent communicator with the innate ability to manage multiple projects with competing deadlines.

Skills

Some of my skill tools to work with on my projects:

  • Python
  • R Programming
  • MS Excel & VBA
  • SQL
  • Tableau
  • FactSet & Bloomberg
  • English, Khmer & French

Hobbies

  • Talking about investment & Data
  • Reading
  • Soccer
  • Travel
  • Helping people
  • Listening to podcasts

Accomplishments


Guide to Research Triangle Park: a K-means application

Tools used: R programming: for coding Adobe illustrator: for editing chart or plot

Global Commodity Trade Statistics This assignment deal with visualization of global commodity trade statistics which is a collection of 5,000 commodities across most countries in the world over the last 30 years. The goal is to find the best interesting factors from this dataset to give the audience most insightful information. Dataset description: This file were provided by United Nation Statistics Division on the UNData site http://data.un.org/Explorer.aspx.

SQL-Investment-Performance_Project

Tools used: MS Access, Visio Diagram, SQL Server

The general idea of this portfolio performance will create a proper asset allocation which is the strategy that involves building a portfolio around asset classes including stock, bond, cash, real estate, and other alternative investment. This portfolio performance will reflect to each client risk tolerance, financial goal, and long-term target goal.

Sales Prediction across 60 shops and more than 100 products

Tools used: Python, Numpy, Pandas, Seaborn, Sklearn, matplotlib, xgboost, SARIMA, Dash

Predict Future Sales Data Science plays a huge role in forecasting sales and risks in the retail sector. Majority of the leading retail stores implement Data Science to keep a track of their customer needs and make better business decisions. For this final project we will do forecast by using different types of data mining algorithms to forecast the total amount of products sold in every shop.

Smart Phone Recommender Sentiment Analysis Chatbot

Tools used: NLTK, numpy, tflearn, tensorflow, random, json, matplot

The main idea of our project is based on the knowledge of NLTK package from lecture to build a human-AI reacting interface leaning on the result of natural language process sentimental analysis. Given the training data, the algorithm is able to predict the sentiment score for specific brand and model.

Let's talk!

I welcome the chance to help analyze using statitical experimentation and visualize your data into a digestable format in order to produces optimization to drive business impact, so please feel free to reach out to me via email or any of my social media channels.
Click here to view my resume on Google Drive.