Dao Chi's Portfolio
    • Posts
    • Analyze and Predict House Prices
    • Improve Product Review System
    • PUBG Player Role Analysis
    • Stock Price Prediction
    Hero Image
    PUBG Player Role Analysis

    Grouping professional players in Player Unknown’s Battlegrounds (PUBG) PCS Charity Showdown tournament into different groups of players using the k-means model. The tournament data will be scraped by selenium on the https://esports.pubgrank.org/ page. Building a simple regression model to analyze the relationship between the players from different clusters in each team and the team’s overall placement in the tournament. TL;DR Based on the elbow method, the model created 8 different clusters of players from the input data.

    November 13, 2020 Read
    Hero Image
    Stock Price Prediction

    Predicting HSBC Bank stock prices to make better buying/ selling decisions using an artificial recurrent neural network (RNN) architecture: Long short-term memory (LSTM). In addition to using past prices for prediction, I applied some stock technical analysis that I learned to see if it can outperform the deep learning model. Background and Motivation “The greatest risks are never the ones you can see and measure, but the ones you can’t see and therefore can never measure.

    September 3, 2020 Read
    Hero Image
    Improve Product Review System

    Improve the traditional product review system through text sentimental analysis and Natural Language Processing (NLP). By taking only the customer review comment about the product as input, I can create a sentiment detection algorithm to rate the product based on the comment. I will also include topic modeling in this project to detect the general topics of what the reviews are about. Background and Motivation I have an idea for this project from the situation I had when doing the thing that most college students do when they are bored: online shopping.

    August 28, 2020 Read
    Hero Image
    Analyze and Predict House Prices

    Analyzing and predict Boston housing prices using data scraped from trulia.com using advanced regression models. I will go in-depth for all the processes of this project: using Beautiful Soup to scrape data, analyzing and comparing different regression models, and building an Application Programming Interface (API) using Flask. Background and Motivation My goal for this project is to use the best regression model to predict Boston housing prices on Trulia based on the number of features that the source provides.

    July 13, 2020 Read
    Navigation
    • About
    • Skills
    • Experiences
    • Education
    • Recent Posts
    Contact me:
    • Email: lamdaochi27@gmail.com
    • Phone: (+1) 857-310-9338

    Toha Theme Logo Toha
    © 2020 Copyright.
    Powered by Hugo Logo