Zhiyu(Garros) Gong's Projects
A major issue with traditional, statistical-inference approaches to A/B Testing is that it only compares 2 variables - an experiment/control to an outcome. The problem is that customer behavior is vastly more complex than this. Customers take different paths, spend different amounts of time on the site, come from different backgrounds (age, gender, interests), and more. This is where Machine Learning excels - generating insights from complex systems.
A machine learning model using classification algorithms and techniques to accurately detect if a credit card transaction is fraudulent or not.
Neural Style transfer is an optimization technique used to take a content and a style image and blend them together so the output image looks like the content image but painted in the style of the style image.
Build and apply a deep neural network to supervised learning
This is my digital resume portfolio
This project envisions running an exploratory data analysis on the dataset and then building a web page to display all the results and relevant information about the bank clients.
This app provides a comprehensive equity research dashboard using data from Financial Modeling Prep API.
Are you interested in ESG investment? Here is a sample project that deploys cutting-edge NLP techniques to analyze a company's ESG performance.
Financial dashboard using Python and Streamlit
Hi there π, This is my Github README.
Ask a home buyer to describe their dream house, and they probably won't begin with the height of the basement ceiling or the proximity to an east-west railroad. But this playground competition's dataset proves that much more influences price negotiations than the number of bedrooms or a white-picket fence.
A streamlit application for determining the sentiment labels of live tweets
This Streamlit app calculates an optimal investment portfolio based on a user-defined minimum required return and selection of funds.
The app caculates a company's valuation by making probabilistic projections about its future cash flows. After the user of the app has entered a stock ticker, the application pulls financial information from Yahoo Finance to provide historical financial figures on important inputs to the valuation model.
We are going to create a recurrent neural network and train it on a tweet emotion dataset to learn to recognize emotions in tweets. The dataset has thousands of tweets each classified in one of 6 emotions. This is a multi class classification problem in the natural language processing domain.
Purpose: Compare different option chains and calculate value of calls/puts with Black Scholes
A Modern Portfolio Theory based portfolio optimizer dashboard web app with Streamlit, from a userβs input stock tickers.
The repository is a streamlit based web app deployed as - https://rossman-streamlit.herokuapp.com/ which analyses sales for Rossman Stores using seaborn python library and make future sales prediction using Decision Tree Algorithm.
This app is a demonstration of how data solutions like data analysis and forecast can easily be made end user friendly, such type of apps (web apps) can be used to get an overview of a company and its performance in the recent time.
Predicting closing stock prices using Deep Learning models such as Long Short Term Memory (LSTM), a Basic Artificial Neural Network(CNN), Recurrent Neural Networks (RNN), Multilayer Perceptron (MLP) and Autoencoder.
The competition is simple: use machine learning to create a model that predicts which passengers survived the Titanic shipwreck.