yitaohu88 Goto Github PK
Type: User
Type: User
A Convolutional Neutral Network built using Python Jupiter Notebook For Udacity Machine Learning Engineer Micro-degree
In-class projects completed for Corporate Finance Course
Winter 2020 Course description: Econometric and statistical techniques commonly used in quantitative finance. Use of estimation application software in exercises to estimate volatility, correlations, stability, regressions, and statistical inference using financial time series. Topic 1: Time series properties of stock market returns and prices Class intro: Forecasting and Finance The random walk hypothesis Stationarity Time-varying volatility and General Least Squares Robust standard errors and OLS Topic 2: Time-dependence and predictability ARMA models The likelihood function, exact and conditional likelihood estimation Predictive regressions, autocorrelation robust standard errors The Campbell-Shiller decomposition Present value restrictions Multivariate analysis: Vector Autoregression (VAR) models, the Kalman Filter Topic 3: Heteroscedasticity Time-varying volatility in the data Realized Variance ARCH and GARCH models, application to Value-at-Risk Topic 4: Time series properties of the cross-section of stock returns Single- and multifactor models Economic factors: Models and data exploration Statistical factors: Principal Components Analysis Fama-MacBeth regressions and characteristics-based factors
Basic bond valuation in HW1 and simple strip-principal arbitrage trading algorithm implemented in HW2
Machine Learning and Data Mining: Regression [Linear (Selection and Shrinkage, Dimension Reduction, Beyond Linearity) & Non-Linear Regressions (Logistics, K-NN, Trees)], Cross Validation (LOOCV, K-Folds, Bias vs. Variance), Classification (LDA, QDA, K-NN, Logistic, Tree, SVM), Clustering (PCA, K-Means, Hierarchical) This course will provide an introduction to main topics in data mining / statistical learning, including: statistical foundations, data visualization, classification, regression, clustering. Emphasis will be on statistical learning methodology and the models, intuition, and assumptions behind it, as well as applications to real-world problems. You may find my final project in the stats 415 project folder. Project Summary Implemented all the classifier learned throughout the semester to predict obesity rates in America as classified through the BMI with the best classifier as 7-fold KNN and prediction accuracy of 81.54% Analyzed model selection methods to provide the most optimal model and finding the best predictors; concluded that BMI can be non-parametrically predicted based off income, eating habits, exercise habits and shopping habits
Estimated the Covariance Matrix with the LedoitWolf and Diagonalization shrinkage methods, significantly reducing the out-of-sample estimating errors Constructed a risk parity and a minimum-variance portfolio using Convex optimization and nested clustered optimization algorithm Backtested the risk parity and minimum-variance portfolios with monthly rebalancing and 49 industry portfolios as asset universe, improving the Sharpe Ratio from 0.23 (no shrinkage) to 0.63
A Simple demo on how to build a trading algorithm
The goal is to run a backtest simulation using some classical alphas. The backtest is intended to be realistic due to the inclusion of transaction costs.
I am a MFE (Master of Financial Engineering) student at UCLA Anderson School of Management, pursuing a career in quantitative finance or data science
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.