Chris IO

My I/O Module in Life

Web Scraping IV - Scrapy and Sentiment Analysis

Project Description: Scrap forex news specific to each currency pair in the last 24 hours on FXStreet at 7am each day, then calculate an average sentiment score. Use of Tools: Scrapy: A we...

Web Scraping III - Data Synchronization

In this article, I would continue from the previous example - crawling betting odds from Jockery Club, to update on the data synchronization using scp and sshpass. Previously, the data was stored ...

Web Scraping II - On a Remote Ubuntu Machine

In the last article, I have managed to collected and saved the betting odds on the Hong Kong Jockery Club, using Splinter, a Python light-weight scrapper leveraging on Selenium. As scraping on loc...

Web Scraping - Football Match on Jockery Club

Recently I have been drawn to the technique of web scraping. It is a cool technique to collect first-hand data that is not readily available through an API or preporcessed. The good thing is, given...

Pair Trading - II - Regression and Ornstein-Uhlenbeck process(O-U Model)

This is a continuation of the Pair Trading Series. For the first article which discusses how to find out potential trading pairs using clustering algorithms DBSCAN, you may go back to here. In thi...

When I ran like what Forrest Gump does

Today was an awesome one where I managed to bust my bad mood. It was the beginning of the semester, but I have already felt I got stuck in everything I do. I got stuck in the coding projects that ...

Pair Trading - I - DBSCAN on HK Stocks

Selecting Stock Pair with a Click

I was inspired by the Pairs Trading with Machine Learning on Quantopian, where the author Mr. Jonathan Larkin applies DBSCAN, a clustering technique to select stock pairs that behave similarly. Usi...

Understanding HSI - IV - Momentum Signal - Efficient Ratio benchmarked to HSI

In the last article, I have done a comparison of EWMA pairs as a short sell signal. I treated the signal as a categorical one(0,1), assumpting that only one contract is traded whenever a signal pro...

Numerai Tutorial - II - Label Specific Preprocessing and Iterative Screening

Make sense of input data

In the previous article, I have demonstrated the method to iteratively read in the data for Numerai tournament, implement data preprocessing, and high-level algorithms from scikit learn by creatin...

Numerai Tutorial - I - Vanilla Algorithms and Adversarial Validation

plug-and-play machine learning

Numerai Competition is an online machine learning tournament which is operated by Numerai, a hedge fund. You may refer to this article for an introduction. In this article, I want to describe how I...