Category Archives: TA

Technical Analysis

Open a topic for Machine Learning and Technical Analysis

In early 2013, I made a proposal to HKUSPACE as well as School of Continuing & Professional Studies, The Chinese University of Hong Kong.  The proposal is about opening a General Short Course for the about topic.

Machine learning (an topic in AI) is an interesting subject and find its application in modern live. Many web site, google, facebook, amazon, … uses the technology to entertain their customer as well as to make their advertisement more effective.

The ML is not rocket science and can be understood by general public with high school education. On the other side, the maths and model behind it may threaten most population. Further, learning something without solid example makes the student feels boring and lost the initiative.

Technical Analysis for finance forecasting is an interesting subject to many people. They have a lot of doubts about the feasibility of it. This course will use Technical Analysis as an subject to attract the audience to learn ML and use the technique to verify if Technical Analysis works or not.

The objective of the course is to teach the general concept as well as the practical use of the ML in data analysis.

The course is actually a 2 courses in 1. In every lecture, the first part will talk a topics in TA, and teach the student how to verify if a TA works or not. The second part of each lecture will be a topic in ML. Gradually, the student will discover the ML is very useful for them to understand / interpret TA.

Unfortunately, there is no any response from both parties.  I thought of to book classroom to carry out such course on my own, but it involves a lot cost and advertisement.  Also quite difficult to book the lecture hall in government facility.  Finally, I decided to take a more relax approach, I write them in a blog.

Lect Part I Part II
1 Introduction ML Problem Statement
2 Tools for backtest The Linear Model
3 Backtest moving average, AMA Error and Noise, Overfitting
4 Backtest RSI and oscillators Training versus Testing
5 Backtest Momentum Theory of Generalization
6 Backtest MACD The VC Dimension
7 Backtest OBV Bias-Variance Tradeoff
8 Stochastic oscillator Neural Networks
9 Candle sticks patterns Regularization
10 Martingale strategy Validation
11 Elliott wave principle Support Vector Machines
12 Data snooping, look-ahead bias Kernel Methods, RBF
13 Traps in ML