
About Us
OUR STORY

WHAT WE DO
Asia-Pacific Stocks Quant (APSQ) is a Free quantitative finance site with AI-enabled models for all quantitative finance enthusiasts. Our unique models use a combination of AI, Econometric and Statistical tools to analyze and provide probabilistic forecasts of trend, support and resistance levels of stocks listed on major Asia-Pacific Exchanges. Together with our fundamental screens we provide investors with information on What to Buy and When to Buy. Currently, we cover the major Exchanges of the following countries: Singapore, Malaysia, Indonesia, Thailand, Hong Kong and India.
As this is a personal website, I am only able to feature a few stocks each week. But I invite readers to submit requests for me to cover the stocks they are interested in. Email me at the address in Contact page. Subject to my time constraint, I will run their desired stock through the models and post the results here, but without revealing the name of the requester. However, I must advise that the models are valid only for stocks with a minimum level of liquidity (average daily trading volume), and if your stock does not fit this requirement I will inform you.
Note: To derive maximum benefit from the posts we recommend that you first read the article "Explaining the graphics in the blog and reports"
Meet Me

Ng Tian Khean
(Honours) B.Sc. in Economics & Law, National University of Singapore.
The following phrase from a traditional European nursery rhyme which is also used by Gypsy fortune tellers to divine your future best describes me (minus the “beggar man” and “thief”): "Tinker, tailor, soldier, sailor, rich man, poor man, beggar man, thief."
From a stint in the military, to being an Aviary Assistant at one of the world’s largest bird parks, to helping a friend build offshore oil rigs in Shanghai; and being the personal assistant of an eccentric Indonesian tycoon, yes, I have done it all and more. However, the jobs relevant to this Blog are: Economics Research Officer on container ship transportation for Port of Singapore Authority, Securities Dealer in the country’s top brokerage, Vice President, Business Development for a quantitative finance company in Princeton, New Jersey; Associate Director in an Investor Relations Consultancy and the Editor of its weekly investment magazine. Just retired from full-time employment as of September 2024, the motivation for this website is to have something pleasant to do in addition to my numerous other hobbies. It is also a means by which I can connect with like-minded individuals globally.
My current models are a more recent development made possible by advancements in AI algorithms and computer power. Much has changed since the earliest days of AI in the form of rules-based Expert Systems, primitive Perceptrons, and Cellular Automata.
Email: tiankhean@gmail.com

Our Models
The models are based on a combination of Artificial Intelligence, Econometric and Statistical methodologies such Neural Networks, Decision Trees, ARIMA, Boosting/Bagging Ensembles, Monte Carlo Simulation, and unbounded MetaLog Distributions.
Model Inputs: Daily Open, High Low, Close and Trading Volume data.
These models can be likened to AI-driven traditional technical analysis (TA) models. but are minus the many inherent flaws of TA
Inherent Flaws of Traditional TA Indicators
The inherent flaws of traditional technical analysis indicators, such as RSI, MACD, Bollinger Bands, and Linear Regression, include their reliance on historical price data, which may not always predict future market movements accurately.
They all assume that the relationship between market variables is linear and that data distributions are Gaussian (Normal). But it is well-known that financial markets exhibit non-linear dynamic characteristics with distributions that are not Normal i.e. have more than 1 peak, are highly skewed and have long fat tails (kurtosis). And that the relationship between market variables is highly non-linear.
How Do We Avoid These Inherent Flaws of TA?
We first run all the models in our ‘arsenal’ of tools to find the combination of models that would yield the best performance for a specific stock.
-
AI models like Neural Nets, Decision Trees and Random Forests handle non-linearity easily through their activation functions, nodes and hidden layers of neurons;
-
Econometric models such as ARIMA and Holt-Winters Smoothing help to distinguish between noise and true signals;
-
Decision Trees and Random Forests of Decision Trees are used for data where Neural Networks tend to overfit;
-
Ensembles harness the output of multiple copies for a consensus that reduce the margin of error;
-
Statistical Bagging (random sampling with replacement) and Boosting (enhanced gradient descent) ensembles increase model performance;
-
Monte Carlo simulations test the model by running 1000 trials and establishing the Probability Density Functions (PDF);
-
Results are fitted to MetaLog PDFs which are best suited to are financial markets data to establish the 5% and 95% Confidence Levels for Support and Resistance prices.
The Learning Corner
For those without a mathematics or engineering background, quantitative analysis of financial markets can be daunting but also rewarding.
This section of the website is for the benefit of those who wish to learn more about the use of Artificial Intelligence in Finance, the characteristics of financial markets data, statistical modelling, econometric modelling, Monte Carlo simulation, and all such relevant topics. I will attempt to explain all these topics in as non-technical a language as possible and try to illustrate with examples from everyday life. For expediency, the articles in Learning Corner are retrieved from my previous Blog on Exchange Traded Funds listed on US Exchanges. But they are just as relevant and useful for Asia Pacific stocks.