Michael's blog

When it comes to using machine learning algorithm to pick the stocks that are most likely to produce a good return, it is similar to seeking the opinion of an investment consultant. However, it can be unsettling to make your investment decision after listening to just one consultant. Now is the moment to get second opinions and hire more investment advisors to make sure the investment concept is reliable, doable, and profitable.

The same principle that you consult other machine learning algorithms to confirm the predictions made by these models are applied in ensemble learning. When you have collected all of the final data from these models, you may take your time relaxing in your nice chair like a big boss, analyzing the results, and making your important and sacred decision.

Photo by Brett Jordan on Unsplash

From the previous article, we’ve learned several indicators that we can calculate and use to evaluate the performances of your algorithm trading strategies. Given these indicators, we’re able to see how we can further polish our strategy and make it more seemingly profitable. Therefore, let’s work on our features to see how we can improve our machine learning trading strategy.

Grid trading strategy is famous for its simplicity and ease of execution, and you don’t even have to guess where the market is going. No technical analysis and indicators are needed or recognize any patterns among endless candlesticks. It was once known as the ‘no-loss strategy’.

But, is this true that there is a strategy that causes you no risk?

Today we’re going to look at what grid trading strategy is about, and we will conduct a series of backtesting against the Forex market to see whether it is the holy grail of our trading strategies.

I have to admit that my attention was drawn by the name of this indicator at the first glance. Therefore my interest in implementing a series of backtesting against this indicator was unavoidable. In today’s article, we’re going to introduce what Supertrend indicator is about and how to produce one yourself. After that, I will show you a series of backtest that I have performed and see what we can get out of them.

Phew! With all the hard work of fetching data, processing factors, splitting training and testing datasets, selecting the right model to train, you finally have your machine learning model trained and be able to test how powerful it is. You’re very excited to feed a bunch of test data and got a 100%+ rate of return. What a success! But be careful, rate of return is not the sole factor to evaluate the quality of your trading strategy. There are other metrics that help you to understand the strengths and weaknesses of your trading strategy, and you can improve your trading behavior based on these metrics.

Value investing is an investing strategy that has been popular for decades. The main idea involves picking quality stocks among distressed companies, buying and holding them for the long-term (over several years), and expecting the good quality stocks to remain good and rebound from the valley. In short, value investing is to buy good companies at a good price. In this post, we’re going to go through the framework that some of the value investors use to evaluate the company value.

We talked about how to use MACD indicator and other secondary indicators to tell when to long certain stocks in the previous articles. If you haven’t read them yet, below are the links to catch up on where we left. But, is this the end of the optimization of our trading strategy? In this article, we’re going to demonstrate the power of RSI indicators and see how this indicator can be a help to our current trading strategy.

• How to save your silver bullets with MACD strategy?
• Optimize your MACD strategies with advanced indicators

After reading the post How to Improve Investment Portfolio with Rebalancing Strategy in Python by Bee Guan Teo, I was thrilled to know that this trading strategy can be that powerful and the portfolio return is greater than any of my existing trading strategies. Therefore I decided to give it a try and backtest this strategy to verify the profitability it claimed.

Previous reading:

• 【Pair Trading】Introduction to pair trading strategy
• 【Pair Trading】In-depth analysis of 5 distance approach strategies in pair trading

In the previous post 【Pair Trading】In-depth analysis of 5 distance approach strategies in pair trading, we have conducted various research against each variation of distance approaches in pair trading strategy. Despite the research has given us probable insights whether there is an $\alpha$ exists in the strategy we constructed, we still haven’t established our portfolio construction strategy. Here we introduce a concept called the “long-short equity (LSE)” strategy.

Therefore, the objectives of this post are consists of three:

1. What is the long-short equity (LSE) strategy
2. Review our backtest results to see the impact of adopting the long-short strategy
3. What are the advanced strategies that we can explore

After knowing what the pair trading strategy is about from the previous post, we’re going to use the QuantConnect platform to research and validate each variation of the distance method. The agenda of this post would be:

1. Introduction: what is the distance approach and what are its variants
2. Research methodology: the methodology we use to conduct this research
3. Research and performance analysis: Implement each variation and compare

Let’s get it started!