Development of trading strategies using fundamental and technical analysis in SGX

Abstract

Fundamental and technical analysis are the two pillars of stock analysis. Fundamental analysis helps us identify stocks that are worthy of investments. Technical analysis gives us insights in the trend of stock prices and helps us determine entry and exit points. This study combined both approaches to form stock market strategy. Fundamental analysis was used to filter out five stocks with strong growth potential in Food & Beverage Sector in SGX. After that, Long Short-Term Memory (LSTM) network was used to predict future prices of the selected stocks. In terms of feature engineering, Least Absolute Shrinkage and Selection Operator (LASSO) and Principal Component Analysis (PCA) were used to reduce the dimension of the input data. With predictions in future stock prices, a trading strategy was tested on historical data of the five stocks and achieved an average 28.3% annualized rate of return.

This study first shows that use of dimensionality reduction method LASSO enhances the accuracy of the LSTM model and gives good predictions on stock prices. Secondly, it proves that machine learning models can be useful in generating rewarding trading strategies in real life. Lastly, this study demonstrates that it is not only feasible but also powerful to incorporate fundamental and technical analysis.