What is it about?

This paper explores the application of machine learning techniques, specifically Long Short-Term Memory (LSTM) and Support Vector Machine (SVM), for predicting stock prices in the Hong Kong share market. We utilized a publicly available dataset and performed feature engineering to extract relevant features. Subsequently, LSTM and SVM algorithms were applied to predict stock prices. Our results indicate that the proposed machine learning techniques can predict stock prices in the Hong Kong share market with the error metrics presented.

Featured Image

Why is it important?

Predicting stock prices has always been a challenging task due to their volatility and unpredictability. Our research provides a novel approach to predicting stock prices in the Hong Kong share market, which could be highly beneficial for investors and market analysts. Our results demonstrate that LSTM outperforms SVM in predicting stock prices, providing valuable insights for future research in stock price prediction.

Perspectives

Writing this paper was an intellectually stimulating journey. It was a collaborative effort, and I had the opportunity to work with my professional PhD supervisor. Our collective passion for exploring the potential of machine learning in predicting stock prices was the driving force behind this research. The process of comparing the effectiveness of different machine learning methods, specifically LSTM and SVM, in predicting stock prices was both challenging and rewarding. The results we obtained were encouraging and opened up new avenues for future research. I believe our findings could potentially revolutionize the way investors and market analysts approach stock price prediction. More than anything, I hope this paper sparks interest in the intersection of machine learning and finance, and inspires further research in this field. I look forward to seeing how our research contributes to the broader understanding of stock price prediction and influences future studies. I hope you find our research insightful and thought-provoking. I am eager to hear your feedback and perspectives on our work.

Chinyang Lin
University of Saint Joseph

Read the Original

This page is a summary of: An Exploratory Comparison of Stock Prices Prediction using Multiple Machine Learning Approaches based on Hong Kong Share Market, July 2023, ACM (Association for Computing Machinery),
DOI: 10.1145/3616712.3616762.
You can read the full text:

Read

Resources

Contributors

The following have contributed to this page