25 August 2023
Aswath Babu H
Researchers extracted stock indicators like moving averages, RSI, MACD to analyze price trends
Quantum annealing was effective for feature selection from indicators
Quantum SVM did not outperform classical SVM significantly for price classification
Study provides insights on using quantum algorithms for stock prediction
Limitations exist in applying quantum techniques to financial analysis currently
Quantum techniques for stock price prediction
Researchers conducted experiments using quantum algorithms like quantum annealing and quantum support vector machines to predict stock prices, comparing them to classical machine learning models. They extracted stock indicators like moving averages and relative strength index from Apple, Visa, Johnson & Johnson, and Honeywell stock data. Quantum annealing was effective for feature selection, outperforming principal component analysis. However, quantum support vector machine did not significantly outperform classical SVM for binary stock price classification. The study sheds light on potential advantages and limitations of quantum techniques for financial analysis.
No comments yet, be the first to start the conversation...
Sign up to comment on this paper