Sun, XianfangAloraini, Osama Mohammed A2024-01-222024-01-222024cardiff harvard referencinghttps://hdl.handle.net/20.500.14154/71249The objective of this project is to develop stock price prediction algorithms using two deep learning models: LSTM and CNN. The data features utilised include stock technical analysis, commodities data like energy prices and gold, and key market indices from the U.S. stock market. Additionally, technical indicators are employed to obtain trading strategies, represented as vectors for data features. Moreover, based on features categories, nine experiments were conducted for each model to assess the impact of various feature combinations. Therefore, the primary evaluation metrics for both models are accuracy and simulated trading profit. Lastly, the results from these experiments are compared, and the outputs of the two models are also compared.This study investigates the efficacy of deep learning models, specifically Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN), for forecasting stock price movements in the U.S. stock market. The dataset used includes 133 stocks across 19 different sectors and covers the period from 2010 to 2023. Moreover, to enrich the dataset, eleven technical indicators and their corresponding trading strategies, represented as vectors, were integrated along with market indices and commodities data. Consequently, various experiments were conducted to assess the effectiveness of different feature combinations. The findings reveal that the CNN model outperforms the LSTM model in both accuracy and profitability, achieving the highest accuracy of 59.7%. Furthermore, models demonstrated an ability to identify significant trend-changing points in stock price movements. Another finding shows that translating trading strategies into vector form plays a critical role in enhancing the performance of both models. However, it was observed that incorporating external features like market indices and commodities data led to model overfitting. Conversely, relying only on stock-specific features triggered a risk of model underfitting.66endeep learningmachine learningartificial intelligencestockstocksAILTSMCNNneural networkConvolutional neural networkConvolutionalLong Short-Term MemorypredictionclassificationmodelThesis