This paper proposes a novel framework for stock price forecasting that integrates visual representations of time series data with an advanced deep learning model, named Temporal Fusion Transformer (TFT). Specifically, historical Open, High, Low, and Close (OHLC) prices of Apple stock from 2015 to 2025 are transformed into images using Gramian Angular Fields (GAF), from which high-level features are extracted via a pre-trained ResNet-18 network to serve as the past covariates of the TFT model. To evaluate the performance, we compare the TFT model against a Long Short-Term Memory (LSTM) network trained on raw OHLC data. Empirical evaluations reveal that the TFT model achieves an RMSE of 5.05, and MAPE of 1.99 %, significantly outperforming a baseline LSTM model with corresponding values of 3 8. 0 0, and 16.21, highlighting its potential for improved accuracy in financial time series prediction. These findings highlight the effectiveness of integrating imagebased time series representations with deep learning models for financial forecasting, offering a promising avenue for improving predictive accuracy in stock price forecasting.

This study presents a comparative analysis of different reinforcement learning configurations for the stock trading problem, with IBM as a case study. To address the challenge of noisy data, we explore the effectiveness of various denoising methods, including Wavelet Transform, Temporal Attention Network (TAN), and Fourier Transform, in improving model performance. We employ two different architectures, Multilayer Perceptron (MLP) and Long Short-Term Memory (LSTM), to calculate Q-values for each possible action, resulting in six distinct configurations. Evaluation is based on key metrics such as yearly returns, Sharpe ratios, and maximum drawdowns over a specified timeframe. We compare the performance of our models against benchmark strategies including Relative Strength Index (RSI), Moving Average Convergence Divergence (MACD), and Bollinger Bands. Our results demonstrate that DQN-based trading outperforms benchmark methods. Furthermore, configurations utilizing TAN, whether in conjunction with MLP or LSTM, consistently exhibit superior performance. These findings suggest that TAN-based denoising methods combined with DQN offer promising solutions for enhancing stock trading strategies using reinforcement learning techniques.

There has been a recent surge of interest on development of news-oriented Deep Neural Network (DNN) architectures to predict stock trend movements. Limited focus is, however, devoted to reliability fusing different available information resources. In this regard, this paper proposes a Noisy Deep Stock Movement Prediction Fusion framework (ND-SMPF) for stock price movement prediction. The proposed ND-SMPF predictive framework uses information fusion to combine twitter data with extended horizon market historical prices to boost the accuracy of the stock movement prediction task. More specifically, Noisy Bi-directional Gated Recurrent Unit (NBGRU) is utilized coupled with a Hybrid Attention Network (HAN) to extract news level temporal information. A two level attention layer is used to identify relevant words with highest correlation and effects on the stock trends, which are then fused with historical price data to perform the prediction task. A real dataset is incorporated to evaluate performance of the proposed ND-SMPF framework, which illustrates superior performance in comparison to its recently developed counterparts.