Jul 2026· International Journal of Adaptive Management and Business Intelligence· 0 citations· 24 references
TL;DR
The results indicate that self-supervised representation learning can serve as an effective and scalable substitute for manual feature engineering in finance time-series forecasting.
Abstract
Accurate prediction of financial time series is still a difficult problem as financial markets display high volatility, non-linearity and stochasticity. Traditional forecasting methods necessitate extensive domain knowledge in designing technical indicators for subsequent analysis, often resulting in the loss of intricate time dependencies. The goal of the present study is to propose a framework allowing for learning representations automatically from raw financial data that are informative in downstream forecasting tasks. The proposed framework, contrasting predictive coding (CPC), is based on self-supervised representation learning. The learned embeddings are applied to Linear Regression, Random Forest and LSTM to predict the next-day log returns of three major foreign exchange currency pairs: EUR/USD, GBP/USD and USD/JPY. Evaluating the Performance of CPC-Generated Representations and Conventional Handcrafted Features on Forecasting Models trained on Historical Market Data. The LSTM with CPC context embeddings produces the best overall performance with a drop in mean squared error of 18%, directional prediction accuracy of roughly 59%, and better risk-adjusted trading performance with Sharpe ratios above 0.7. Additionally, the outcomes of transfer learning experiments reveal that a CPC encoder trained using one currency pair efficiently generalizes to other currency pairs. The results indicate that self-supervised representation learning can serve as an effective and scalable substitute for manual feature engineering in finance time-series forecasting.
The findings demonstrate that rigorous leakage-free validation is essential for reliable forecasting research and that, for monthly Robusta coffee prices, increased model complexity does not necessarily yield superior predictive performance.
Dler H Kadir, D. Khalil, Azhin M. Khudhur· Forecasting· 0 citations
A multivariate deep learning framework based on a stacked Long Short-Term Memory (LSTM) network for short-term gold price forecasting that significantly outperforms the traditional Recurrent Neural Network (RNN) in terms of stability, accuracy, and robustness.
P. N. Huu, Bach Dang Pham, T. Thanh· Neural computing & applicati...· 0 citations
Stock price forecasting is a key part of investment decision-making, especially for high-capitalization stocks such as PT Bank Central Asia Tbk. (BBCA). Accurate prediction remains challenging because complex market dynamics and nonlinear price movements influence stock prices. This study proposes a multivariate Long Short-Term Memory (LSTM) model that integrates the closing price and the RSI-14 technical indicator as input features to improve accuracy over conventional univariate approaches. We obtained historical data from the Yahoo Finance API covering January 2015 to December 2025, totaling 2,698 trading days after RSI-14 feature engineering. The dataset was split to 80:20 for training and testing, with MinMaxScaler normalization applied only to the training data to prevent data leakage. The LSTM model used 100 neurons with an input shape of (10, 2) and was trained using the Adam optimizer with early stopping at epoch 24 to avoid overfitting. Evaluation results show an RMSE of 169.72 IDR, an MAE of 134.68 IDR, a MAPE of 1.58%, and an R² of 0.9368, indicating a good regression-level fit. Adding the RSI-14 feature improved the regression metrics relative to a univariate closing-price-only LSTM. Given the modest trend-classification accuracy and the lack of trading back testing, transaction costs, or risk-adjusted performance measures, view the results as a methodological contribution rather than direct evidence of practical investment value. Future work could extend this research by exploring hybrid architectures that combine LSTM with attention mechanisms or Transformer-based models, and by validating the approach on other high-capitalization stocks to assess generalizability across market conditions.
Muhammad Jahron, J. A. Widians, Andi Tejawati· TEPIAN· 0 citations
The Indian stock market is characterized by high volatility, non-linear price behaviour, and sensitivity to
macroeconomic, sectoral, and sentiment-driven factors, which limits the accuracy of traditional linear forecasting models such
as ARIMA. Building on our earlier literature review and problem formulation, this paper presents the implementation and
evaluation of an integrated deep learning framework for next-day closing price prediction of Indian equities. The framework
combines a two-layer Long Short-Term Memory (LSTM) network with four complementary technical indicators — Moving
Average Convergence Divergence (MACD), Relative Strength Index (RSI), the 10–20 day Exponential Moving Average (EMA)
crossover, and the Stochastic Oscillator — as engineered input features, and a downstream XGBoost classifier that converts the
LSTM's continuous price forecast, together with the current indicator states, into discrete BUY, HOLD, or SELL trading signals
with associated confidence scores. The complete pipeline is implemented as a full-stack platform (Python, Flask, MongoDB,
React) that retrieves real-time NSE/BSE data through the yfinance API. The proposed model is evaluated on RELIANCE.NS
using Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE), supported by a per-indicator ablation study and a
comparison against an autoregressive (AR) linear baseline, a Support Vector Machine (SVM) regressor, and a single-indicator
LSTM baseline.
The proposed model achieved an RMSE of ₹28.56 and MAE of ₹23.48 (MAPE 1.71%) on the held-out test partition, achieving
the lowest RMSE among all compared models, while the downstream XGBoost signal classifier achieved 91.7% accuracy on
held-out BUY/HOLD/SELL labels.
Ayush Jha, Pankaj Singh· International Journal for Re...· 0 citations
Predicting financial asset returns remains one of the most difficult challenges in empirical finance, driven by the low signal-to-noise ratio and the semi-strong form of market efficiency. While deep learning models, especially LSTM networks, have shown promise in capturing temporal dependencies, standard architectures often struggle to account for the cross-sectional heterogeneity of asset returns. This paper proposes a novel architectural extension to the basic LSTM model designed to improve both predictive accuracy and model interpretability. The framework integrates macro-financial covariates to capture broader economic signals and learnable sector embeddings to encompass heterogeneity by sector. The trading strategy involves constructing a long-short portfolio based on daily directional forecasts for each S&P 500 constituent, targeting stocks expected to under- or outperform the cross-sectional median return of the S&P 500. Model Performance is evaluated against three competitive benchmarks: a basic LSTM, a Random Forest model and a traditional market buy-and-hold strategy. The empirical results demonstrate that the LSTM with sector embeddings outperforms all benchmarks across key risk and return metrics. By utilizing sector embeddings, the model explicitly incorporates cross-sectional heterogeneity, allowing it to adapt to varying industry dynamics within the market. To address the black-box nature of deep learning, I use latent space visualizations to analyse how the model differentiates between sectors, providing insights into the internal representation of the sectors in the LSTM. The impact of the sector information can be quantified using a novel contribution metric by inspecting the weights of the LSTM. The predictive signal is driven by a short-term reversal factor and an industry momentum factor.
The findings indicate that passing attention-derived context into a bidirectional memory module offers a practical means of combining long-horizon structure with local temporal variation, although computational cost remains relevant for latency-sensitive trading applications.
Hao Wu· AI and Data Science Journal· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
