.
Portfolio optimization remains a central challenge in finance, demanding accurate stock forecasting and effective risk-return trade-offs. This study introduces a novel hybrid model, the Improved Arithmetic Optimization Algorithm Long Short-Term Memory (IAOA-LSTM), tailored for portfolio selection in the biotechnology and oil gas sectors. Leveraging a decade-long dataset comprising daily prices of 50 representative stocks, the proposed model integrates the temporal modeling strength of LSTM with the global search capabilities of an enhanced Arithmetic Optimization Algorithm. Comparative analyses against standard Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), Grid Search LSTM(GRID-LSTM), Random Search LSTM (RANDOM-LSTM), Genetic Algorithm LSTM (GA-LSTM) models demonstrate IAOA-LSTM’s superior predictive performance, achieving the lowest errors. Stocks were ranked using a reconstruction error-based metric, and the most predictable were selected to construct optimized portfolios. Furthermore, the efficient frontier, derived via Monte Carlo simulations, identified the portfolio with the highest Sharpe ratio at volatility-return coordinates, offering the most favorable risk-adjusted return. Rigorous statistical testing confirms the model’s significant improvement over benchmarks. These findings underscore the potential of IAOA-LSTM in enhancing investment strategies through deep learning (DL) and bio-inspired optimization. By aligning sector-specific dynamics with advanced modeling, this research offers a robust decision-support tool for investors aiming to maximize returns under uncertainty.
A precise characterization of molecular vibrations and thermodynamic properties is essential for applications in spectroscopy, computational modeling, and chemical process design. In this study, the q-deformed Tietz (qDT) oscillator is applied to examine vibrational energy spectra of diatomic molecules and thermodynamic properties of nonlinear symmetric triatomic molecules. Vibrational energy eigenvalues were obtained analytically using the improved Nikiforov-Uvarov method. The symmetric vibrational mode was described with the qDT oscillator, while asymmetric and bending modes were modeled using the rigid rotor harmonic oscillator (RRHO); translational and rotational contributions were incorporated from standard models. For diatomic molecules (BrF, CO+, CrO, ICl, KRb, NaBr), mean absolute percentage errors (MAPE) ranged from 0.53% to 1.73% for vibrational energy eigenvalues and 0.34% to 1.08% for potential fits. Extending the analysis to triatomic molecules, thermodynamic properties of AlCl2, BF2, Cl2O, OF2, O3, and SO2 were calculated with the qDT model, yielding low MAPE benchmarked against NIST-JANAF reference data: entropy 0.203% to 0.614%, enthalpy 1.792% to 5.861%, Gibbs free energy 0.419% to 1.270%, and constant-pressure heat capacity 1.475% to 4.978%. These results demonstrate the versatility and accuracy of the qDT oscillator as an analytical framework connecting molecular potentials, vibrational energies, and thermodynamic functions, providing a practical and tractable approach for modeling both diatomic and symmetric triatomic systems.
This study examined the influence of audit committee attributes on audit reporting lag (ARL) of listed industrial goods companies in Nigeria from 2020 to 2024. Using an ex post facto research design, secondary data were collected from the annual reports of 10 selected companies among the 13 industrial goods firms listed on the Nigerian Exchange Group (NXG). The study focuses on three key audit committee attributes: audit committee financial expertise (AFEXP), audit committee independence (ACI), and audit committee meetings (ACM), while controlling for firm size, leverage, and firm age. Data were analyzed using multiple regression. The findings revealed that audit committee meetings (ACM) and audit committee independence (ACI) have a significant effect on audit reporting lag of listed Industrial goods companies in Nigeria. However, audit committee financial expertise (ACFEXP) has no significant influence on audit reporting lag of listed Industrial goods companies in Nigeria. To expedite financial reporting timeliness, audit committees in the industrial goods sector in Nigeria should be composed primarily of independent directors who can streamline agendas and focus only on essential discussions to avoid excessive meetings that would significantly delay the release of financial statements. Hence, excessive meetings should be avoided unless necessary to expedite audit processes.
This study examines the effect of high interest rates on economic growth in Nigeria, focusing on the Central Bank of Nigeria's (CBN) monetary policy framework. It specifically evaluates the short-run and long-run relationships among the Monetary Policy Rate (MPR), Gross Domestic Product (GDP), inflation rate, exchange rate, and broad money supply. The study adopts an ex-post facto research design and employs annual time-series data covering 2005–2024. The study analyzes data using the Autoregressive Distributed Lag (ARDL) model to examine short-run and long-run dynamics among variables with different orders of integration. The model assesses the effects of MPR, inflation rate, exchange rate, and broad money supply on economic growth. The findings indicate that high interest rates, proxied by MPR, have a statistically significant negative effect on GDP, suggesting that tight monetary policy constrains economic growth by increasing borrowing costs and discouraging private investment. Conversely, broad money supply has a positive and statistically significant effect on GDP, demonstrating the importance of adequate liquidity in stimulating investment and productive economic activities. The findings further indicate that although inflation control remains essential, excessively high interest rates may undermine output expansion and private-sector investment. The study concludes that the CBN should pursue a balanced monetary policy that controls Inflation without imposing excessively restrictive interest rates. Policymakers should improve access to affordable credit for businesses and households and strengthen monetary-fiscal policy coordination. Such measures would support investment, sustainable economic growth, price stability, and improved macroeconomic performance in Nigeria.
This study evaluates the performance of the Runge–Kutta Dual Attention (RUN-DA) optimization framework for hyperparameter tuning in a dual-attention Long Short-Term Memory (LSTM) model for financial time-series forecasting. The experiment was conducted using historical stock price data of MRS Oil Plc covering the period 2012–2024, representing a Nigerian financial market dataset. The proposed optimizer was compared with the Genetic Algorithm (GA) and Brown Bear Optimization Algorithm (BBOA) under consistent experimental conditions. Model performance was assessed using validation Mean Squared Error (MSE) and computational efficiency. Results show that RUN-DA achieved the lowest mean fitness value of 0.1369, compared with 0.4054 for GA and 0.1924 for BBOA. Sensitivity analysis indicated that moderate learning rates and time-step values produced more stable generalization performance. The evaluation under different market regimes further showed that RUN-DA maintained relatively lower fitness values across volatility conditions, decreasing from 0.2343 in low-volatility periods to 0.0473 in high-volatility periods, while GA and BBOA recorded higher corresponding values. In terms of computational efficiency, RUN-DA converged in 1015.23 seconds, slightly faster than GA (1073.25 seconds) and substantially faster than BBOA (2147.05 seconds). These results suggest that RUN-DA provides an effective optimization approach for improving LSTM-based financial forecasting models, although further validation on additional financial assets and evaluation metrics is recommended.
