Deep Learning for Financial Markets: A Case-Based Analysis of BRICS Nations in the Era of Intelligent Forecasting

Journal of Economics Finance and Accounting Studies, Journal Year: 2025, Volume and Issue: 7(1), P. 01 - 15

Published: Jan. 5, 2025

In this paper, we develop a method based on deep learning in financial market prediction, which includes BRICS economies as the test cases. Financial markets are rife with volatility that is affected by "bed of complexity," coddled local and distal factors. To leverage these vast datasets both models such Convolutional Neural Networks (CNNs), Long Short Term Memory (LSTM) networks well hybrid architectures used study. The paper evaluates predictive accuracy models, so doing, identifies their strengths predicting temporal dependencies intricate patterns. particular, techniques applied to case studies individual countries highlight application disparate country specific problems, liquidity crises shocks. These findings show classical statistical methods outperformed systems precise reliable forecasting. This research highlights ability AI driven change decision making processes, improving investor confidence economic stability nations. study also readers value analysis, especially developing countries. Application e.g. (CNNs) excel at identifying spatial patterns, Short-Term renowned for prowess sequential time series data, real world prediction explained. addition, discusses extend knowledge, fusing improve how develops solve particular challenges. Through reading notes get exposed data preprocessing normalization feature selection important boosting performance. an introduction evaluation using MSE R-squared values validating them terms outputs. combines theory practical offer useful educational resource students, researchers, practitioners who want apply forecasting complex dynamic global markets.

Language: Английский

---

Hybrid BiGRU‐CNN Model for Load Forecasting in Smart Grids with High Renewable Energy Integration

IET Generation Transmission & Distribution, Journal Year: 2025, Volume and Issue: 19(1)

Published: Jan. 1, 2025

ABSTRACT Integrating renewable energy sources into smart grids increases supply and demand management because are intermittent variable. To overcome this type of challenge, short‐term load forecasting (STLF) is essential for managing energy, demand‐side flexibility, the stability with integration. This paper presents a new model called BiGRU‐CNN to improve operation STLF in grids. The integrates bidirectional gated recurrent units (BiGRUs) temporal dependencies convolutional neural networks (CNNs) extract spatial patterns from consumption data. newly developed BiGRU captures past future contexts through processing, CNN component extracts high‐level features enhance accuracy prediction. compared two other hybrid models, CNN‐LSTM CNN‐GRU, on real‐world data American electric power (AEP) ISONE datasets. Simulation results show that proposed outperforms single‐step yielding root mean square error (RMSE) 121.43 123.57 (ISONE), absolute (MAE) 90.95 62.97 percentage (MAPE) 0.61% 0.41% (ISONE). For multi‐step forecasting, yields RMSE 680.02 581.12 MAE 481.12 411.20 MAPE 3.27% 2.91% can generate accurate reliable STLF, which useful massive energy‐integrated

Language: Английский

---

Prediction of the Financial Stock Market: A Comprehensive Analysis of Artificial Intelligence

International Journal of Advanced Research in Science Communication and Technology, Journal Year: 2025, Volume and Issue: unknown, P. 744 - 754

Published: Jan. 1, 2025

Since the inception of stock trading, scholars and investors have searched for reliable methods to forecast course values next day. there are several variables that might influence day, forecasting prices is a challenging undertaking. Stock Market Forecasting (SMF) forward-looking process anticipating future values, allowing make sound financial decisions. In order create predictions, academics started using machine learning approaches in conjunction with technical indicator analysis. However, precision predictions lacking. One progress applying ML, particularly LSTM networks, market lies automating this process. Human bias implies same can be misleading contribute fact they need use ML AI technology. The data used was fetched from finance.yahoo.com, confidence data, it took steps such as lemmatisation, null value management deletion duplicates. A total four different prediction were utilised: also being ANN, CNN, K-Nearest Neighbour many other algorithms. model's performance evaluated measures including F1-score(Fs), recall(Rc), accuracy(Acc), precision(Pr). Outcomes showed models not all equally successful; however, model had best accuracy at 93%. Future attempts consider categorisation strategies improving preprocessing improve Acc

Language: Английский

---

Multi-Scale Building Load Forecasting Without Relying on Weather Forecast Data: A Temporal Convolutional Network, Long Short-Term Memory Network, and Self-Attention Mechanism Approach

Buildings, Journal Year: 2025, Volume and Issue: 15(2), P. 298 - 298

Published: Jan. 20, 2025

Accurate load forecasting is of vital importance for improving the energy utilization efficiency and economic profitability intelligent buildings. However, restricted in popularization application conventional techniques due to great difficulty obtaining numerical weather prediction data at hourly level requirement conduct predictions on multiple time scales. Under condition lacking meteorological forecast data, this paper proposes utilize a temporal convolutional network (TCN) extract coupled spatial features among multivariate loads. The reconstructed are then input into long short-term memory (LSTM) neural achieve extraction features. Subsequently, self-attention mechanism employed strengthen model’s ability feature information. Finally, carried out through fully connected network, multi-time scale model building loads based TCN–LSTM–self-attention constructed. Taking hospital as an example, predicts cooling, heating, electrical next 1 h, day, week. experimental results show that scales, proposed more accurate than LSTM, CNN-LSTM, TCN-LSTM models. Especially task predicting 1-week scale, achieves improvements 16.58%, 6.77%, 3.87%, respectively, RMSE indicator compared with model.

Language: Английский

---

Dynamic Adaptive Artificial Hummingbird Algorithm-Enhanced Deep Learning Framework for Accurate Transmission Line Temperature Prediction

Electronics, Journal Year: 2025, Volume and Issue: 14(3), P. 403 - 403

Published: Jan. 21, 2025

As power demand increases and the scale of grids expands, accurately predicting transmission line temperatures is becoming essential for ensuring stability security systems. Traditional physical statistical models struggle with complex multivariate time series, often failing to balance short-term fluctuations long-term dependencies, their prediction accuracy adaptability remain limited. To address these challenges, this paper proposes a deep learning model architecture based on Dynamic Adaptive Artificial Hummingbird Algorithm (DA-AHA), named DA-AHA-CNN-LSTM-TPA (DA-AHA-CLT). The integrates convolutional neural networks (CNNs) local feature extraction, long memory (LSTM) temporal modeling, pattern attention mechanisms (TPA) dynamic weighting, while DA-AHA optimizes hyperparameters enhance stability. traditional artificial hummingbird algorithm (AHA) further improved by introducing step-size adjustment, greedy search, grouped parallel search global exploration exploitation. Our experimental results demonstrate that DA-AHA-CLT achieves coefficient determination (R2) 0.987, root-mean-square error (RMSE) 0.023, mean absolute (MAE) 0.018, median (MedAE) 0.011, outperforming such as CNN-LSTM LSTM-TPA. These findings confirm effectively captures characteristics temperatures, offering superior performance robustness in full-time-step tasks, highlight its potential solving challenging time-series forecasting problems

Language: Английский

---

Enhanced Electricity Forecasting for Smart Buildings Using a TCN‐Bi‐LSTM Deep Learning Model

Expert Systems, Journal Year: 2025, Volume and Issue: 42(3)

Published: Jan. 30, 2025

ABSTRACT Integration of sensor technology and advanced software empowers consumers to manage energy usage proactively. This proactive approach yields positive impacts at both micro macro levels, benefiting individuals contributing broader environmental conservation efforts. By leveraging predictive models, can make informed decisions that serve their interests promote a greener more sustainable future for all. Thus, consumption (EC) prediction is crucial effective resource management. In this study, we propose an innovative deep‐learning predict EC, focusing specifically on smart buildings. Our model utilises hybrid deep learning architecture effectively capture low high information patterns present in multivariate time series data various sensors deployed buildings numerous influencing factors. To address the nonlinear dynamic nature data, our combines neural network (DNN) with sequential (DLS). Specifically, temporal convolutional networks (TCN) within DNN family are employed extract trends from while DLS model, which consists Bi‐directional Long Short‐term Memory Networks (Bi‐LSTM), learn these effectively. Consequently, framework leverages related EC shared feature representation. validate approach, extensively evaluate using dataset office building Berkeley, California. Experimental results demonstrate achieves satisfactory accuracy prediction. For 7‐h horizon TS R 2 0.97 realised proposed model. confirmed by 1.65% improvement transiting univariate supports multiple modalities.

Language: Английский

---

Analyzing and Predicting Residential Electricity Consumption Using Smart Meter Data: A Copula-Based Approach

Energy and Buildings, Journal Year: 2025, Volume and Issue: unknown, P. 115432 - 115432

Published: Feb. 1, 2025

Language: Английский

---

Time Series Analysis of Solar Power Generation Based on Machine Learning for Efficient Monitoring

Engineering Reports, Journal Year: 2025, Volume and Issue: 7(2)

Published: Feb. 1, 2025

ABSTRACT Solar energy, a renewable resource, is essential for the efficiency of solar photovoltaic (PV) panels. However, meteorological factors, such as irradiation, weather patterns, precipitation, and overall climate conditions, pose challenges to seamless integration energy production into power grid. Accurate prediction PV system output necessary enhance The study focuses on utilizing machine learning (ML) methodologies accurate forecasting generation, addressing related integrating By analyzing generation data employing advanced ML models, research aims predictability systems. significance this lies in its potential optimize production, improve grid stability, contribute transition towards sustainable sources. This assesses appropriateness approaches accurately projecting half‐hourly cycles next day. consists many analytical phases, including exploratory analysis, inverter which are carried out two separate plants. following step conduct comparative analyses. analyzed using models like gradient boosting classifiers linear regressions. first plant produces best results, with an amazing 0.97% accuracy classifier regression classifier. Contrarily, second achieved 0.61% 0.62% models. study's techniques insights can help operators electricity market stakeholders make informed decisions use generated power, minimize waste, plan preservation, reduce costs, facilitate widespread

Language: Английский

---

Transforming Supply Chain Performance Based on Electronic Data Interchange (EDI) Integration: A Detailed Analysis

Deleted Journal, Journal Year: 2025, Volume and Issue: 3(2), P. 25 - 40

Published: March 1, 2025

EDI currently remains one of the most significant technological formats that respond to contemporary rapid and connected business environment by ensuring real-time, efficient accurate data exchange in supply chain management. This paper's central idea is evolution from early days standard trade papers technologies like blockchain, AI, ML, IoT. Focusing on processes where these innovations add value for EDI, providing real-time data, improving security, facilitating better decisions, this paper emphasises essential functions modernisation chains. In addition, it examines how integration can help minimise cost; manage stocks; enhance associations. Altogether, showcases EDI’s positive effects performance-enhancing aspects outlines prospective applications novel further global processes.

Language: Английский

---

Automated Image Identification and Classification of Tiger Beetles Based on Deep Learning Model

2022 IEEE 12th Annual Computing and Communication Workshop and Conference (CCWC), Journal Year: 2025, Volume and Issue: unknown, P. 01125 - 01132

Published: Jan. 6, 2025

Language: Английский

---