Author: editoracademians@gmail.com

IJEDF-3-Integrating Deep Learning and Econometric Models for Predictive Analysis of Macroeconomic Indicators

International Journal of Economic Dynamics and Finance

An Open Access Peer Reviewed International Journal.
Publication Frequency: Bimonthly
ISSN Online: XXXX-XXXX
Country of Origin: Nigeria
Language: English
Publisher Name: Academians Publishers

Integrating Deep Learning and Econometric Models for Predictive Analysis of Macroeconomic Indicators

Keywords:

Deep learning, Econometric models, Hybrid forecasting, Macroeconomic indicators, RNN, SVAR, GDP, Inflation, High-frequency data, Economic policy analysis

Abstract

Abstract: The proliferation of large-scale economic datasets and advances in deep learning have created new avenues for forecasting critical macroeconomic indicators. Traditional econometric models, while interpretable, often struggle to capture nonlinear, high-dimensional relationships. This paper proposes a novel hybrid framework that integrates recurrent neural networks (RNNs) with structural vector autoregressions (SVARs) to leverage the strengths of both approaches. The RNN component extracts complex temporal patterns from high-frequency financial and sentiment data, while the SVAR imposes economic theory–guided structural identification. We apply this framework to forecast U.S. quarterly GDP growth and inflation rates using a richly textured dataset including daily market returns, text-based sentiment indices, and monthly labor statistics from 2000 to 2024. The hybrid model exhibits a 15% reduction in root mean squared forecast error (RMSFE) for GDP and a 12% reduction for inflation relative to benchmark VAR and pure deep learning models. Structural impulse‐response functions derived from the SVAR component retain economic interpretability, demonstrating realistic propagation of shocks through key economic channels.

In addition to strong predictive performance, the proposed framework is designed to facilitate economic policy analysis by ensuring the hybrid model’s outputs remain aligned with established macroeconomic theory. The integration of high-frequency sentiment and financial data enables the model to capture rapid shifts in market expectations and labor conditions, offering timely insights during periods of economic uncertainty such as the global financial crisis and the COVID-19 pandemic. Robustness checks confirm that the hybrid model’s gains persist across alternative sentiment proxies and varying model specifications, underscoring its versatility. Our results highlight not only the value of combining machine learning with econometric structures for robust and interpretable macroeconomic forecasting, but also the potential of such frameworks to inform economic decision-making in a fast-evolving data landscape.

Editorial Team
Join as Editor

IJEDF

IJEDF-2-Digital Content Quality and Market Dynamics in the Era of Artificial Intelligence: An Economic Framework for Understanding Information Ecosystems

International Journal of Economic Dynamics and Finance

Digital Content Quality and Market Dynamics in the Era of Artificial Intelligence: An Economic Framework for Understanding Information Ecosystems

Keywords:

Information Economics, Digital Content Quality, Market Failures, Algorithmic Governance, Information Pollution

Abstract

The rapid advancement of artificial intelligence—particularly large language models—has fundamentally transformed the economics of digital content creation. This transformation introduces profound challenges for preserving information quality, sustaining market efficiency, and safeguarding social welfare. Unlike traditional economic theories that focus on information asymmetries, today’s digital landscape is characterized by the mass production of apparently credible yet low-quality content at minimal cost, while generating high-quality, verified content remains resource-intensive. This paper presents a comprehensive economic framework to analyze how AI-induced cost differentials reshape digital information markets, create novel market failures, and demand innovative governance responses. Using both theoretical models and empirical evidence, we demonstrate that current market dynamics contribute to a systemic erosion of content quality. We introduce a multidimensional index to assess ecosystem health and propose adaptable policy frameworks suited to rapid technological change. Our findings deepen the understanding of technological disruption in information markets and inform the design of evidence-based policy solutions for the digital economy.

Editorial Team
Join as Editor

IJEDF

IJEDF-1-Behavioral Integration in Personal Finance Large Language Models: A Data-Centric Framework for Efficient and Trustworthy Financial Advisory Systems

International Journal of Economic Dynamics and Finance

Behavioral Integration in Personal Finance Large Language Models: A Data-Centric Framework for Efficient and Trustworthy Financial Advisory Systems

Keywords:

Large Language Models, Personal Finance, Behavioral Finance, Chain-of-Thought Reasoning, Financial Advisory, Data-Centric

Abstract

The rapid advancement of large language models (LLMs) is transforming the landscape of automated financial advisory, offering the potential for scalable, personalized, and data-driven guidance. However, current solutions are constrained by significant computational demands, insufficient adaptation to individual user behavior, and the persistence of systematic biases. In this paper, we propose a comprehensive data-centric framework that fundamentally rethinks the training and deployment of personal finance LLMs. Central to our approach is the integration of behavioral finance principles at every stage of the model development pipeline, including an innovative four-phase chain-of-thought generation process that explicitly incorporates users’ psychological states and emotional cues into financial reasoning. We constructed an extensive dataset of 19,000 real-world personal finance queries across eight diverse domains—ranging from debt management to retirement planning—and used it to fine-tune a Qwen-3-8B model. Our multi-faceted evaluation, combining held-out testing, blind LLM-jury studies, and cost-benefit analysis, demonstrates that the resulting 8B-parameter model matches or surpasses the performance of models 2–4 times larger (14–32B parameters) in factual accuracy, response fluency, and degree of personalization, while reducing operational costs by 80%. This framework directly tackles the pitfalls of current agentic and general-purpose approaches, notably their architectural complexity, high maintenance burden, and poor real-world efficiency. By showing that principled behavioral integration and robust data design can substitute for brute-force computational scaling, our work paves the way for practical, accessible, and genuinely trustworthy financial AI systems applicable to a broad range of users and scenarios.

Editorial Team
Join as Editor

IJAECS

ijaecs/2025/Exploring Bounded Rationality Through Computational Intelligence: A Comprehensive Review

International Journal of Advances in Engineering and Computer Science

Exploring Bounded Rationality Through Computational Intelligence: A Comprehensive Review

Keywords:

Abstract

Bounded rationality departs from the traditional economic assumption of fully rational agents by highlighting the impact of cognitive and computational constraints on human decisions. This review synthesizes recent progress in computational intelligence that addresses how to model and enhance rationality within the bounds of these limitations. We discuss foundational theories, including Herbert Simon’s bounded rationality and Ariel Rubinstein’s algorithmic framework, alongside contemporary computational approaches involving heuristic search, machine learning, and multi-agent systems. Special attention is given to methods that bridge psychology, economics, and artificial intelligence, offering realistic models of decision-making and examining their consequences for economics, behavioral finance, and autonomous system design. The review concludes by identifying future research opportunities for creating more adaptable and robust agents capable of navigating complex environments under limited information and computational resources.

Editorial Team
Join as Editor

IJAECS

ijaecs/2025/The Symbiotic Evolution of Intelligent Hardware and Data Processing for Next-Generation Immersive Realities

International Journal of Advances in Engineering and Computer Science

The Symbiotic Evolution of Intelligent Hardware and Data Processing for Next-Generation Immersive Realities

Keywords:

Extended Reality, Intelligent Hardware, Data Pipeline, Immersive Computing, Edge AI, Neuromorphic Processing, Multimodal Data, Latency, Privacy, Brain-Computer Interface

Abstract

The drive for genuine immersion is propelling Extended Reality (XR)—covering Virtual, Augmented, and Mixed Reality—past the constraints of conventional computing. This progress is powered by a surge in multimodal data (spatial, biometric, and behavioral) and made possible by a new generation of intelligent, purpose-built hardware. This paper thoroughly explores how data and smart hardware co-evolve to shape future immersive environments. It breaks down the entire data workflow, from capturing multiple data types and processing them at the edge, to AI-powered rendering and secure data storage. The discussion highlights how custom chips, neuromorphic processors, and advanced sensors are tackling challenges of latency, bandwidth, and computation. The paper also investigates the importance of edge and fog computing for enabling real-time responsiveness and personalization. In addition to technical aspects, it examines critical ethical, security, and privacy issues that arise from handling sensitive biometric and behavioral information. The concluding section looks ahead to developments like brain-computer interfaces, real-time photorealistic rendering, and AI-generated content, and sets out a research agenda for developing immersive experiences that are scalable, ethical, and transformative.

Editorial Team
Join as Editor

IJAECS

ijaecs/2025/ADVANCING ENTERPRISE AGILITY: A CONTEMPORARY EXAMINATION OF SERVERLESS ARCHITECTURES FOR SCALABLE CLOUD-NATIVE APPLICATIONS

International Journal of Advances in Engineering and Computer Science

ADVANCING ENTERPRISE AGILITY: A CONTEMPORARY EXAMINATION OF SERVERLESS ARCHITECTURES FOR SCALABLE CLOUD-NATIVE APPLICATIONS

Keywords:

serverless computing, FaaS, cloud-native, scalability, event-driven architecture, microservices, DevOps, cost optimization, vendor lock-in, cloud security

Abstract

Cloud computing has evolved continuously, with serverless architectures representing a pivotal innovation that decouples application logic from infrastructure management. This paper provides a comprehensive analysis of modern serverless computing, identifying it as a critical enabler for highly scalable, cost-efficient, and agile enterprise applications. Beyond foundational concepts, the analysis examines the composition of Function-as-a-Service (FaaS) and Backend-as-a-Service (BaaS) models within contemporary cloud ecosystems. The research investigates architectural features that enable automatic elasticity, event-driven processing, and a shift in DevOps practices, reducing operational overhead. By evaluating diverse use cases, including real-time data analytics, microservices, and Internet of Things (IoT) deployments, the paper demonstrates the business value of serverless adoption. Additionally, it addresses challenges such as cold start latency, vendor lock-in, and security complexities in distributed environments, and proposes mitigation strategies and best practices. The study concludes by forecasting future developments, including the convergence of serverless computing with edge computing, artificial intelligence (AI), and multi-cloud orchestration frameworks, and provides a roadmap for enterprises undergoing digital transformation.

Editorial Team
Join as Editor

IJAECS

ijaecs/2025/FlowMesh: A Dynamic Service Mesh for Orchestrating Serverless Workflows Across Heterogeneous Edge-Cloud Continuums

International Journal of Advances in Engineering and Computer Science

FlowMesh: A Dynamic Service Mesh for Orchestrating Serverless Workflows Across Heterogeneous Edge-Cloud Continuums

Keywords:

Serverless Computing, Edge-Cloud Continuum, Service Mesh, Workflow Orchestration, Fault Tolerance, Distributed Systems, Function-as-a-Service (FaaS)

Abstract

The integration of serverless computing with edge environments introduces a paradigm of highly distributed, low-latency processing. However, orchestrating complex serverless workflows across a heterogeneous continuum of resource-constrained edge devices and powerful cloud nodes presents significant challenges in latency, state synchronization, and fault tolerance. Existing orchestration systems, often designed for homogeneous cloud environments, struggle with the inherent network instability and resource asymmetry of edge-cloud topologies. This paper presents FlowMesh, a dynamic service mesh architecture specifically designed for decentralized serverless workflow orchestration. FlowMesh introduces a novel, lightweight control plane that embeds orchestration logic directly within a mesh of sidecar proxies co-located with function runtime environments. This design enables intelligent, context-aware routing and state management without a centralized bottleneck. Key innovations include a distributed consensus protocol for fault-tolerant state management, a latency-aware function placement scheduler, and a transparent checkpointing mechanism for seamless fault recovery across stateful workflows. We evaluate FlowMesh against state-of-the-art systems, such as FaaSFlow and AWS Step Functions, in a simulated edge-cloud testbed. Results demonstrate that FlowMesh reduces end-to-end workflow latency by up to 40% in edge scenarios and improves fault recovery success rate by 65% compared to cloud-centric alternatives, while maintaining minimal overhead. This work provides a blueprint for building robust, high-performance serverless platforms that truly span the edge-to-cloud continuum.

Editorial Team
Join as Editor

IJAECS

ijaecs/2025/PQC-IMC: A Memristor-based In-Memory Computing Architecture for Accelerating Post-Quantum Cryptography Lattice-Based Operations

International Journal of Advances in Engineering and Computer Science

PQC-IMC: A Memristor-based In-Memory Computing Architecture for Accelerating Post-Quantum Cryptography Lattice-Based Operations

Keywords:

Post-Quantum Cryptography, Lattice-Based Cryptography, In-Memory Computing, Memristor, Hardware Acceleration, Number Theoretic Transform, Internet of Things, Edge Security

Abstract

The rapid rise of quantum computing threatens to undermine existing public-key cryptographic methods, driving an urgent push for Post-Quantum Cryptography (PQC) solutions. Lattice-based cryptographic protocols, including Kyber for key encapsulation and Dilithium for digital signatures, have emerged as top contenders due to their robust security. Yet, deploying these schemes in low-power IoT and edge platforms remains challenging, largely because polynomial multiplication—central to their operations—demands substantial computational resources. Standard von Neumann computer systems struggle with these tasks due to inefficiencies in shuttling data between memory and processor. This study presents PQC-IMC: a new in-memory computing (IMC) framework built on memristor (MR) crossbar arrays to accelerate the most intensive arithmetic steps in lattice-based PQC. We introduce a memristor-centric processing unit that executes Number Theoretic Transform (NTT) and point-wise multiplication directly where data is stored. Harnessing the parallelism and analog strengths of MR crossbars, PQC-IMC minimizes data transfer bottlenecks. Our comprehensive hardware blueprint features a coefficient mapping scheme for the crossbar and a digital circuit for managing operations and modular arithmetic. The system’s polynomial multiplication core was prototyped on a Xilinx Artix-7 FPGA using an MR emulator. Evaluation results show that PQC-IMC delivers a 4.1-fold speed increase and cuts energy use by 68% per polynomial multiplication compared to an optimized ARM Cortex-M4 software approach. Additionally, it achieves an 83% lower energy-delay product (EDP) than a leading ASIC accelerator. These outcomes highlight IMC’s potential for enabling secure, quantum-resistant cryptography in next-generation, energy-conscious edge devices.

Editorial Team
Join as Editor

AJAAR

ajaar/2025/A Neuromorphic Edge-Based Irrigation Control System for Precision Agriculture

Post author By editoracademians@gmail.com
Post date October 1, 2025
No Comments on ajaar/2025/A Neuromorphic Edge-Based Irrigation Control System for Precision Agriculture

International Journal of Advanced Agriculture and Research

A Neuromorphic Edge-Based Irrigation Control System for Precision Agriculture

Keywords:

Precision irrigation; neuromorphic computing; spiking neural networks; edge computing; soil matric potential; energy-efficient control.

Abstract

Efficient water utilization is paramount for sustainable agriculture under increasing environmental pressures, especially as global populations rise and climate change intensifies water scarcity. Traditional precision irrigation systems rely on centralized architectures and periodic remote data processing, resulting in high energy costs and dependency on reliable connectivity, which can be particularly problematic in remote or undeveloped regions where robust infrastructure is lacking. This study presents a novel, fully autonomous irrigation controller leveraging a mixed-signal neuromorphic processor (DYNAP-SE1) to perform local, event-driven decision-making based on soil matric potential (SMP) measurements, thus reducing reliance on external networks and enhancing system resilience. In our approach, soil moisture data from apple and kiwi orchards were encoded into spike trains and processed by a spiking neural state machine with excitatory–inhibitory (EI) balanced dynamics to maintain long-term memory of sparse sensor inputs, allowing for more efficient and timely irrigation decisions. A direction-sensitive readout module generated “open” and “close” actuator commands, replicating conventional threshold-based irrigation rules and ensuring that water is delivered precisely when and where it is needed, minimizing waste. Validation on real-world datasets demonstrated close alignment with standard methods across -20 cm and -40 cm depths, with temporal discrepancies under 2 minutes, indicating the high reliability and accuracy of the neuromorphic controller in practical scenarios. Energy consumption per irrigation decision was estimated at 5.97 µWh, exceeding the efficiency of comparable IoT solutions and offering significant energy savings that are critical for sustainable agriculture. This neuromorphic pipeline offers a scalable, ultra-low-power platform for edge-based irrigation control, eliminating the need for cloud infrastructure and enabling resilient water management in resource-constrained environments, ultimately contributing to long-term agricultural sustainability.

Editorial Team
Join as Editor

AJAAR

ajaar/2025/Leveraging Generative Adversarial Networks for Synthetic Data Augmentation in Maize Seedling Detection: A Novel Approach to Mitigate Class Imbalance in the MSDD Benchmark

International Journal of Advanced Agriculture and Research

Leveraging Generative Adversarial Networks for Synthetic Data Augmentation in Maize Seedling Detection: A Novel Approach to Mitigate Class Imbalance in the MSDD Benchmark

Keywords:

Synthetic Data Augmentation, Generative Adversarial Networks (GANs), Class Imbalance, Precision Agriculture, Maize Seedling Detection, YOLO, Deep Learning, UAV.

Abstract

The automation of plant stand counting via Unmanned Aerial Vehicles (UAVs) and deep learning represents a paradigm shift in precision agriculture. However, the performance of object detection models is severely hampered by a fundamental challenge: extreme class imbalance in real-world agricultural datasets. Models excel at detecting prevalent “single plant” instances but fail on rare yet agronomically critical “double” and “triple” plant clusters. This study proposes a novel methodology to mitigate this imbalance by leveraging Generative Adversarial Networks (GANs) for synthetic data augmentation. Building upon the publicly available Maize Seedling Detection Dataset (MSDD), we developed a conditional StyleGAN2-ADA architecture to generate high-fidelity, synthetic images of double and triple maize seedlings across varied growth stages (V4-V8) and environmental conditions. We augmented the original MSDD training set with this synthetic data and benchmarked the performance of YOLOv9 and YOLO11 models. Results demonstrate that models trained on the augmented dataset showed a marked improvement in detecting rare classes. The mAP@0.5 for double plants increased by 18.7% for YOLOv9 and 22.3% for YOLO11, while recall for triple plants improved by 15.1% and 19.8%, respectively, without compromising performance on the single plant class. This research establishes a robust, scalable framework for synthetic data generation in agricultural computer vision, effectively addressing data scarcity for rare classes and paving the way for more reliable automated stand counting systems in precision agriculture.

Editorial Team
Join as Editor