Browse Items (14421 total)
Sort by:
-
Carbonized Molybdenum Disulfide-Decorated Carbon from Waste Papaya Straws as Counter Electrode for Bifacial Dye-Sensitized Solar Cells
Abstract: Ongoing research efforts are aimed at developing bifacial dye-sensitized solar cells (DSSCs) that are both economically viable and high-performance. In this investigation, molybdenum disulfide-decorated biomass-derived carbon from waste papaya straws (MoS2@PS) was synthesized via a hydrothermal technique, and then subsequently subjected to annealing at various temperatures, referred to as PS26, PS27, and PS28. Annealing MoS2 -decorated PS resulted in an increase in surface area which was confirmed using BrunauerEmmettTeller measurements, revealing type IV isotherms with an H3 hysteresis loop showing the mesoscopic nature of PS28. The maximum recorded photovoltaic conversion efficiency was approximately 6.85% for the PS28 composite counter electrode (CE), highlighting its potential as a platinum-free alternative. Moreover, cyclic voltammetry and Tafel polarization studies confirmed the superior electrocatalytic activity of the MoS2@PS CE in the reduction process of triiodide ions (I3?). Studies on transmittance were conducted to validate the bifacial characteristics of DSSCs. The results from electrochemical impedance spectroscopy indicate that the MoS2@PS CE-based DSSCs exhibit rapid charge transfer at the electrode/electrolyte interface, with a resistance of RCT = 24.27 ? for the PS28 counter electrode. The favourable attributes of optimal conversion efficiency, high transmittance, ease of preparation, rapid charge transfer, and affordability suggest that MoS2@PS counter electrodes hold significant potential for applications in DSSCs. The Minerals, Metals & Materials Society 2025. -
Cotton-derived carbon fibers and MoS2 hybrids for efficient I3? reduction in bifacial dye-sensitized solar cells
In light of recent advancements, a novel platinum-free counter electrode for dye-sensitized solar cells (DSSCs) has been developed utilizing hierarchical MoS2 structures in conjunction with bio-derived carbon materials. Carbon fibers produced from cotton and molybdenum-doped carbon rods synthesized from melamine were fabricated through a straightforward hydrothermal process, which significantly enhanced both electrocatalytic activity and stability. The resulting counter electrodes exhibited notably low charge transfer resistances of 9.45 ? and 6.43 ?, thus facilitating efficient redox reactions. Consequently, DSSCs incorporating these materials achieved remarkable power conversion efficiencies of 7.04 % and 7.58 %, surpassing traditional platinum-based counter electrodes, which recorded an efficiency of 7.50 %. Furthermore, the high optical transmittance of these materials renders them suitable for bifacial DSSCs, broadening their potential applications. This research underscores the promise of bio-inspired carbon composites as sustainable and efficient alternatives in solar energy technologies, offering an environmentally friendly substitute for conventional noble metal electrodes. 2025 Elsevier Ltd -
Modeling of Real Time Traffic Flow Monitoring System Using Deep Learning and Unmanned Aerial Vehicles
Recently, intelligent video surveillance technologies using unmanned aerial vehicles (UAVs) have been considerably increased in the transportation sector. Real time collection of traffic videos by the use of UAVs finds useful to monitor the traffic flow and road conditions. Since traffic jams have become common in urban areas, it is needed to design artificial intelligence (AI) based recognition techniques to attain effective traffic flow monitoring. Besides, the traffic flow monitoring system can assist the traffic managers to start efficient dispersal actions. Therefore, this study designs a real time traffic flow monitoring system using deep learning (DL) and UAVs, called RTTFM-DL. The proposed RTTFM-DL technique aims to detect vehicles, count vehicles, estimate speed and determine traffic flow. In addition, an efficient vehicle detection model is proposed by the use of Faster Regional Convolutional Neural Network (Faster RCNN) with Residual Network (ResNet). Also, a detection line based vehicle counting approach is designed, which is based on overlap ratio. Finally, traffic flow monitoring takes place based on the estimated vehicle count and vehicle speed. In order to guarantee the effectual performance of the RTTFM-DL technique, a series of experimental analyses take place and the results are examined under varying aspects. The experimental outcomes highlighted the betterment of the RTTFM-DL technique over the recent techniques. The RTTFM-DL technique has gained improved outcomes with a higher accuracy of 0.975. 2022 River Publishers. -
Comparison of Convergence Rates in Federated Learning and Federated Multi-Task Learning Using the CIFAR-10 Dataset
Many smart or cell phones have built-in distance, signal, and air pollution sensors. While collecting information, an acceleration registering device is a three-dimensional one and it can be applied in the gait analysis to address issues such as falls and health status determination. Indeed, the data is abundance in terms of quantity and some of the data may be of great concern in terms of privacy. In the time of Industry 4.0 the data has emerged as a key resource. Personal information/identity must not be maintained and hence cannot be stored at one place or all collected in a single place. AI models are moving to decentralized where a machine learning setting called Federated learning (FL) is being applied. FL has adversities such as statistical and systems heterogeneity. Actually, to better use shared information and build local models, Federated Multi-task learning (FMTL) has been devised. We also compare the number of iterations required to converge using CIFAR dataset of FL and FMTL. Several graphs illustrated in this paper show that convergence rates depend on the algorithm, number of communication rounds and number of clients or devices. Thus, it is clear that in some cases FL outperforms with FMTL in terms of convergence or conversely. However, it cannot be deduced that the type of FMTL always converges better than FL. The reliance on this graph is evident in this paper in order to as explain as prove the fact that, as the number of clients in FL rises, the rate of convergence declines. If ten communication rounds are employed with the use of the MOCHA algorithm, the model does not converge appropriately. The RMSE score declined from 1.14 to 1.02 throughout 20 epochs. 2025 IEEE. -
An Interpretable Federated Multi-Task Learning Framework for Smart Traffic Management with Hessian-Driven Optimization Insights
Smart traffic management faces challenges in balancing privacy, interpretability, and optimization robustness, particularly when using deep learning for vehicle detection and traffic prediction. Existing methods struggle to provide transparent feature attribution while preserving data confidentiality in decentralized settings. This study proposes a federated multi-task learning (FMTL) framework based on YOLOv10, trained on an original traffic dataset, to address these limitations. The framework simultaneously performs vehicle detection, traffic density analysis, and no-entry sign identification, while employing Grad-CAM to enhance interpretability and Hessian-based eigenvalue analysis to evaluate optimization complexity. Results demonstrate an average mean accuracy of 89.7% across three real-world locations, with Grad-CAM revealing meaningful focus on vehicle density and intersection geometry. Hessian analysis confirms the presence of mixed-sign eigenvalues, proving the non-convexity of the optimization surface and highlighting convergence challenges. These outcomes establish a privacypreserving, interpretable, and optimization-aware framework for real-world smart traffic management. 2025 IEEE. -
Federated Multi-Task Learning Using Server-Side Normalized Loss-Based Weighting Method
Federated multi-task learning is an approach where multiple clients collaboratively train related but distinct models on their local data without sharing it, thereby preserving privacy while leveraging collective knowledge. However, participating clients can have very different data distributions, sizes and quality, leading to statistical heterogeneity. This heterogeneity is a major challenge in federated learning, as noisy or inconsistent updates from some clients can slow down convergence or degrade the global model's performance. MOCHA is a seminal federated multi-task learning framework that explicitly models task relationships and optimizes clientspecific models, while addressing system challenges like communication costs, fault tolerance and client dropouts. In this work, we enhance MOCHA with a server-side normalized lossbased weighting technique that focuses on the quality of client updates. Each client in the federated multi-task setup computes its local training loss, which is sent to the server during communication rounds. The server normalizes these losses across clients and assigns adaptive aggregation weights, giving more influence to clients with lower normalized losses and down-weighting noisy or unreliable clients. This design simplifies client-side implementation because all weighting is performed at the server. Experiments on heterogeneous MNIST and CIFAR-10 tasks show that the proposed method achieves a slightly higher final-round average test accuracy (0.5108 vs. 0.5065), reduces average training loss by approximately 2.6% (from 1.1148 to 1.0858), and improves fairness by lowering the standard deviation of client accuracies by about 5% (from 0.3631 to 0.3450) compared to baseline MOCHA. These results indicate that server-side normalized loss-based weighting improves training stability, convergence behavior and crossclient fairness in federated multi-task learning under nonconvex optimization. 2025 IEEE. -
Machine learningbased approaches for enhancing human resource management using automated employee performance prediction systems
Purpose: This study focuses on enhancing the accuracy and efficiency of employee performance prediction to enhance decision making and improve organisational productivity. By introducing advance machine learning (ML) techniques, this study aims to create a more reliable and data-driven approach to evaluate employee performance. Design/methodology/approach: In this study, nine machine learning (ML) models were used for forecasting employee performance: Random Forest, AdaBoost, CatBoost, LGB Classifier, SVM, KNN, XGBoost, Decision Tree and one Hybrid model (SVM + XGBoost). Each ML model is trained on an HR data set covering various features such as employee demographics, job-related factors and past performance records, ensuring reliable performance predictions. Feature scaling techniques, namely, min-max scaling, Standard Scaler and PCA, have been used to enhance the effectiveness of employee performance prediction. The models are trained to classify data, predicting whether an employees performance meets expectations or needs improvement. Findings: All proposed models used in the study can correctly categorize data with an average accuracy of 94%. Notably, the Random Forest model demonstrates the highest accuracy across all three scaling techniques, achieving optimise accuracy, respectively. The results presented have significant implications for HR procedures, providing businesses with the opportunity to make data-driven decisions, improve personnel management and foster a more effective and productive workforce. Research limitations/implications: The scope of the used data set limits the study, despite our models delivering high accuracy. Further research could extend to different data sets or more diverse organisational settings to validate the models effectiveness across various contexts. Practical implications: The proposed ML models in the study provide essential tools for HR departments, enabling them to make more informed data driven decisions with regard to employee performance. This approach can enhance personnel management, improve workforce productivity and fostering a more effective organisational environment. Social implications: Although AI models have shown promising outcomes, it is crucial to recognise the constraints and difficulties involved in their use. To ensure the fair and responsible use of AI in employee performance prediction, ethical considerations, privacy problems and any biases in the data should be properly addressed. Future work will be required to improve and broaden the capabilities of AI models in predicting employee performance. Originality/value: This study introduces an exclusive combination of ML models for accurately predicting employee performance. By employing these advanced techniques, the study offers novel insight into how organisations might transition from a conventional evaluation method to a more advanced and objective, data-backed approach. 2024, Emerald Publishing Limited. -
Machine learningbased approaches for enhancing human resource management using automated employee performance prediction systems
Purpose This study focuses on enhancing the accuracy and efficiency of employee performance prediction to enhance decision making and improve organisational productivity. By introducing advance machine learning (ML) techniques, this study aims to create a more reliable and data-driven approach to evaluate employee performance. Design/methodology/approach In this study, nine machine learning (ML) models were used for forecasting employee performance: Random Forest, AdaBoost, CatBoost, LGB Classifier, SVM, KNN, XGBoost, Decision Tree and one Hybrid model (SVM + XGBoost). Each ML model is trained on an HR data set covering various features such as employee demographics, job-related factors and past performance records, ensuring reliable performance predictions. Feature scaling techniques, namely, min-max scaling, Standard Scaler and PCA, have been used to enhance the effectiveness of employee performance prediction. The models are trained to classify data, predicting whether an employees performance meets expectations or needs improvement. Findings All proposed models used in the study can correctly categorize data with an average accuracy of 94%. Notably, the Random Forest model demonstrates the highest accuracy across all three scaling techniques, achieving optimise accuracy, respectively. The results presented have significant implications for HR procedures, providing businesses with the opportunity to make data-driven decisions, improve personnel management and foster a more effective and productive workforce. Research limitations/implications The scope of the used data set limits the study, despite our models delivering high accuracy. Further research could extend to different data sets or more diverse organisational settings to validate the models effectiveness across various contexts. Practical implications The proposed ML models in the study provide essential tools for HR departments, enabling them to make more informed data driven decisions with regard to employee performance. This approach can enhance personnel management, improve workforce productivity and fostering a more effective organisational environment. Social implications Although AI models have shown promising outcomes, it is crucial to recognise the constraints and difficulties involved in their use. To ensure the fair and responsible use of AI in employee performance prediction, ethical considerations, privacy problems and any biases in the data should be properly addressed. Future work will be required to improve and broaden the capabilities of AI models in predicting employee performance. Originality/value This study introduces an exclusive combination of ML models for accurately predicting employee performance. By employing these advanced techniques, the study offers novel insight into how organisations might transition from a conventional evaluation method to a more advanced and objective, data-backed approach. 2024 Emerald Publishing Limited -
Translating artificial intelligence into socio-economic insight: a hybrid deep learning approach to employee financial well-being
This study aims to translate recent advancements in hybrid artificial intelligence (AI) modeling into a functional tool for assessing individual financial well-being. The objective is to develop a system that aids organizations in understanding employees financial stress, with broader implications for enhancing workplace productivity and societal economic resilience. A deep learning pipeline was developed to classify individuals into three financial well-being categories: Financially Secure, Moderately Stable, and Financially At-Risk. The approach utilizes a structured dataset of 20,000 Indian individuals and implements 15 advanced deep learning models, including Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Gated Recurrent Units (GRU), Bidirectional Long Short-Term Memory (BiLSTM), and Wide & Deep networks. Model performance was assessed using standard evaluation metrics, including validation accuracy and ROC-AUC scores. Among the tested models, the hybrid Wide & Deep + CNN configuration yielded the highest performance, achieving a validation accuracy of 99.44% and a perfect ROC-AUC score of 1.0000. These results validate the models capacity for robust classification and real-world applicability to financial profiling. This study demonstrates a practical application of AI in financial decision support systems and contributes to organizational research by offering a scalable solution to assess and mitigate employee financial stress. The Author(s) 2026. -
AI Meets the Edge: Optimizing Computation Through Intelligent Offloading
The chapter looks into the developing bond between artificial intelligence (AI) and edge computing. In particular, the idea of using AI to intelligently offload computations. As the number of latency-sensitive applications have increased and the use cases for smart devices has widened, resource allocation at the edge has become critical. We discuss AI-based methods that intelligently determine what and when to transfer compute-intense tasks from resource-constrained edge devices to nearby edge servers or cloud environments. Pragmatic methods, RL optimization procedures and ML research exercises are the main focus of the standardized testing. To illustrate real-world examples, smart cities, autonomous vehicles, and industrial IoT are further explored. This chapter focuses on the development of a new hybrid offloading framework, synthesizing some of the greatest qualities of the predictive analytic and real-time learning to put into practice. These challenges including device heterogeneity, network variability, privacy, etc., are elaborated. Finally, in the concluding chapter, we argue the need for open problems that inform the path toward a sustainable, secure, AI-enabled edge computing. The Author(s), under exclusive license to Springer Nature Switzerland AG 2026. -
Geospatial Analysis of Groundwater Recharge Zones in Bengaluru
Urban flooding in cities like Bengaluru results from excessive rainfall overwhelming drainage systems, worsened by rapid urbanisation and the expansion of impervious surfaces. This study investigates the causes and consequences of urban flooding in Bengaluru, highlighting the decline in natural drainage and the encroachment of water bodies. Using QGIS, a geographic information system tool, spatial data from sources like NRSCs Bhuvan portal and USGS were analysed to identify flood-prone areas, drainage networks, and land use changes. The analysis revealed critical flooding zones such as Bellandur, Bommanahalli, and Mahadevapura. The study also emphasises the importance of implementing Best Management Practices (BMPs) and Rainwater Harvesting (RWH) strategies. Land Use and Land Cover (LULC) mapping, soil infiltration data, and rainfall patterns were assessed to understand urban hydrology. The findings stress the need for climate-resilient infrastructure, lake rejuvenation, and improved public awareness to mitigate future urban flood risks in Bengaluru. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Smart Farming with Ensemble Learning: A Soil-Driven Crop Suggestion Model for Sustainable Agriculture
The use of machine learning (ML) in agriculture has paved new avenues to improve decision making, especially in crop choice. The current research offers a data-driven crop recommendation system using a machine learning approach based on key soil and environmental factorsi.e., nitrogen (N), phosphorus (P), potassium (K), pH, temperature, humidity, and rainfall. A dataset of 2,200 soil records was processed using exploratory data analysis (EDA), normalization, and model training with algorithms such as Random Forest, Logistic Regression, and Gradient Boosting. Of these, Random Forest provided the best test accuracy of 99.32%, with high predictive ability and interpretability via feature importance measures. Violin and boxplots showed distinct feature separability among crop types, particularly in variables such as rainfall, temperature, and NPK concentrations, confirming the model's classification effectiveness. The practicability of the system is in its possible incorporation in IoT-based soil monitoring devices and cell advisory apps, delivering real-time, location-specific crop advice. This strategy enables farmers to make informed decisions, minimizes fertilizer waste, and promotes sustainable farming practices. The suggested system not only showcases technical strength but also fits well within the overall vision of smart farming and precision agriculture. Author(s) 2025. -
Leveraging unsupervised machine learning to optimize customer segmentation and product recommendations for increased retail profits
The retail sector's success hinges on understanding and responding adeptly to diverse consumer behaviours and preferences. In this context, the burgeoning volume of transactional data has underscored the need for advanced analytical methodologies to extract actionable insights. This research delves into the realm of unsupervised machine learning techniques within retail analytics, specifically focusing on customer segmentation and the subsequent recommendation strategy based on clustered preferences. The purpose of this study is to determine which unsupervised machine learning clustering algorithms perform best for segmenting retail customer data to improve marketing strategies. Through a comprehensive comparative analysis, this study explores the performance of multiple algorithms, aiming to identify the most suitable technique for retail customer segmentation. Through this segmentation, the study aims not only to discern and profile varied customer groups but also to derive actionable recommendations tailored to each cluster's preferences and purchasing patterns. 2024, IGI Global. All rights reserved. -
Wave Height Forecasting over Ocean of Things Based on Machine Learning Techniques: An Application for Ocean Renewable Energy Generation
With the evolution and integration of information and communication technologies, the marine environment is being converted into a smart ocean of things. The only way to monitor the marine environment is to access marine information through satellites, radar, etc. Recently, many researchers have focused their interest on generating power from renewable energy. Among all the available renewable resources, ocean waves are attracting the interest of researchers for power generation. Therefore, this article focuses on designing a data-driven forecasting model for marine renewable energy generation applications. This article applies a novel Gini-impurity-index-based bidirectional long short-term memory model for selecting the best ocean/marine environmental factors to forecast wave height and ultimately predict power generation using the numerical model. This article presents short- and long-term forecasting results. In the experiment, four stations each are taken for both short- and long-term forecasting. The average root-mean-square error was approximately 0.17 for long-term forecasting and approximately 0.05 for short-term forecasting. 1976-2012 IEEE. -
Investigation on the analysis of integration of IoT and AI technologies with information security for advanced education 4.0
This research examines the integration of emerging technologies in the form of the Internet of Things and Artificial Intelligence in driving forward to the educational application of Education 4.0. The systematic meta-analysis study provides evidence in the transformative capability of these technologies regarding attendance, performance, and learning pathway. The systems implementation was in the form of IoT sensors to capture and record student attendance, while the use of Artificial Intelligence based on machine learning models such as Support Vector Machine, Artificial Neural Network, k-Nearest Neighbors, and Decision Tree generated a personalized recommendation for the academic improvement or sports activity to be participated as an extracurricular activity. The performance evaluation of these models was illustrated for accuracy to correctly predict student responses related to the provided recommendations. The findings of implementation suggest the systems significant impacts given the augmented performance achievement with respect to academics and sports is the result of the implementation. It was measured comparing students performance before and after system implementation to capture the interpretation of student improvement regarding the use of the implemented system. The findings indicated that the systems implementation contributed to the increase in academic improvement from 65% to 75% and sports performance from 55% to 70% depending on student response to the provided academical or extracurricular recommendations. Such findings confirm an overall improvement in performance based on the use of the presented system. Taru Publications. -
Artificial Neural Networks for Enhancing E-commerce: A Study on Improving Personalization, Recommendation, and Customer Experience
With e-commerce companies, artificial intelligence (AI) has emerged as a crucial innovation that allows companies to streamline processes, improve customer interactions, and increase operational capabilities. To provide tailored suggestions, address client care requests, and improve inventory control, AI systems may evaluate consumer data. Moreover, AI can improve pricing methods and identify fraudulent activity. Companies can actually compete and provide better consumer interactions with the growing usage of machine learning in e-commerce. This essay examines how AI is reshaping the e-commerce sector and creating fresh chances for companies to enhance their processes and spur expansion. AI technology which enables companies to enhance their procedures and offer a more individualized customer experiences has grown into a crucial component of the e-commerce sector. Purpose of providing product suggestions and improve pricing tactics, intelligent machines may examine consumer behavior, interests, and purchase history. Customer service employees will have less work to do as a result of chatbots powered by artificial intelligence handling client queries and grievances. AI may also aid online retailers in streamlining their inventory control by anticipating demands and avoiding overstocking. The use of AI technologies can also identify suspicious transactions and stop economic losses. AI is positioned to assume a greater part in the expansion and accomplishment of the e-commerce sector as it grows in popularity. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Blockchain Empowered IVF: Revolutionizing Efficiency and Trust Through Smart Contracts
Couples who are having trouble becoming pregnant now have hope thanks to in vitro fertilization (IVF), a revolutionary medical advancement. However, the IVF procedure calls for a large number of stakeholders, intricate paperwork, and highly confidential management of information that frequently results in inaccuracies, mistakes, and worries about data confidentiality and confidence. In this study, the revolutionary potential of the blockchain and smart contracts enabling the treatment of IVF is investigated. The IVF procedure may be accelerated by utilizing smart contracts, resulting in improved effectiveness, openness, and confidence among everybody involved. The paper explores the primary advantages of using smart agreements in IVF, including automation, implementing obligations under contracts, doing away with middlemen, assuring confidentiality and anonymity, and enabling safe and auditable operations. The implementation of electronic agreements and blockchain-based technologies in the discipline of IVF is also investigated, along with the problems it may face and possible alternatives. This study offers insightful information about the use of intelligent agreements and blockchain technology in the field of IVF, accompanied by conducting an in-depth evaluation of the literature on the topic, research papers, and interviews with professionals. The results demonstrate the possibility of lower prices, more accessibility, higher success rates, and better patient experiences in the IVF field. In general, this study intends to illuminate how blockchain and smart contracts have revolutionized IVF technological advances, opening the door for a more effective, transparent, and reliable IVF procedure. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Artificial Intelligence, Smart Contracts, and the Groundbreaking Potential of Blockchain technology: Unlock the Next Generation of Innovation
The blockchain technology consists of blocks and is a decentralized network of nodes (miners). Each block is made up of three parts: the data, the hash, and the hash from the previous block. After data has been stored, it is extremely difficult to temper the data. Transactions are verified by miners, who are compensated with a commission for their labor. Readers will gain a comprehensive understanding of blockchain technology from this review article, including how it may be used in a variety of industries including supply chains, healthcare, and banking. Most individuals were already familiar with Bitcoin as one of the well-known blockchain applications. In this section, we'll discuss a few of the countless research publications on the cutting-edge applications of this technology. We'll talk about the challenges that come with actually using these applications as well. Blockchain is an industry that is growing thanks to its more recent applications in a number of fields, such as hospital administration, cryptocurrency use, and other places. Only the manner that blockchain works and runs makes it possible for these applications. 2023 IEEE. -
Deep Dive Into Diabetic Retinopathy Identification: A Deep Learning Approach with Blood Vessel Segmentation and Lesion Detection
In the landscape of diabetes-related ocular complications, diabetic retinopathy stands as a formidable challenge, reigning as the leading cause of vision impairment worldwide. Despite extensive research, the quest for effective treatments remains an ongoing pursuit. This study explores the burgeoning domain of AI-driven approaches in ocular research, particularly focusing on diabetic retinopathy detection. It delves into various diagnostic methodologies, encompassing the detection of microaneurysms, identification of hemorrhages, and segmentation of blood vessels, primarily utilizing retinal fundus photographs. Our findings juxtapose conventional machine learning techniques against deep neural networks, showcasing the remarkable efficacy of Convolutional neural network (CNN) and Random Forest (RF) in segmenting blood vessels and the robustness of deep learning in lesion identification. As we navigate the quest for clearer vision, artificial intelligence takes center stage, promising a transformative leap forward in the realm of vision care. 2024 River Publishers. -
Discrete financial in sentimental analysis using exploring patterns and trends
In todays rapidly evolving financial environment, its crucial for investors and decision-makers to effectively analyze stakeholder communications to gain valuable insights. This research conducts a comprehensive evaluation of a range of models that utilize machine learning, such as CNN (Convolutional Neural Network), LR (Logistic Regression), Doc2vec, and LSTM (Long Short-Term Memory), to determine their efficacy in interpreting investors sentiments and predicting business assessments and trading dynamics. The justification for preferring deep neural architectures compared to conventional data analysis lies in the challenge of handling extensive amounts of diverse and unorganized data. Deep learning techniques have shown impressive capacity in automatically detecting complex characteristics and unveiling concealed patterns within written records, rendering them well-suited for sentiment analysis in financial dialogue. This research questions the notion that depending exclusively on data from a solitary origin leads to persistently effective investment moves. In fact, stakeholder communication is impacted by numerous influential elements, leading to diverse sentiments and sentiments. Through our comparative assessment, we aim to illuminate how various deep learning models can adeptly capture the intricate nuances of sentiment within fiscal messaging. 2024, Taru Publications. All rights reserved.