Finetuning Analytics Information Systems for a Better Understanding of Users: Evidence of Personification Bias on Multiple Digital Channels DOI Creative Commons
Bernard J. Jansen,

Soon‐gyo Jung,

Joni Salminen

et al.

Information Systems Frontiers, Journal Year: 2023, Volume and Issue: 26(2), P. 775 - 798

Published: April 22, 2023

Abstract Although the effect of hyperparameters on algorithmic outputs is well known in machine learning, effects information systems that produce user or customer segments are relatively unexplored. This research investigates varying number personification engagement data a real analytics system, employing concept persona. We increment personas from 5 to 15 for total 330 and 33 persona generations. then examine changing hyperparameter gender, age, nationality, combined gender-age-nationality representation population. The results show despite using same algorithm, strongly biases system’s selection 990 an average deviation 54.5% 42.9% 28.9% 40.5% gender-age-nationality. A repeated analysis two other organizations shows similar all attributes. occurred platforms attributes, as high 90.9% some cases. imply decision makers should be aware set they exposed to. Organizations looking effectively use must wary altering could substantially change results, leading drastically different interpretations about actual base.

Language: Английский

Examination of the Criticality of Customer Segmentation Using Unsupervised Learning Methods DOI
Arpit Saxena, Ashi Agarwal, Binay Kumar Pandey

et al.

Circular Economy and Sustainability, Journal Year: 2024, Volume and Issue: 4(2), P. 1447 - 1460

Published: Jan. 9, 2024

Language: Английский

Citations

148
A Study on Machine Learning-Enhanced Roadside Unit-Based Detection of Abnormal Driving in Autonomous Vehicles DOI Open Access

Keon Yun,

Heesun Yun, Sangmin Lee

et al.

Electronics, Journal Year: 2024, Volume and Issue: 13(2), P. 288 - 288

Published: Jan. 8, 2024

Ensuring the safety of autonomous vehicles is becoming increasingly important with ongoing technological advancements. In this paper, we suggest a machine learning-based approach for detecting and responding to various abnormal behaviors within V2X system, system that mirrors real-world road conditions. Our including RSU, designed identify exhibiting driving. Abnormal driving can arise from causes, such as communication delays, sensor errors, navigation malfunctions, environmental challenges, cybersecurity threats. We simulated exploring three primary scenarios driving: overlapping vehicles, counterflow The applicability learning algorithms these anomalies was evaluated. Minisom algorithm, in particular, demonstrated high accuracy, recall, precision identifying vehicle overlaps, situations. Notably, changes vehicle’s direction its characteristics proved be significant indicators Basic Safety Messages (BSM). propose adding new element called linePosition BSM Part 2, enhancing our ability promptly detect address abnormalities. This addition underpins technical capabilities RSU systems equipped edge computing, enabling real-time analysis data appropriate responsive measures. emphasize effectiveness behavior offering ways enhance facilitate smoother traffic flow.

Language: Английский

Citations

8
The Future of Marketing: The Transformative Power of Artificial Intelligence DOI Open Access
Hafize Nurgül Durmuş Şenyapar

International Journal of Management and Administration, Journal Year: 2024, Volume and Issue: 8(15), P. 1 - 19

Published: Feb. 17, 2024

This research offers a rich narrative explaining this multifaceted relationship by exploring the transformative impact of Artificial Intelligence (AI) on marketing adopting qualitative descriptive approach for in-depth exploration. The findings reveal profound implications customer engagement, market strategy, and ethical considerations. integration AI into enables personalization increases brand loyalty. Predictive analytics enable businesses to develop proactive strategies aligned with future dynamics. Despite its advantages, considerations surrounding data privacy consumer consent require be used responsibly transparently. Integrated augmented reality, virtual predictive journeys, Internet Things that transform dynamics must harnessed balance concerns. A comprehensive resource academic researchers industry professionals, work provides clear roadmap organizations effectively leverage in their operations an environment increasing reliance digital platforms expanding availability.

Language: Английский

Citations

8
Assessing the intention to adopt computational intelligence in interactive marketing DOI
Rajat Kumar Behera, Pradip Kumar Bala, Nripendra P. Rana

et al.

Journal of Retailing and Consumer Services, Journal Year: 2024, Volume and Issue: 78, P. 103765 - 103765

Published: Feb. 24, 2024

Language: Английский

Citations

7
The Impact of AI-enabled CRM Systems on Organizational Competitive Advantage: A mixed-method approach using BERTopic and PLS-SEM DOI Creative Commons
Joon Woo Yoo, Junsung Park, Heejun Park

et al.

Heliyon, Journal Year: 2024, Volume and Issue: 10(16), P. e36392 - e36392

Published: Aug. 1, 2024

The recent advances in machine learning and deep algorithms, along with the advent of generative AI, have led AI to become "new normal" organizations. This trend has extended CRM, resulting development AI-enabled CRM systems, or AI-CRM. Despite growing adoption as part competitive strategies, many firms report minimal no positive effect on performance. study addresses research questions: "What are critical features AI-CRM systems?" "How do these impact organizational advantage?" To explore this, we aim identify key characteristics assess their In Study 1, utilize BERTopic topic modeling extract from user reviews. 2 employs PLS-SEM examine how influence advantage. 1 reveals four main (general, marketing, sales, service/support), each comprising distinct features. shows that differentially capability, significantly affecting performance findings offer valuable insights for both theory practice regarding effective use

Language: Английский

Citations

7
Deep Learning in Finance: A Survey of Applications and Techniques DOI Creative Commons

Ebikella Mienye,

Nobert Jere, George Obaido

et al.

AI, Journal Year: 2024, Volume and Issue: 5(4), P. 2066 - 2091

Published: Oct. 28, 2024

Machine learning (ML) has transformed the financial industry by enabling advanced applications such as credit scoring, fraud detection, and market forecasting. At core of this transformation is deep (DL), a subset ML that robust in processing analyzing complex large datasets. This paper provides comprehensive overview key models, including Convolutional Neural Networks (CNNs), Long Short-Term Memory networks (LSTMs), Deep Belief (DBNs), Transformers, Generative Adversarial (GANs), Reinforcement Learning (Deep RL). Beyond summarizing their mathematical foundations processes, study offers new insights into how these models are applied real-world contexts, highlighting specific advantages limitations tasks algorithmic trading, risk management, portfolio optimization. It also examines recent advances emerging trends alongside critical challenges data quality, model interpretability, computational complexity. These can guide future research directions toward developing more efficient, robust, explainable address evolving needs sector.

Language: Английский

Citations

5
Customer Segmentation DOI Open Access

Ishita Shah

International Journal for Research in Applied Science and Engineering Technology, Journal Year: 2024, Volume and Issue: 12(1), P. 1586 - 1591

Published: Jan. 31, 2024

Abstract: Effective marketing involves targeting specific customer groups with personalized products, services, and campaigns, making segmentation a crucial strategy in modern business. This paper introduces pioneering method that utilizes machine learning techniques to accurately efficiently segment customers based on their behaviors, demographics, transaction history. By combining transfer learning, Rfm (recency, frequency, monetary) modeling, clustering algorithms like K-means, our approach generates meaningful segments, offering valuable insights for improved experiences. We showcase the positive impact of real-world dataset, displaying noteworthy enhancements effectiveness satisfaction.

Language: Английский

Citations

4
Bibliometric insights into the evolution of digital marketing trends DOI Creative Commons
Nguyễn Minh Sáng

Innovative Marketing, Journal Year: 2024, Volume and Issue: 20(2), P. 1 - 14

Published: April 1, 2024

This bibliometric analysis aims to delineate the progression of research in domain digital marketing by examining 513 English-language articles published Scopus during period 2003–2024. An examination scholarly productivity indicates an upward trend, as evidenced increase publications from one 2003 115 2022 and citations 79 1131 2021, determined keyword, citation, authorship analyses. A review citation patterns reveals that with significant impact are primarily found prestigious academic journals, such Industrial Marketing Management International Journal Research Marketing. Prominent contributors hail Jordan, Finland, Spain, United Arab Emirates, Saudi Arabia; among other regions – States, Middle East, Europe, Asia. Keyword revealed emphasis on emerging technologies artificial intelligence traditional techniques (e.g., social media, content marketing, internet marketing). Co-occurrence theme highlighted strategy, audiences, transformation business acceleration adoption a result COVID-19. Further areas investigation encompass optimizing utilization emergent media platforms, implementing virtual augmented reality enhance customer experience, capitalizing potential machine learning augment efficacy marketing. By utilizing data-driven insights, this study offers guidance for curricular enhancements, agendas, practice. AcknowledgmentThe author thanks everyone who helped make possible, but especially those at Ho Chi Minh University Banking, Vietnam.

Language: Английский

Citations

4
Parallel web crawling for customer analytics DOI
Jinfeng Zhou,

Jinliang Wei,

Malini Ratnam

et al.

Textile Research Journal, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 10, 2025

This paper presents a parallel web crawling system designed to collect publicly available customer shopping data from retailer's website, aiming understand purchase behaviors and formulate customized engagement strategies. The architecture includes framework with scalable leaf units that facilitate the distributed process, expediting complete downloading of retailer’s product webpages. collected encompasses customers’ data, including name, price, date, alongside demographic information such as gender, age group, location. Our dataset comprises 836,369 records, representing 27,160 items purchased online by 455,088 customers over decade-long period. can be transformed into recency–frequency–monetary ( RFM) metrics, suitable for k-means clustering analysis segment distinct clusters: Lost, Potential, Hibernating & Valuable, Extant Active, Loyal Lucrative. These clusters provide valuable profiles assist retailer meet unique needs preferences each cluster. Demographic reveals female constitute nearly 90% Lucrative groups, underscoring their significant role active consumers on website. Furthermore, aged 50 above account 62% across all clusters, highlighting appeal among older shoppers. A geographical breakdown shows California, Texas, New York, Florida are states highest concentration in every

Language: Английский

Citations

0
CGAOA-STRA-BiConvLSTM: An automated deep learning framework for global TEC map prediction DOI
Haijun Liu, Haoran Wang, Huijun Le

et al.

GPS Solutions, Journal Year: 2025, Volume and Issue: 29(1)

Published: Jan. 1, 2025

Language: Английский

Citations

0