Self-Service Analytics 2.0: AI-Powered Dashboard Generation with Human-in-the Loop Feedback Architecture
Keywords:
: Explainable AI, Cyberbullying, Real-Time NLP, Multi-Teacher Knowledge Distillation, XGBoost, SHAP, Emotion Detection, Sarcasm Detection, Multilingual NLP, conscious language use, symmetry principle, , positional labelling, computational linguistic encoding, syllable typology, formal notation system, rhythm-based phonology, meter and linguistic melody, ӭagyar MᲩa-siralom, Planctus ante nescia, speech processing, NLP., Compliance, Internet privacy, third-party vendors, data breaches, GDPR, CCPA, HIPAA, PCI DSS, vendor risk management, supply chain security, Business Intelligence Architecture, Human-in-the-Loop Systems, Automated Analytics, Dashboard Generation, Feedback MechanismsAbstract
This paper presents the architectural foundation and implementation results of Self-Service Analytics 2.0, an AI-powered system that automatically generates business dashboards from raw data while incorporating continuous human feedback loops. Our architecture integrates automated schema detection, intelligent KPI discovery, and adaptive visualization generation through a multi-layered feedback mechanism that learns from user interactions. The system demonstrates a 47% reduction in dashboard creation time and achieves 78% user satisfaction scores through iterative refinement. We detail the comprehensive architecture including feedback collection pipelines, model adaptation mechanisms, and human-in-the-loop quality assurance workflows that ensure generated insights remain aligned with business objectives.
References
I. A. Abu-AlSondosa (2023) The impact of business intelligence system (BIS) on quality of strategic decision-making in top-level management. 7(1). https://www.growingscience.com/ijds/Vol7/ijdns_2023_100.pdf
H. Chen, R. H. L. Chiang, V. C. Storey (2012) Business intelligence and analytics: From big data to big impact. 36(4), 1165–1188. https://doi.org/10.2307/41703503
D. Deng, A. Wu, H. Qu, Y. Wu (2022) DashBot: Insight-driven dashboard generation based on deep reinforcement learning. https://arxiv.org/abs/2208.01232
T. S. Leelavati, S. Madhavi, P. Dharani, M. L. N. Sireesha, J. Sravani, B. V. Sai Krishna, M. Kumara Swamy (2023) Business analytics – A systematic literature review. 27(Special 2), 1–6. https://www.abacademies.org/articles/businessanalytics-a-systematic-literature-review.pdf
G. Phillips-Wren, M. Daly, F. Burstein (2021) Reconciling business intelligence, analytics and decision support systems: More data, deeper insight. 38(4). https://doi.org/10.1016/j.im.2021.101563
Quantzig (2025) AI powered dashboards: Transform insights for decisions. https://www.quantzig.com/ai-powered-dashboards-transform-insights-for-decisions
J. Valkenburgh (2024) Enhancing business industry collaboration funding. dashboards with explanatory analytics. https://arxiv.org/abs/2301.04193
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Authors and Global Journals Private Limited
This work is licensed under a Creative Commons Attribution 4.0 International License.
