AI-Enhanced Business Intelligence Dashboard for Decision-Centric Predictive Analytics

Abstract

Traditional business intelligence tools are used for the visualization of the data by the organizations, but the major problem is analysts have to make efforts to find the insights from this and also find the predictions on the basis of any one factor or metric; this makes the whole process time-consuming and difficult. This project proposes a framework focusing on decision-based analytics using a transactional dataset and creating a platform using Python and Streamlit that will provide a platform with options for data visualization and provide automated insights and predictions based on multiple variables with the help of a real-world dataset. The prediction model created using the Random Forest algorithm achieved an R² score of 0.99 and the Mean Absolute Error (MAE) of 37.93, thus the prediction deviation is low. This study also highlights the importance of Artificial Intelligence by implementing it the system using Machine Learning, showing how AI can help in advancing the dashboards from the traditional dashboards. The dashboard created will help to demonstrate how this proposed idea will enhance the efficiency and reduce the effort required for manually analyzing and interpreting and be easily usable by anyone, whether from a technical or non-technical field. The proposed system dashboard is reliable, time saving and requires less efforts, less complex and efficient.

Introduction

The text discusses the limitations of traditional Business Intelligence (BI) tools, which mainly provide static visualizations and require manual analysis to extract insights. These methods are time-consuming and often focus on single-variable analysis, making it difficult to understand complex business relationships where multiple factors influence outcomes like revenue. To address this, the study proposes an AI-enhanced, decision-centric BI system using a Python–Streamlit framework.

The proposed system integrates a Random Forest regression model to enable real-time “what-if” analysis, allowing users to adjust multiple variables (such as price and discount) and instantly see predicted outcomes. It also incorporates Explainable AI (XAI) to show feature importance, helping users understand which factors most influence results. Additionally, the system provides automated insight generation using simple statistical rules to summarize key trends from transactional data.

Compared to existing research, which is mostly conceptual and lacks practical implementation, this work delivers a fully functional, lightweight BI tool that combines visualization, prediction, and interpretation in one platform. It improves accessibility for non-technical users by removing the need for coding knowledge and enabling interactive decision-making.

Conclusion

This paper shows a project that implements a decision-based data visualization dashboard, which provides options to generate automated insights and download them for making decisions instead of manually finding them from the visualizations, and also predictions using a machine learning regression algorithm on the basis of multi-variable data, allowing the users to change the values of the variables and see the changes in the revenue accordingly. The prediction model performs well with a R² score of 0.99 and MAE score of 37.93. In the future, the idea can be extended by providing real-time visualization by incorporating the changes in the dataset, also adding various other prediction features, and providing the advanced natural language processed insights. We can also add an explanation for the events that occurred with the help of XAI. Overall, this paper suggests an efficient application for decision-centric data visualization and can also be used for various datasets with some changes.

References

[1] Ismael, S. N., & Mohd, O. (2025). Beyond Dashboard: How Ai Shaping Business Intelligence. International Journal of Academic Research in Business and Social Sciences, 15(10), 1295–1303. https://doi.org/10.6007/IJARBSS/v15-i10/26731 [2] Jain, A. M. (2023). AI-Powered Business Intelligence Dashboards : A Cross-Sector analysis of transformative impact and future directions. International Journal of Scientific Research in Computer Science Engineering and Information Technology, 524–536. https://doi.org/10.32628/cseit23564514 [3] Shamnad Mohamed Shaffi. “AI-Driven Analytics: The Future of Business Intelligence.” International Journal of Research in Engineering and Science, vol. 12, no. 12, 1 Dec. 2024, pp. 356–367, www.researchgate.net/publication/389554401_AI-Driven_Analytics_The_Future_of_Business_Intelligence. [4] Cate, M. (2025, January 1). AI-Driven Automation of Big Data Insights for Business Intelligence. https://www.researchgate.net/publication/388415967_AI-Driven_Automation_of_Big_Data_Insights_for_Business_Intelligenc e [5] Ezeilo, O. J., Orobosa Ikponmwoba, S., Chima, O. K., Ojonugwa, B. M., Ochefu, A., & Adesuyi, M. O. (n.d.). Systematic Review of Business Intelligence Tools and Strategic Dash boarding Techniques. International Journal of Scientific Research in Science and Technology Available Online. https://doi.org/10.32628/IJSRST [6] J. Ramya, Sai Sahishnu Yerraguravagari, Santosh Gaikwad, Rajeev Kumar Gupta, Kavipragash R (2024) AI and Machine Learning in Predictive Analytics: Revolutionizing Business Strategies through Big Data Insights. Library Progress International, 44(3), 14192-14201 [7] Chen, R. H. Chiang, and V. C. Storey, “Business intelligence and analytics: From big data to big impact,” MIS Quarterly, vol. 36, no. 4, pp. 1165–1188, 2012. [8] T. Davenport and J. Harris, Competing on Analytics: The New Science of Winning, Boston, MA, USA: Harvard Business School Press, 2017. [9] A. Gandomi and M. Haider, “Beyond the hype: Big data concepts, methods, and analytics,” International Journal of Information Management, vol. 35, no. 2, pp. 137–144, 2015. [10] L. Breiman, “Random forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001. [11] M. T. Ribeiro, S. Singh, and C. Guestrin, “Why should I trust you? Explaining the predictions of any classifier,” in Proc. ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, 2016, pp. 1135–1144. [12] F. Provost and T. Fawcett, Data Science for Business: What You Need to Know about Data Mining and Data-Analytic Thinking, Sebastopol, CA, USA: O’Reilly Media, 2013.

Copyright

Copyright © 2026 C. Kalpana, Manoj Devare, Bhagya P Bijay Kumar . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.