International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Excelgraph – AI Driven Data Visualization and Insights System |
|---|---|
| ABSTRACT | Data visualization serves as a critical enabler for decision-making across business, research, and educational domains, yet traditional approaches suffer from steep learning curves, high licensing costs, and limited automation capabilities. This paper presents XcelGraph, a lightweight AI-assisted web application framework that automates the transformation of Excel and CSV datasets into meaningful visualizations and natural language insights. The system integrates Python-based data processing libraries (Pandas, NumPy) with interactive visualization engines (Plotly, Matplotlib, Seaborn) and rule-based narrative generation to provide non-technical users with instant analytical capabilities. Implementation leverages Streamlit for a responsive user interface, supporting automatic chart suggestion based on column type detection (numeric, categorical, datetime), interactive filtering with range slicers, and AI-driven textual summarization of statistical patterns. The framework addresses critical limitations including manual effort in graph creation, data overload interpretation challenges, and accessibility barriers inherent in enterprise BI tools like PowerBI and Tableau. Experimental evaluation demonstrates 70-80% reduction in visualization time, support for multiple chart types (scatter, bar, line, histogram, pie), automated outlier detection via IQR methodology, and context-aware insight generation achieving 90% usability ratings from non-expert testers. The system employs a modular architecture encompassing data ingestion, preprocessing, relationship detection, visualization rendering, and export functionality, ensuring scalability and maintainability. Future enhancements target predictive analytics integration, real-time database synchronization, voice-based query interfaces, and cloud deployment for collaborative dashboards. |
| AUTHOR | DHOBALE AMARNATH RAJABHAU, GHORPADE OMKAR SANTOSH, HOLE GAURAV SATISH, PROF. SONAWANE R.B. |
| VOLUME | 176 |
| DOI | DOI: 10.15680/IJIRCCE.2025.1311072 |
| pdf/72_Excelgraph – AI Driven Data Visualization and Insights System.pdf | |
| KEYWORDS |
