Copyright © 2026 Authors retain the copyright of this article. This article 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.
@article{211109,
author = {Prathamesh Mankar and Om Sangar and Alfaz Tamboli and Sahil Shaikh and Dr. Shuddhodhan Bokefode},
title = {INSIGHT FORGE: AN AI-POWERED PLATFORM FOR AUTOMATED DATA CLEANING, ANALYSIS, AND INTERACTIVE VISUALIZATION},
journal = {International Journal of Innovative Research in Technology},
year = {2026},
volume = {13},
number = {6},
pages = {3536-3542},
issn = {2349-6002},
url = {https://ijirt.org/article?manuscript=211109},
abstract = {Data preparation is a critical prerequisite for reliable analytics, yet raw tabular datasets frequently contain missing entries, statistical outliers, inconsistent data types, and structural ambiguities that hinder non-technical users. This paper presents Insight Forge an AI-powered analytics platform that unifies automated data cleaning, tabular aggregation, and interactive visualization within a single lightweight workflow. Built using Python, Pandas, NumPy, FastAPI, Streamlit, and Plotly, the system targets students, small businesses, and entry-level analysts who require structured data exploration without chaining multiple separate tools. Its cleaning module supports mean, median, and mode imputation alongside interquartile range (IQR) and Z-score outlier flagging, paired with an inspectable cleaning log that tracks applied transformations. The analytical layer supports grouped aggregations, while the dashboard renders key performance indicator (KPI) cards, interactive Plotly charts, dynamic filters, rearrangeable layouts, and data summaries. A conversational assistant, Forge Assistant, integrates the Google Gemini API to provide guided natural-language support. The end-to-end workflow has been exercised using a sales dataset of approximately 10,000 rows and 10 columns; however, formal quantitative benchmarking remains in progress. Accordingly, this paper documents the implemented system architecture, safety and transparency safeguards, and a structured Phase 2 evaluation protocol rather than reporting unmeasured speed, accuracy, or usability scores. Future work includes executing controlled cleaning and aggregation benchmarks, completing PostgreSQL production integration, adding reversible transformation pipelines, and conducting structured user evaluation.},
keywords = {Data cleaning, data analytics, artificial intelligence, outlier detection, interactive visualization, large language models, exploratory data analysis.},
month = {November},
}
Submit your research paper and those of your network (friends, colleagues, or peers) through your IPN account, and receive 800 INR for each paper that gets published.
Join NowNational Conference on Sustainable Engineering and Management - 2024 Last Date: 15th March 2024
Submit inquiry