Intelligent Automated Extraction and ML-Based Predictive Analytics System for India's Union Budget, Government Schemes, and GDP Performance Forecasting

Sarang Sahare; Vijayata Dalwankar

Intelligent Automated Extraction and ML-Based Predictive Analytics System for India's Union Budget, Government Schemes, and GDP Performance Forecasting

Author(s)	Mr. Sarang Sahare, Prof. Vijayata Dalwankar
Country	India
Abstract	Public budget analysis in India is constrained by heterogeneous documents, scanned fiscal tables, scheme narratives, variable evidence quality and weak traceability between allocations, implementation signals and macroeconomic outcomes. This study presents an evidence-gated automated extraction and predictive analytics framework for India's Union Budget, government scheme records and GDP performance indicators. The framework converts official and public fiscal artifacts into auditable document chunks, structured scheme profiles, macroeconomic panels and model-ready features. The inspected experimental artifact contains 3,000 structured scheme rows, 64,728 document chunks, 54,399 OCR-derived evidence chunks, 10 annual GDP rows, 10 annual RBI macro rows and 54 quarterly GDP observations from Q1 2012-13 to Q2 2025-26. The revised contribution is a strengthened validation design: source-separated and time-separated testing are specified for the scheme classifier, feature-group ablation is introduced for geography, duration, budget and evidence variables, and GDP forecasting is evaluated against naive and historical-mean baselines using readiness criteria. Internal scheme classification is highly separable, but the dominance of state coverage and duration prevents overclaiming. Annual GDP regression remains diagnostic due to the small sample, whereas normal-period quarterly planning ranges are defensible under explicit shock warnings. The study contributes a responsible public-finance analytics framework that integrates extraction, evidence lineage, machine-learning diagnostics, ablation logic, baseline discipline and deployment-readiness safeguards.
Keywords	Union Budget Analytics; Government Schemes; Public Finance; Document AI; OCR Audit; Evidence Retrieval; Machine Learning; Source-Separated Validation; Feature Ablation; GDP Forecasting; Responsible AI
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 8, Issue 3, May-June 2026
Published On	2026-06-11

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 8 Isu 3 Cover Page Vol 8 Isu 2 Cover Page Vol 8 Isu 2

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Intelligent Automated Extraction and ML-Based Predictive Analytics System for India's Union Budget, Government Schemes, and GDP Performance Forecasting

Share this