CROWDSOURCED LOCAL ISSUE REPORTING AND RISK MAPPING WITH POWER BI

Abstract

Public infrastructure management remains a significant challenge for people living in both urban and rural areas, where traditional complaint systems often suffer from inefficiencies, delays, and lack of transparency. This paper presents a comprehensive survey of existing Artificial Intelligence (AI)-based complaint management systems and evaluates their limitations in terms of automation, accuracy, and user engagement. Various approaches, including Natural Language Processing (NLP), machine learning models, and geolocation-based systems, are reviewed and analyzed. Based on the identified research gaps, this paper proposes an AI-powered complaint management system that integrates text and image classification with GPS-based location intelligence. The proposed system aims to improve complaint classification accuracy, ensure efficient routing to appropriate authorities, and enhance transparency through real-time tracking. This study contributes by addressing the limitations of existing systems and presenting a scalable solution that benefits citizens across both urban and rural environments.

Keywords: Natural Language Processing (NLP), Artificial Intelligence (AI), Global Positioning System (GPS), Machine Learning (ML), Long Short-Term Memory (LSTM), AutoRegressive Integrated Moving Average (ARIMA)