• Reshma K.J
• Shama Shivanand
• Sweekrithi K.S
• Shreya K
• Vaishnavi

Rapid growth of urbanization has led to vast amount of waste generation, making it quite challenging to collect and dispose them efficiently. Traditional waste management methods rely on fixed schedules, which often lead to problems such as increase in operational costs, fuel consumption and environmental effects. This article presents Eco Sethu, a dynamic waste management system that uses various machine learning techniques and route optimization algorithm for efficient waste collection. In particular, the model initially predicts the household waste generated using the collected historical data and various performance metrics. Among all the other models, Random Forest model showed better performance with higher accuracy. These predictions were used as the input to the route optimization algorithm model, which is solved using the Traveling Salesman Problem and Nearest Neighbour Approach. This helps in reducing the travel distances and use the truck’s capacity effectively. Additionally, a web application is also developed using Fast API and SQLite, providing real-time collection schedules, issue reporting, and waste segregation practices to increase community participation.

waste management, route optimization, machine learning, Fast-Api, nearest neighbor algorithm, traveling Salesman problem, web application.

"Eco Sethu: Smart Routing for Efficient Waste Management Systems ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 6, page no.134-142, June-2025, Available :http://www.jetir.org/papers/JETIRGW06023.pdf

"Eco Sethu: Smart Routing for Efficient Waste Management Systems ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 6, page no. pp134-142, June-2025, Available at : http://www.jetir.org/papers/JETIRGW06023.pdf