RE-GrievanceAssist: Enhancing Customer Experience through ML-Powered Complaint Management

TL;DR

RE-GrievanceAssist is an ML-powered complaint management pipeline for real estate platforms that reduces manual effort and costs by automating response prediction, user classification, and issue categorization.

Contribution

The paper presents a novel end-to-end ML pipeline tailored for real estate customer complaints, integrating multiple classifiers and deployment in Databricks for efficiency.

Findings

40% reduction in manual effort

Monthly cost savings of Rs 1,50,000

Effective automation of complaint handling

Abstract

In recent years, digital platform companies have faced increasing challenges in managing customer complaints, driven by widespread consumer adoption. This paper introduces an end-to-end pipeline, named RE-GrievanceAssist, designed specifically for real estate customer complaint management. The pipeline consists of three key components: i) response/no-response ML model using TF-IDF vectorization and XGBoost classifier ; ii) user type classifier using fasttext classifier; iii) issue/sub-issue classifier using TF-IDF vectorization and XGBoost classifier. Finally, it has been deployed as a batch job in Databricks, resulting in a remarkable 40% reduction in overall manual effort with monthly cost reduction of Rs 1,50,000 since August 2023.