RE-RecSys: An End-to-End system for recommending properties in Real-Estate domain

TL;DR

RE-RecSys is a comprehensive real-estate recommendation system that categorizes users, employs tailored algorithms for each category, and demonstrates real-world efficiency with low latency on a major Indian platform.

Contribution

The paper introduces a novel end-to-end real-estate recommendation pipeline with user categorization, rule-based cold-start handling, and a combined content-collaborative filtering approach, optimized for production.

Findings

Effective user categorization improves recommendation relevance.

The system achieves <40 ms latency at 1000 rpm.

Demonstrated success on real-world Indian real-estate data.

Abstract

We propose an end-to-end real-estate recommendation system, RE-RecSys, which has been productionized in real-world industry setting. We categorize any user into 4 categories based on available historical data: i) cold-start users; ii) short-term users; iii) long-term users; and iv) short-long term users. For cold-start users, we propose a novel rule-based engine that is based on the popularity of locality and user preferences. For short-term users, we propose to use content-filtering model which recommends properties based on recent interactions of users. For long-term and short-long term users, we propose a novel combination of content and collaborative filtering based approach which can be easily productionized in the real-world scenario. Moreover, based on the conversion rate, we have designed a novel weighing scheme for different impressions done by users on the platform for the training of content and collaborative models. Finally, we show the efficiency of the proposed pipeline, RE-RecSys, on a real-world property and clickstream dataset collected from leading real-estate platform in India. We show that the proposed pipeline is deployable in real-world scenario with an average latency of <40 ms serving 1000 rpm.