1 views collected around this technical thread.
This tutorial walks you through building a Python web‑scraper for Beike (Lianjia) second‑hand property listings, covering session spoofing, dynamic parameters, pagination, multithreaded detail fetching, data cleaning, and exporting results to Excel in a step‑by‑step manner.
This article presents a comprehensive case study on how large language models are integrated into 58.com’s real‑estate recommendation platform, detailing challenges, data adaptation, prompt and parameter optimizations, embedding generation, conversational recommendation, and future directions for multimodal and generative recommendation systems.
This article provides a comprehensive Python tutorial for scraping second‑hand housing community data from Anjuke, covering city selection, URL collection, HTML parsing with lxml, data cleaning, CSV export, and full‑city crawling strategies, complete with runnable code examples.
This presentation outlines the landscape of black and gray market activities in China's residential real‑estate platform, describes the various fraud scenarios, details intelligence collection, tracing architecture, and anti‑fraud measures, and shares typical cases such as fake C‑side registrations and crawler attacks.
This article presents Beike's experience in intelligent real‑estate advertising, detailing the business background, key technical challenges such as conversion‑rate estimation, delayed‑feedback modeling, GEO targeting, and budget allocation, and sharing practical solutions that improved conversion rates by over 10%.
This article presents Beike's experience in applying intelligent advertising to the real‑estate industry, detailing business background, key technical challenges, multi‑task conversion modeling, GEO user targeting, delayed‑feedback calibration, and ROI‑driven budget allocation to improve ad effectiveness.
This presentation details the current landscape of black and gray market activities in the residential services sector, describes typical fraud scenarios such as fake user registrations and crawler attacks, and outlines Beike's intelligence collection, tracing capabilities, and multi‑stage anti‑fraud operations to detect, investigate, and mitigate these threats.
This article explains the wide applicability of causal inference, outlines three major challenges—correlation vs. causation, confounding factors, and selection bias—and demonstrates a scientific three‑level approach using examples such as smoking and a real‑world deployment of an intelligent client‑management tool at Beike, including experimental designs, results, and lessons learned.
This article analyzes the structure of black production in the real estate industry, focusing on its impact on companies like 贝壳 and the countermeasures implemented to combat it.
This article presents the end‑to‑end practice of a second‑hand housing recommendation system at 58.com and Anjuke, covering business background, embedding‑based vector recall, multi‑objective ranking methods such as ESMM and MMOE, experimental results, and future development directions.
This presentation details Beike Real Estate's development of entity and reasoning knowledge graphs, their integration into intelligent training, the methods for knowledge acquisition, organization, and operation, and future directions for industry-wide knowledge standards, illustrating how AI-driven data pipelines enhance real‑estate services.
This presentation details Beike's AI‑driven commercial strategy platform, covering business scenarios, the evolution of its architecture from 2018 to 2020, the challenges faced, the redesign into online, near‑real‑time, and offline layers, key technologies such as vector search, model serving, and microservice governance, as well as performance gains and future directions.
This paper explores user preference mining techniques in real estate, utilizing statistical methods and machine learning models like XGBoost, LSTM, and Seq4Rec to address challenges in high-dimensional, sparse data, enhancing personalized recommendations and marketing strategies.
This article presents a comprehensive study of the Wide & Deep architecture applied to user purchase‑intent quantification in the real‑estate domain, detailing feature engineering, model design, training procedures, experimental results, and extensions with GRU‑based sequential modeling to improve accuracy.
This article analyzes the challenges of generating massive QR codes for a real‑estate mini‑program, including URL length, concurrency limits, and path management, and presents a backend‑focused solution that uses short‑URL services, request‑id binding, pre‑generation, caching, and Kafka to achieve scalable, low‑latency QR code delivery.
This article explains how 58.com applies various embedding methods—including ALS, Skip‑gram, and DeepWalk—to vectorize users and properties, improve similarity calculations, and enhance both recall and ranking stages of its real‑estate recommendation system, with detailed technical descriptions and evaluation results.
The article explains how Beike Real Estate constructs an industry knowledge graph by integrating internal and external data, outlines the technical framework and data processing steps, and demonstrates its AI-driven applications such as intelligent Q&A, recommendation, and decision support for the real‑estate market.
The talk explains how Beike Real Estate constructs a large‑scale relationship graph from billions of user, house, and agent interactions, quantifies edge strengths, builds homogeneous and heterogeneous sub‑graphs, derives graph capabilities such as node influence, embedding, similarity and relation prediction, and finally deploys these capabilities in multi‑degree queries, house‑similarity recommendations and B‑side agent assistance, achieving measurable CTR improvements.
The article details how Beike's Agent Cooperation Network employs a multi‑layered risk control framework built on large‑scale knowledge graphs, graph mining, and machine‑learning techniques to detect fake listings, malicious competition, and other threats across both online and offline real‑estate scenarios.
The article reports on Beike Zhaofang's knowledge‑graph technology conference, detailing how relationship graphs are applied to risk control, the four‑layer graph architecture, the use of Spark GraphX, JanusGraph and DGraph, and broader industry‑graph applications in real‑estate AI solutions.