AUTHOR=Kaplan Ahmet , Seker Sadi Evren , Yoruk Rabia 

TITLE=A review of AI-based business lead generation: Scrapus as a case study

JOURNAL=Frontiers in Artificial Intelligence

VOLUME=Volume 8 - 2025

YEAR=2025

URL=https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2025.1606431

DOI=10.3389/frai.2025.1606431

ISSN=2624-8212

ABSTRACT=The exponential growth of open web data provides unprecedented opportunities for business-to-business (B2B) lead generation. However, automating the discovery and qualification of new leads from unstructured web content is a complex challenge requiring the integration of web crawling, information extraction, and data-driven analytics. This article presents a comprehensive review of artificial intelligence (AI) methods for automated lead generation and introduces Scrapus, an AI-driven web prospecting platform that unifies these methods into an end-to-end system. Scrapus autonomously crawls the open web for company information, extracts and enriches relevant data (using natural language processing and knowledge graphs), matches findings to user-defined ideal customer profiles, and generates concise natural-language lead summaries using large language models. We survey relevant literature in web mining, focused crawling, entity resolution, and text summarization – highlighting how Scrapus builds upon and extends prior work. The system’s modular architecture and AI components are described in detail, reflecting accurate implementation details. We also report an experimental evaluation on real-world data: Scrapus significantly outperforms baseline approaches in lead discovery rate, extraction accuracy, lead qualification (achieving ~90% precision and recall), and summary usefulness. The results show a ~3 × higher relevant lead yield from web crawling due to reinforcement learning, a substantial increase in extraction F1 (from ~0.77 to ~0.92) through transformer-based NLP, and greatly improved lead scoring over traditional methods. This review and case study demonstrate that combining reinforcement learning, transformer-based NLP, and knowledge-enhanced analysis can effectively automate B2B lead generation. The advances surveyed here point toward a new generation of intelligent sales prospecting tools, in which AI techniques augment human expertise to identify and engage leads at scale.