AI-Driven Lead Discovery and Ranking for Middle-Sized Enterprises

  • Konstantin Johannes Lausecker

Student thesis: Master's Thesis

Abstract

In an increasingly competitive business landscape, small and medium-sized enterprises
(SMEs) face significant challenges in identifying and acquiring high-quality leads. While
Customer Relationship Management (CRM) systems store vast amounts of customer
data, many enterprises struggle to transform this data into actionable insights.
This thesis explores the potential of artificial intelligence (AI) to optimize lead discovery and ranking processes, enhancing customer acquisition efforts for SMEs. By using
data from CRM systems to develop advanced machine learning models, this thesis provides recommendations for automating lead generation and prioritization. The research
focuses on web scraping techniques to enrich CRM data with external datasets, leveraging these expanded datasets to train machine learning algorithms for predicting lead
quality and revenue potential.
Key AI techniques, including random forest, logistic regression and linear regression,
are evaluated to identify the most effective methods for lead prediction and scoring.
The findings demonstrate that AI-driven lead prediction and scoring not only outperform random guessing but also show potential to increase the efficiency of sales teams
by prioritizing high-value prospects.
Furthermore, recommendations for integration of these AI models into existing CRM
systems and directions for further development on enhancing the most promising machine learning models of this thesis are made.
Date of Award2024
Original languageEnglish (American)
SupervisorUlrich Bodenhofer (Supervisor)

Cite this

'