This thesis explores a comprehensive customer segmentation and churn prediction framework in a B2B machinery rental context using advanced Customer Relationship Management (CRM) methodologies. Unlike typical B2C environments, B2B customer behavior is more complex and often includes both contractual and non-contractual elements. The study builds on foundational RFM (Recency, Frequency, Monetary) analysis and extends it by incorporating purchase and quantity regularity to enhance prediction accuracy and strategic insights. Various clustering methods are employed to segment customers based on behavioral patterns, and churn models such as Gradient Boosting and Erlang-k are applied to assess future engagement likelihood. The approach introduces a quarterly churn labeling system tailored to project-based B2B sales cycles, which differ significantly from conventional churn definitions. Results demonstrate that regularity metrics and frequency are key predictors of churn. Additionally, Lean and Theory of Constraints (TOC) principles are applied to CRM strategies to align operational efficiency with customer value. The findings provide actionable insights for customer retention, fleet optimization, and targeted marketing strategies, contributing to a data-driven framework for sustainable relationship management in industrial services.
Questa tesi esplora un quadro completo per la segmentazione dei clienti e la previsione del churn nel contesto B2B del noleggio di macchinari, utilizzando metodologie avanzate di Customer Relationship Management (CRM). A differenza degli ambienti tipici B2C, il comportamento dei clienti B2B è più complesso e spesso include elementi sia contrattuali che non contrattuali. Lo studio si basa sull’analisi RFM (Recency, Frequency, Monetary) e la estende integrando la regolarità degli acquisti e delle quantità per migliorare l’accuratezza predittiva e offrire approfondimenti strategici. Vengono impiegati diversi metodi di clustering per segmentare i clienti in base ai modelli comportamentali, mentre modelli di churn come Gradient Boosting ed Erlang-k sono utilizzati per valutare la probabilità di engagement futuro. L’approccio introduce un sistema di etichettatura del churn su base trimestrale, adattato ai cicli di vendita B2B basati sui progetti, significativamente diversi dalle definizioni convenzionali di churn. I risultati dimostrano che le metriche di regolarità e la frequenza sono predittori chiave del churn. Inoltre, i principi del Lean Management e della Theory of Constraints (TOC) vengono applicati alle strategie CRM per allineare l’efficienza operativa al valore del cliente. I risultati forniscono indicazioni pratiche per la fidelizzazione dei clienti, l’ottimizzazione del parco macchine e strategie di marketing mirate, contribuendo a un quadro basato sui dati per una gestione sostenibile delle relazioni nei servizi industriali.
Enhancing the B2B machinery rental retention by integrating RFM and purchase regularity of the customers
Mardani, Bahareh
2024/2025
Abstract
This thesis explores a comprehensive customer segmentation and churn prediction framework in a B2B machinery rental context using advanced Customer Relationship Management (CRM) methodologies. Unlike typical B2C environments, B2B customer behavior is more complex and often includes both contractual and non-contractual elements. The study builds on foundational RFM (Recency, Frequency, Monetary) analysis and extends it by incorporating purchase and quantity regularity to enhance prediction accuracy and strategic insights. Various clustering methods are employed to segment customers based on behavioral patterns, and churn models such as Gradient Boosting and Erlang-k are applied to assess future engagement likelihood. The approach introduces a quarterly churn labeling system tailored to project-based B2B sales cycles, which differ significantly from conventional churn definitions. Results demonstrate that regularity metrics and frequency are key predictors of churn. Additionally, Lean and Theory of Constraints (TOC) principles are applied to CRM strategies to align operational efficiency with customer value. The findings provide actionable insights for customer retention, fleet optimization, and targeted marketing strategies, contributing to a data-driven framework for sustainable relationship management in industrial services.File | Dimensione | Formato | |
---|---|---|---|
Enhancing the B2B Machinery Rental Retention by Integrating RFM and Purchase Regularity of the Customers.pdf
accessibile in internet per tutti a partire dal 26/06/2026
Dimensione
4.21 MB
Formato
Adobe PDF
|
4.21 MB | Adobe PDF | Visualizza/Apri |
I documenti in POLITesi sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/10589/240923