In modern industrial environments, the increasing volume and complexity of operational data require companies to adopt advanced decision-support systems capable of transforming raw information into actionable managerial insights. Within supply chain and commercial operations, fragmented data sources, manual reporting processes, and limited analytical integration often hinder timely and informed decision-making. This thesis addresses these challenges through the design and implementation of a data-driven decision-support system for the PCT (Pre-Cured Tread) product group within Bridgestone EMEA. The objective of this research is to develop an analytical framework that improves data accessibility, decision traceability, and operational visibility for stakeholders involved in sales, forecasting, production planning, and inventory management. The proposed solution consists of an interactive dashboard developed in Microsoft Power BI, integrating data from multiple sources including SAP transactional systems, corporate Master Data repositories, and structured datasets stored in Excel. A structured data model was designed to consolidate sales, forecast, stock, order book, and production information, enabling the calculation of key performance indicators (KPIs) that support both operational monitoring and tactical decision-making. The dashboard architecture enables users to analyse business performance across multiple dimensions such as time, region, product (IPC), and production source. Through interactive visualizations and standardized KPI logic, the system provides a consistent and transparent view of the business, reducing the need for manual data extraction and improving the efficiency of managerial reporting. Stakeholder feedback was incorporated to assess usability, identify analytical limitations, and propose further improvements. The results demonstrate how a centralized analytical tool can enhance data consistency, reduce reporting inefficiencies, and support faster and more informed decision-making processes. The study contributes to the practical implementation of data-driven supply chain management and outlines future developments related to automation, advanced analytics, and artificial intelligence integration in industrial decision-support systems.
Negli ambienti industriali moderni, il crescente volume e la complessità dei dati operativi richiedono alle aziende l’adozione di sistemi avanzati di supporto alle decisioni in grado di trasformare informazioni grezze in conoscenza utile per il management. Nell’ambito delle operazioni di supply chain e commerciali, la frammentazione delle fonti informative, i processi di reporting manuali e la limitata integrazione analitica ostacolano spesso un processo decisionale tempestivo e informato. Questa tesi affronta tali problematiche attraverso la progettazione e l’implementazione di un sistema di supporto alle decisioni basato sui dati per il gruppo di prodotti PCT (Pre-Cured Tread) di Bridgestone EMEA. L’obiettivo della ricerca è sviluppare un framework analitico che migliori l’accessibilità ai dati, la tracciabilità delle decisioni e la visibilità operativa per gli stakeholder coinvolti nelle attività di vendita, previsione della domanda, pianificazione della produzione e gestione delle scorte. La soluzione proposta consiste in una dashboard interattiva sviluppata in Microsoft Power BI, che integra dati provenienti da diverse fonti, tra cui i sistemi transazionali SAP, i repository di Master Data aziendali e dataset strutturati in Excel. È stato progettato un modello dati strutturato per consolidare informazioni relative a vendite, forecast, stock, order book e produzione, consentendo il calcolo di indicatori chiave di prestazione (KPI) utili al monitoraggio operativo e alle decisioni tattiche. L’architettura della dashboard consente agli utenti di analizzare le performance aziendali secondo diverse dimensioni, come il tempo, la regione, il prodotto (IPC) e la fonte di produzione. Attraverso visualizzazioni interattive e una logica standardizzata di KPI, il sistema fornisce una visione coerente e trasparente del business, riducendo la necessità di estrazione manuale dei dati e migliorando l’efficienza del reporting manageriale. Il feedback degli stakeholder è stato utilizzato per valutare l’usabilità dello strumento, identificare limitazioni analitiche e proporre possibili miglioramenti futuri. I risultati dimostrano come uno strumento analitico centralizzato possa migliorare la coerenza dei dati, ridurre le inefficienze nei processi di reporting e supportare decisioni più rapide e informate. Lo studio contribuisce all’implementazione pratica della gestione della supply chain basata sui dati e delinea possibili sviluppi futuri legati all’automazione, all’analisi avanzata e all’integrazione dell’intelligenza artificiale nei sistemi di supporto alle decisioni industriali.
Design of a data-driven decision support system for industrial business application: the PCT case in Bridgestone EMEA
Álvarez Ceballos, Javier
2025/2026
Abstract
In modern industrial environments, the increasing volume and complexity of operational data require companies to adopt advanced decision-support systems capable of transforming raw information into actionable managerial insights. Within supply chain and commercial operations, fragmented data sources, manual reporting processes, and limited analytical integration often hinder timely and informed decision-making. This thesis addresses these challenges through the design and implementation of a data-driven decision-support system for the PCT (Pre-Cured Tread) product group within Bridgestone EMEA. The objective of this research is to develop an analytical framework that improves data accessibility, decision traceability, and operational visibility for stakeholders involved in sales, forecasting, production planning, and inventory management. The proposed solution consists of an interactive dashboard developed in Microsoft Power BI, integrating data from multiple sources including SAP transactional systems, corporate Master Data repositories, and structured datasets stored in Excel. A structured data model was designed to consolidate sales, forecast, stock, order book, and production information, enabling the calculation of key performance indicators (KPIs) that support both operational monitoring and tactical decision-making. The dashboard architecture enables users to analyse business performance across multiple dimensions such as time, region, product (IPC), and production source. Through interactive visualizations and standardized KPI logic, the system provides a consistent and transparent view of the business, reducing the need for manual data extraction and improving the efficiency of managerial reporting. Stakeholder feedback was incorporated to assess usability, identify analytical limitations, and propose further improvements. The results demonstrate how a centralized analytical tool can enhance data consistency, reduce reporting inefficiencies, and support faster and more informed decision-making processes. The study contributes to the practical implementation of data-driven supply chain management and outlines future developments related to automation, advanced analytics, and artificial intelligence integration in industrial decision-support systems.| File | Dimensione | Formato | |
|---|---|---|---|
|
Thesis_Polimi_Javier_Alvarez_Ceballos_Final.pdf
accessibile in internet per tutti a partire dal 24/06/2027
Dimensione
1.32 MB
Formato
Adobe PDF
|
1.32 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/10589/260629