This thesis describes the activity carried out by Stefani Riccardo during a 320-hour curricular internship at the company Oribea AI S.r.l. The project is part of the Business Intelligence and Machine Learning fields, with the aim of developing a Task AI for sales analysis, using data from company databases or public datasets. The system created uses a Large Language Model (LLM) to generate automatic, interpretable and customizable analyses. Furthermore, the project also includes the development of a recommendation system integrated into a specific Task AI, which allows recommending products to customers based on their preferences and purchasing behaviors, and vice versa to suggest potential customers to whom to propose the products, optimizing marketing and sales strategies. Before the development phase, an in-depth study was conducted of the technologies chosen and the fundamental economic concepts to guarantee the quality of the sales analyses and recommendations produced. The activities and solutions adopted are illustrated in the following chapters.
Questo elaborato descrive l’attività svolta da Stefani Riccardo durante un tirocinio curriculare della durata di 320 ore presso l’azienda Oribea AI S.r.l. Il progetto si inserisce negli ambiti della Business Intelligence e del Machine Learning, con l'obiettivo di sviluppare una Task AI per l'analisi delle vendite, utilizzando dati provenienti da database aziendali o dataset pubblici. Il sistema realizzato sfrutta un Large Language Model (LLM) per generare analisi automatiche, interpretabili e personalizzabili. Inoltre, il progetto prevede anche lo sviluppo di un sistema di raccomandazione integrato in un'apposita Task AI, che permetta di raccomandare prodotti ai clienti in base alle loro preferenze e comportamenti di acquisto, e viceversa di suggerire possibili clienti a cui proporre i prodotti, ottimizzando le strategie di marketing e vendita. Prima della fase di sviluppo, è stato condotto uno studio approfondito delle tecnologie scelte e dei concetti economici fondamentali per garantire la qualità delle analisi delle vendite e delle raccomandazioni prodotte. Le attività e le soluzioni adottate vengono illustrate nei capitoli successivi.
Migliorare la Business Intelligence con l'AI: Sviluppo di un sistema di raccomandazioni e report automatico basato su analisi delle vendite
STEFANI, RICCARDO
2024/2025
Abstract
This thesis describes the activity carried out by Stefani Riccardo during a 320-hour curricular internship at the company Oribea AI S.r.l. The project is part of the Business Intelligence and Machine Learning fields, with the aim of developing a Task AI for sales analysis, using data from company databases or public datasets. The system created uses a Large Language Model (LLM) to generate automatic, interpretable and customizable analyses. Furthermore, the project also includes the development of a recommendation system integrated into a specific Task AI, which allows recommending products to customers based on their preferences and purchasing behaviors, and vice versa to suggest potential customers to whom to propose the products, optimizing marketing and sales strategies. Before the development phase, an in-depth study was conducted of the technologies chosen and the fundamental economic concepts to guarantee the quality of the sales analyses and recommendations produced. The activities and solutions adopted are illustrated in the following chapters.| File | Dimensione | Formato | |
|---|---|---|---|
|
Stefani_Riccardo_tesi.pdf
accesso aperto
Dimensione
3.83 MB
Formato
Adobe PDF
|
3.83 MB | Adobe PDF | Visualizza/Apri |
The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License
https://hdl.handle.net/20.500.12608/90010