Data analytics e intelligenza artificiale per l’analisi di bilancio. Performance e profili di business degli spin-off accademici

This research applies neural networks – namely: Self-Organising Maps (SOMs) - to analyse a bunch of financial indicators drawn from the balance sheet of academic spin-offs. The goal of the work is twofold: first, it aims at processing financial data to extract knowledge about the still uncertain role and strategic profile of academic spin-offs; second, it aims at understating whether SOMs are able to support investigations on firms’ performance, and to decide strategic orientation thanks to the processing of financial indicators. After a deep literature review about both the application of SOMs to financial reporting data and the business profile of academic spin-offs, the paper carries on an empirical investigation on 810 Italian academic spin-offs, using their financial reporting data. The results show that SOMs succeed in extracting the main features of different academic spin-off archetypes that can be then explained via traditional financial analysis instruments.