Published April 16, 2025 | Version v2
Dissertation Open

Verso un Sistema Adattivo e White-Box per il Supporto alle Decisioni

Authors/Creators

  • 1. Università degli Studi di Firenze

Contributors

Supervisor:

  • 1. Università degli Studi di Firenze

Description

Questa tesi esplora lo sviluppo di un framework adattivo per il supporto alle decisioni automatizzate, ispirato ai processi cognitivi umani descritti nella psicologia comportamentale. Il sistema proposto, denominato CASS (Context Aware Selection System), è progettato per selezionare dinamicamente l’algoritmo di machine learning più appropriato in base alla distribuzione dei dati e al contesto operativo, massimizzando la fiducia nella decisione presa.

L'architettura del CASS si fonda sull'integrazione di tecniche di ensemble learning e modelli di scoring basati sulla fiducia, con l’obiettivo di aumentare la trasparenza e l’adattabilità del processo decisionale. Il sistema prende ispirazione dal Sistema 2 di Kahneman, implementando un approccio deliberativo e analitico alla scelta dell’algoritmo.

La validazione sperimentale è stata condotta su diversi dataset reali, sia in ambito di classificazione che di regressione, dimostrando miglioramenti significativi in termini di robustezza, affidabilità e interpretabilià rispetto a metodi tradizionali e a baseline naïve. La tesi include inoltre una proposta metodologica per l’analisi del livello di fiducia nei modelli, utile per applicazioni in domini critici come la cybersecurity, la sanità e l’intelligenza artificiale responsabile.

Per ulteriori informazioni o approfondimenti sul progetto, è possibile contattarmi all’indirizzo mpietri82@gmail.com oppure visitare il sito marcopietri.framer.website.

 

Abstract (En)

This thesis presents an adaptive framework for decision support, inspired by human cognitive processes. The proposed system, CASS (Context Aware Selection System), dynamically selects the most suitable algorithm based on the characteristics of the input data and the context.

Combining ensemble learning and confidence-based evaluation, the system aims to enhance the reliability and transparency of machine learning decisions. The implementation includes a modular architecture influenced by Kahneman's System 2 and demonstrates improved performance across various datasets and learning scenarios.

For further information or insights regarding this project, feel free to contact me at mpietri82@gmail.com or visit marcopietri.framer.website.

Files

Towards_an_Adaptive_White-Box_System_for_Decision_Support__Marco_Pietri_V5.pdf

Files (1.8 MB)

Additional details

Additional titles

Translated title (En)
Towards an Adaptive and White-Box System for Decision Support

Dates

Accepted
2025-04-01
Tesi consegnata
Accepted
2025-04-16
Data di discussione della tesi

References

  • Simon, H. A. (2013). Administrative behavior. Simon and Schuster.
  • Bazerman, M. H., & Moore, D. A. (2012). Judgment in managerial decision making. John Wiley & Sons.
  • Kahneman, D. (2011). Thinking, fast and slow. Macmillan.
  • Tversky, A., & Kahneman, D. (1974). Judgment under Uncertainty: Heuristics and Biases. Science, 185(4157), 1124–1131.
  • Forsyth, D. R. (2014). Group dynamics. Wadsworth Cengage Learning.
  • Saaty, T. L. (1982). The analytic hierarchy process. Architectural Science Review, 25(3), 64–69.
  • Gigerenzer, G., & Todd, P. M. (1999). Simple heuristics that make us smart.
  • Gigerenzer, G., Todd, P. M., & ABC Research Group, T. (2000). Simple heuristics that make us smart. Oxford University Press.
  • Raiffa, H., & Schlaifer, R. (2000). Applied statistical decision theory. John Wiley & Sons.
  • Loewenstein, G. F., Weber, E. U., Hsee, C. K., & Welch, N. (2001). Risk as feelings. Psychological Bulletin, 127(2), 267.
  • Kahneman, D., & Tversky, A. (2013). Prospect theory: An analysis of decision under risk. In Handbook of the fundamentals of financial decision making: Part I (pp. 99–127).
  • Gigerenzer, G., & Goldstein, D. G. (1996). Reasoning the fast and frugal way. Psychological Review, 103(4), 650.
  • Greene, J. D., Sommerville, R. B., Nystrom, L. E., Darley, J. M., & Cohen, J. D. (2001). An fMRI investigation of emotional engagement in moral judgment. Science, 293(5537), 2105–2108.
  • Hubbard, D. W. (2014). How to measure anything. John Wiley & Sons.
  • Binns, R. (2018). Fairness in machine learning: Lessons from political philosophy. In Conference on fairness, accountability and transparency (pp. 149–159). PMLR.
  • Holzinger, A., Saranti, A., Molnar, C., Biecek, P., & Samek, W. (2020). Explainable AI methods – a brief overview. In Springer Workshop (pp. 13–38).
  • Mitchell, T. M. (1997). Machine learning. New York: McGraw-Hill.
  • Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep feedforward networks. Deep learning, 1, 161–217.
  • Turing, A. M. (2009). Computing machinery and intelligence. Springer Netherlands, 23–65.
  • Breiman, L. (2001). Random forests. Machine Learning, 45, 5–32.
  • Finn, C., Abbeel, P., & Levine, S. (2017). Model-agnostic meta-learning. In ICML (pp. 1126–1135). PMLR.
  • Cannarsa, M. (2021). Ethics guidelines for trustworthy AI. The Cambridge Handbook of Lawyering in the Digital Age, 283–297.
  • Simon, H. A. (1960). The new science of management decision.
  • Mintzberg, H., Raisinghani, D., & Theoret, A. (1976). The structure of "unstructured" decision processes. Administrative Science Quarterly, 246–275.
  • March, J. G., & Simon, H. A. (1958). Organizations. John Wiley & Sons.
  • Tripathy, S. S., & Behera, B. (2024). A review of various datasets for ML-based IDS. IJISAE, 12(4), 3833–3857.
  • Singh, R., Soni, R., Kumar, P., Shukla, A., & Yadav, P. A new approach in neural networks for cyber security.
  • Rajpurkar, P., et al. (2017). ChexNet: Pneumonia detection on X-rays with DL. arXiv:1711.05225.
  • Jumper, J., Evans, R., et al. (2021). AlphaFold. Nature, 596(7873), 583–589.
  • Chen, T., & Guestrin, C. (2016). XGBoost. In KDD '16 (pp. 785–794).
  • Fischer, T., & Krauss, C. (2018). LSTM for financial predictions. European Journal of Operational Research, 270(2), 654–669.
  • Floridi, L., Cowls, J., et al. (2018). AI4People. Minds and Machines, 28, 689–707.
  • Kurakin, A., Goodfellow, I., & Bengio, S. (2016). Adversarial ML at scale. arXiv:1611.01236.
  • Turban, E. (2011). Decision support and BI systems. Pearson Education India.
  • Murphy, K. P. (2012). Machine learning: A probabilistic perspective. MIT Press.
  • Russell, S. J., & Norvig, P. (2016). Artificial intelligence: A modern approach. Pearson.
  • Pearl, J. (2014). Probabilistic reasoning in intelligent systems. Elsevier.
  • Silver, D., et al. (2017). Mastering Go without human knowledge. Nature, 550(7676), 354–359.
  • Feurer, M., et al. (2015). Automated machine learning. NeurIPS, 28.
  • Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). "Why should I trust you?" In KDD '16 (pp. 1135–1144).
  • Vrbančič, G. (2020). Phishing websites dataset (v1). Mendeley Data. https://doi.org/10.17632/72ptz43s9v.1
  • Hannousse, A., & Yahiouche, S. (2021). Web page phishing detection (v3). Mendeley Data. https://doi.org/10.17632/c2gw7fy2j4.3
  • APS Failure at Scania Trucks (2016). UCI ML Repository. https://doi.org/10.24432/C51S51
  • Fisher, R. A. (1936). The use of multiple measurements in taxonomic problems. Annals of Eugenics, 7(2), 179–188.