Skip to main content
Springer Nature Link
Log in

Augmenting XAI with LLMs: A Case Study in Banking Marketing Recommendation

  • Conference paper
  • First Online:
Explainable Artificial Intelligence (xAI 2024)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 2153))

Included in the following conference series:

  • 1045 Accesses

Abstract

Integrating AI-driven recommender systems has proven highly successful in many industries, prompting the banking sector to explore personalised client recommendations. Given the interpersonal nature of banking sales to corporate clients, wherein AI systems recommend to Relationship Managers who facilitate interactions with clients, there is a critical need for explainability in the AI-generated recommendations to support commercial activities. Our work leverages Generative AI and Large Language Models to synthesise natural language explanations for AI algorithms’ motivations, tailored for non-technical users in the banking environment. Through a case study in a major bank, Intesa Sanpaolo, our approach successfully replaces manual expert labour, offering scalable, efficient, and business-relevant explanations. Our study addresses key research questions and contributes by presenting an enriched presentation of SHAP explainer outputs in banking, validated against expert standards. We also explore the impact on the business, providing insights into the value of transparent AI-driven recommendations in the evolving landscape of banking services.

The views and opinions expressed are those of the authors and do not necessarily reflect the views of Intesa Sanpaolo, its affiliates, or employees.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    https://huggingface.co/intfloat/multilingual-e5-large-instruct.

  2. 2.

    The authors did not engage in defining the specific business Key Performance Indicators (KPIs) used to evaluate these business values. These results were shared with the authors by the company, which owns the definition of the specific business KPIs used for evaluating these business values and their monitoring.

References

  1. Ali, T., Kostakos, P.: Huntgpt: integrating machine learning-based anomaly detection and explainable ai with large language models (llms). arXiv preprint arXiv:2309.16021 (2023)

  2. Amatriain, X., Basilico, J.: Recommender systems in industry: a netflix case study. In: Ricci, F., Rokach, L., Shapira, B. (eds.) Recommender Systems Handbook, pp. 385–419. Springer, Boston, MA (2015). https://doi.org/10.1007/978-1-4899-7637-6_11

    Chapter  Google Scholar 

  3. Brennen, A.: What do people really want when they say they want “explainable ai?” we asked 60 stakeholders. In: Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems, pp. 1–7 (2020)

    Google Scholar 

  4. Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877–1901 (2020)

    Google Scholar 

  5. Burkart, N., Huber, M.F.: A survey on the explainability of supervised machine learning. J. Artif. Intell. Res. 70, 245–317 (2021)

    Article  MathSciNet  Google Scholar 

  6. Cambria, E., Malandri, L., Mercorio, F., Mezzanzanica, M., Nobani, N.: A survey on xai and natural language explanations. Inf. Process. Manage. 60(1), 103111 (2023). https://doi.org/10.1016/j.ipm.2022.103111

    Article  Google Scholar 

  7. Castelnovo, A., Cosentini, A., Malandri, L., Mercorio, F., Mezzanzanica, M.: Fftree: a flexible tree to handle multiple fairness criteria. Inf. Process. Manage. 59(6), 103099 (2022)

    Article  Google Scholar 

  8. Chaves, A.P., Gerosa, M.A.: How should my chatbot interact? a survey on social characteristics in human-chatbot interaction design. Int. J. Hum.-Comput. Interact. 37(8), 729–758 (2021)

    Article  Google Scholar 

  9. Chen, T., Guestrin, C.: Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785–794 (2016)

    Google Scholar 

  10. Chun, J., Elkins, K.: explainable ai with gpt4 for story analysis and generation: a novel framework for diachronic sentiment analysis. Int. J. Digital Humanities 5(2), 507–532 (2023)

    Article  Google Scholar 

  11. Costa, F., Ouyang, S., Dolog, P., Lawlor, A.: Automatic generation of natural language explanations. In: Proceedings of the 23rd International Conference on Intelligent User Interfaces Companion, pp. 1–2 (2018)

    Google Scholar 

  12. De Gennaro, M., Krumhuber, E.G., Lucas, G.: Effectiveness of an empathic chatbot in combating adverse effects of social exclusion on mood. Front. Psychol. 10, 3061 (2020)

    Article  Google Scholar 

  13. Donadello, I., Dragoni, M.: Bridging signals to natural language explanations with explanation graphs. In: Proceedings of the 2nd Italian Workshop on Explainable Artificial Intelligence (2021)

    Google Scholar 

  14. Dong, Q., Li, L., Dai, D., Zheng, C., Wu, Z., Chang, B., Sun, X., Xu, J., Sui, Z.: A survey for in-context learning. arXiv preprint arXiv:2301.00234 (2022)

  15. Ehsan, U., Tambwekar, P., Chan, L., Harrison, B., Riedl, M.O.: Automated rationale generation: a technique for explainable ai and its effects on human perceptions. In: Proceedings of the 24th International Conference on Intelligent User Interfaces, pp. 263–274 (2019)

    Google Scholar 

  16. Ghobakhloo, M., Ghobakhloo, M.: Design of a personalized recommender system using sentiment analysis in social media (case study: banking system). Soc. Netw. Anal. Min. 12(1), 84 (2022)

    Article  Google Scholar 

  17. Goyani, M., Chaurasiya, N.: A review of movie recommendation system: Limitations, survey and challenges. ELCVIA: electronic letters on computer vision and image analysis 19(3), 0018–37 (2020)

    Google Scholar 

  18. Hendricks, L.A., Hu, R., Darrell, T., Akata, Z.: Generating counterfactual explanations with natural language. In: ICML Workshop on Human Interpretability in Machine Learning, pp. 95–98 (2018)

    Google Scholar 

  19. Jiang, A.Q., et al.: Mixtral of experts. ArXiv abs/2401.04088 (2024)

    Google Scholar 

  20. Kokalj, E., Škrlj, B., Lavrač, N., Pollak, S., Robnik-Šikonja, M.: BERT meets shapley: extending SHAP explanations to transformer-based classifiers. In: Toivonen, H., Boggia, M. (eds.) Proceedings of the EACL Hackashop on News Media Content Analysis and Automated Report Generation, pp. 16–21. Association for Computational Linguistics, Online, April 2021

    Google Scholar 

  21. Kuiper, O., van den Berg, M., van der Burgt, J., Leijnen, S.: Exploring explainable ai in the financial sector: Perspectives of banks and supervisory authorities. In: Artificial Intelligence and Machine Learning: 33rd Benelux Conference on Artificial Intelligence, BNAIC/Benelearn 2021, Esch-sur-Alzette, Luxembourg, November 10–12, 2021, Revised Selected Papers 33, pp. 105–119. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-93842-0_6

  22. Lin, C.Y.: Rouge: A package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74–81 (2004)

    Google Scholar 

  23. Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: Neural Information Processing Systems (2017)

    Google Scholar 

  24. Malandri, L., Mercorio, F., Mezzanzanica, M., Nobani, N.: Convxai: a system for multimodal interaction with any black-box explainer. Cogn. Comput. 15(2), 613–644 (2023)

    Article  Google Scholar 

  25. Malandri, L., Mercorio, F., Mezzanzanica, M., Nobani, N., Seveso, A.: Contrxt: generating contrastive explanations from any text classifier. Inf. Fusion 81, 103–115 (2022). https://doi.org/10.1016/j.inffus.2021.11.016

    Article  Google Scholar 

  26. Malandri, L., Mercorio, F., Mezzanzanica, M., Nobani, N., Seveso, A., et al.: The good, the bad, and the explainer: a tool for contrastive explanations of text classifiers. In: IJCAI, pp. 5936–5939 (2022)

    Google Scholar 

  27. Malandri, L., Mercorio, F., Mezzanzanica, M., Seveso, A.: Model-contrastive explanations through symbolic reasoning. Decis. Support Syst. 176, 114040 (2024)

    Article  Google Scholar 

  28. Mann, H.B., Whitney, D.R.: On a test of whether one of two random variables is stochastically larger than the other. The annals of mathematical statistics, pp. 50–60 (1947)

    Google Scholar 

  29. Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. Advances in neural information processing systems 26 (2013)

    Google Scholar 

  30. Miller, T.: Explanation in artificial intelligence: insights from the social sciences. Artif. Intell. 267, 1–38 (2019)

    Article  MathSciNet  Google Scholar 

  31. Miller, T.: Explainable ai is dead, long live explainable ai! hypothesis-driven decision support using evaluative ai. In: Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency, FAccT 2023, pp. 333–342. Association for Computing Machinery, New York (2023).https://doi.org/10.1145/3593013.3594001, https://doi.org/10.1145/3593013.3594001

  32. Muennighoff, N., Tazi, N., Magne, L., Reimers, N.: Mteb: massive text embedding benchmark. arXiv preprint arXiv:2210.07316 (2022).https://doi.org/10.48550/ARXIV.2210.07316

  33. O’Hara, K.: Explainable ai and the philosophy and practice of explanation. Comput. Law Secur. Rev. 39, 105474 (2020)

    Article  Google Scholar 

  34. Oyebode, O., Orji, R.: A hybrid recommender system for product sales in a banking environment. J. Banking Financial Technol. 4, 15–25 (2020)

    Article  Google Scholar 

  35. Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)

    Google Scholar 

  36. Raghuwanshi, S.K., Pateriya, R.K.: Recommendation systems: techniques, challenges, application, and evaluation. In: Bansal, J.C., Das, K.N., Nagar, A., Deep, K., Ojha, A.K. (eds.) Soft Computing for Problem Solving. AISC, vol. 817, pp. 151–164. Springer, Singapore (2019). https://doi.org/10.1007/978-981-13-1595-4_12

    Chapter  Google Scholar 

  37. Rahutomo, F., Kitasuka, T., Aritsugi, M.: Semantic cosine similarity. In: The 7th International Student Conference on Advanced Science and Technology ICAST, vol. 4, p. 1 (2012)

    Google Scholar 

  38. Shapiro, S.S., Wilk, M.B.: An analysis of variance test for normality (complete samples). Biometrika 52(3/4), 591–611 (1965)

    Article  MathSciNet  Google Scholar 

  39. Sharaf, M., Hemdan, E.E.D., El-Sayed, A., El-Bahnasawy, N.A.: A survey on recommendation systems for financial services. Multimed. Tools Appl. 81(12), 16761–16781 (2022)

    Article  Google Scholar 

  40. Slack, D., Krishna, S., Lakkaraju, H., Singh, S.: Explaining machine learning models with interactive natural language conversations using talktomodel. Nature Mach. Intell. 5(8), 873–883 (2023)

    Article  Google Scholar 

  41. Smith, B., Linden, G.: Two decades of recommender systems at amazon.com. IEEE Internet Comput. 21(3), 12–18 (2017)

    Google Scholar 

  42. Sokol, K., Flach, P.: Limetree: Consistent and faithful surrogate explanations of multiple classes (2023)

    Google Scholar 

  43. Vaswani, A., et al.: Attention is all you need. Advances in neural information processing systems 30 (2017)

    Google Scholar 

  44. Wang, L., Yang, N., Huang, X., Yang, L., Majumder, R., Wei, F.: Multilingual e5 text embeddings: a technical report. arXiv preprint arXiv:2402.05672 (2024)

  45. Wu, Z., Li, C., Cao, J., Ge, Y.: On scalability of association-rule-based recommendation: a unified distributed-computing framework. ACM Trans. Web (TWEB) 14(3), 1–21 (2020)

    Google Scholar 

  46. Zhang, Y., Chen, X., et al.: Explainable recommendation: a survey and new perspectives. Found. Trends Inf. Retrieval 14(1), 1–101 (2020)

    Google Scholar 

  47. Zhao, W.X., et al.: A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)

  48. Zheng, L., et al.: Judging llm-as-a-judge with mt-bench and chatbot arena. Advances in Neural Information Processing Systems 36 (2024)

    Google Scholar 

Download references

Acknowledgments

We extend our deepest gratitude to the Digital Solutions & Analytics office for their invaluable support and for establishing the gold standards used in this research. Special thanks to Valerio Lodola, Giulia Della Pedrina, Matteo Tribastone, and the Digital Business Partners Eugenia Ceresetti and Brunella Cutrera for facilitating interaction within banking structures.

Additionally, we would like to thank the Competence Center of AI for providing on-premises Gen AI services for this work. We appreciate Pierluigi Lacqua, Francesco Bonazzi, Stefania Piosso, and Claudia Berloco’s invaluable assistance and expertise.

Lastly, thanks to Marco Ditta, Andrea Cosentini, Maddalena Amoruso, and Mauro Pinto for their constant encouragement to explore innovations within Intesa Sanpaolo.

Author information

Authors and Affiliations

  1. Department of Economics and Management, University of Brescia, Brescia, Italy

    Nicolò Mombelli

  2. Digital Solutions and Analytics, Intesa Sanpaolo, Milan, Italy

    Roberto Depalmas

  3. Department of Statistics and Quantitative Methods, University of Milano Bicocca, Milan, Italy

    Fabio Mercorio & Andrea Seveso

  4. CRISP Research Centre, University of Milano Bicocca, Milan, Italy

    Fabio Mercorio, Daniele Potertì, Antonio Serino & Andrea Seveso

  5. AI Delivery Center, Intesa Sanpaolo, Brescia, Italy

    Nicolò Mombelli

  6. Department of Physics, Politecnico di Milano, Milan, Italy

    Salvatore Sorrentino

  7. Var Group Data Science, Bologna, Italy

    Laura Viola

  8. AI Delivery Center, Intesa Sanpaolo, Milan, Italy

    Alessandro Castelnovo & Salvatore Sorrentino

  9. Department of Economics, Management and Statistics, University of Milano Bicocca, Milan, Italy

    Daniele Potertì & Antonio Serino

Authors
  1. Alessandro Castelnovo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Roberto Depalmas
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Fabio Mercorio
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Nicolò Mombelli
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Daniele Potertì
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Antonio Serino
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Andrea Seveso
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Salvatore Sorrentino
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Laura Viola
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Andrea Seveso .

Editor information

Editors and Affiliations

  1. Technological University Dublin, Dublin, Ireland

    Luca Longo

  2. Fraunhofer Institute for Telecommunications, Heinrich-Hertz-Institut, HHI, Berlin, Germany

    Sebastian Lapuschkin

  3. University of Marburg, Marburg, Germany

    Christin Seifert

Ethics declarations

Disclosure of Interests

The authors declare that they have no relevant or material financial interests that relate to the research described in this paper. No funding was received for this study, and no other potential conflicts of interest exist.

Rights and permissions

Reprints and permissions

Copyright information

© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Castelnovo, A. et al. (2024). Augmenting XAI with LLMs: A Case Study in Banking Marketing Recommendation. In: Longo, L., Lapuschkin, S., Seifert, C. (eds) Explainable Artificial Intelligence. xAI 2024. Communications in Computer and Information Science, vol 2153. Springer, Cham. https://doi.org/10.1007/978-3-031-63787-2_11

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-63787-2_11

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-63786-5

  • Online ISBN: 978-3-031-63787-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics