Paper: arXiv 2311.07597

Abstract

Currently, there is a lot of research in the field of neural networks for non-life insurance pricing. The usual goal is to improve the predictive power via neural networks while building upon the generalized linear model, which is the current industry standard. Our paper contributes to this current journey via novel methods to enhance actuarial non-life models with transformer models for tabular data. We build here upon the foundation laid out by the combined actuarial neural network as well as the localGLMnet and enhance those models via the feature tokenizer transformer. The manuscript demonstrates the performance of the proposed methods on a real-world claim frequency dataset and compares them with several benchmark models such as generalized linear models, feed-forward neural networks, combined actuarial neural networks, LocalGLMnet, and pure feature tokenizer transformer. The paper shows that the new methods can achieve better results than the benchmark models while preserving certain generalized linear model advantages. The paper also discusses the practical implications and challenges of applying transformer models in actuarial settings.

Complexity vs Empirical Score

  • Math Complexity: 7.0/10
  • Empirical Rigor: 6.0/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper presents mathematically sophisticated transformer architectures for tabular data and combines them with established actuarial models, yet it validates these methods on a single real-world dataset with standard benchmarks, demonstrating practical backtest-readiness.

Research Flowchart

  flowchart TD
  A["Research Goal<br>Enhance Actuarial Pricing with Transformers"] --> B["Data<br>Real-world Claim Frequency Dataset"]
  B --> C["Methodology<br>Feature Tokenizer Transformer Models"]
  C --> D{"Benchmarks"}
  D --> E["GLM, FNN, CAN, LocalGLMnet, FTT"]
  D --> C
  C --> F["Computational Process<br>Train & Evaluate Hybrid Models"]
  F --> G["Key Findings<br>Superior Performance & GLM Advantages"]

Cited References (46)

  1. LightGBM : A Highly Efficient Gradient Boosting Decision Tree (2017) — link
  2. Predictive learning via rule ensembles (2008) — link
  3. Nesting Classical Actuarial Models into Neural Networks (2019) — link
  4. EDITORIAL : YES , WE CANN ! (2019) — link
  5. From Generalized Linear Models to Neural Networks , and Back (2019) — link
  6. AI : Coming of age? (2022) — link
  7. SHAP for Actuaries : Explain any Model (2023) — link
  8. Enhancing Logistic Regression Using Neural Networks for Classification in Actuarial Learning (2023) — link
and 38 more
  1. LocalGLMnet : interpretable deep learning for tabular data (2023) — link
  2. Entity Embeddings of Categorical Variables (2016) — link
  3. Embeddings for Tabular Data : A Survey (2023) — link
  4. Revisiting Deep Learning Models for Tabular Data (2021) — link
  5. On Embeddings for Numerical Features in Tabular Deep Learning (2022) — link
  6. A unified approach to interpreting model predictions (2017) — link
  7. Statistical foundations of actuarial learning and its applications (2023) — link
  8. Combined Actuarial Neural Networks in Actuarial Rate Making (2021) — link
  9. Neural network theory (2022) — link
  10. Attention is All you Need (2017) — link
  11. Why do tree-based models still outperform deep learning on typical tabular data? (2022) — link
  12. Believing the Bot - Model Risk in the Era of Deep Learning (2019) — link
  13. Generalized Linear Models (1972) — link
  14. Greedy Function Approximation : A Gradient Boosting Machine (2001) — link
  15. Generalized Linear Models (1983)
  16. Deep learning (2016)
  17. Generalized Additive Models (1986) — link
  18. Generalized Additive Models (1990)
  19. Deep Residual Learning for Image Recognition (2016) — link
  20. Bayesian Deep Net GLM and GLMM (2020) — link
  21. TabNet : Attentive Interpretable Tabular Learning (2021) — link
  22. TabPFN : A Transformer That Solves Small Tabular Classification Problems in a Second (2023) — link
  23. TabR : Unlocking the Power of Retrieval - Augmented Tabular Deep Learning (2023) — link
  24. Varying- Coefficient Models (1993) — link
  25. TabTransformer : Tabular Data Modeling Using Contextual Embeddings (2020) — link
  26. The Transformer Model in Equations — link
  27. CASdatasets : Insurance datasets (2018) — link
  28. Peeking into the Black Box : An Actuarial Case Study for Interpretable Machine Learning (2020) — link
  29. Case Study : French Motor Third - Party Liability Claims (2020) — link
  30. GLU Variants Improve Transformer (2020) — link
  31. Delving Deep into Rectifiers : Surpassing Human - Level Performance on ImageNet Classification (2015) — link
  32. The balance property in neural network modelling (2022) — link
  33. CASdatasets : Insurance datasets (2018) — link
  34. API design for machine learning software: experiences from the scikit-learn project (2013)
  35. Python 3 Reference Manual (2009)
  36. TensorFlow : Large-Scale Machine Learning on Heterogeneous Systems (2015) — link
  37. Optuna: A Next-generation Hyperparameter Optimization Framework (2019)
  38. A multi-task network approach for calculating discrimination-free insurance prices (2023) — link

0 of 46 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.