Paper: arXiv 2307.16427

Authors: Satyam Kumar, Yelleti Vivek, Vadlamani Ravi, Indranil Bose

Abstract

Causal Inference plays an significant role in explaining the decisions taken by statistical models and artificial intelligence models. Of late, this field started attracting the attention of researchers and practitioners alike. This paper presents a comprehensive survey of 37 papers published during 1992-2023 and concerning the application of causal inference to banking, finance, and insurance. The papers are categorized according to the following families of domains: (i) Banking, (ii) Finance and its subdomains such as corporate finance, governance finance including financial risk and financial policy, financial economics, and Behavioral finance, and (iii) Insurance. Further, the paper covers the primary ingredients of causal inference namely, statistical methods such as Bayesian Causal Network, Granger Causality and jargon used thereof such as counterfactuals. The review also recommends some important directions for future research. In conclusion, we observed that the application of causal inference in the banking and insurance sectors is still in its infancy, and thus more research is possible to turn it into a viable method.

Complexity vs Empirical Score

  • Math Complexity: 6.0/10
  • Empirical Rigor: 2.0/10
  • Quadrant: Lab Rats — high math complexity, limited empirical testing

Why this score: The paper discusses advanced mathematical concepts like the Causal Hierarchy Theorem and graphical methods (e.g., Bayesian Networks) but is a survey with no implementation, backtests, or datasets, making it theoretical rather than empirical.

Research Flowchart

  flowchart TD
  A["Research Goal<br>Application of Causal Inference<br>in Banking, Finance & Insurance"] --> B["Methodology<br>Survey of 37 Papers (1992-2023)"]
  B --> C["Key Inputs<br>Bayesian Causal Network<br>Granger Causality<br>Counterfactuals"]
  C --> D["Computational Process<br>Categorization by Domain:<br>Banking, Finance, Insurance"]
  D --> E["Key Findings & Outcomes<br>Causal Inference in infancy<br>Future Research Directions"]

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Assumes 2

  • The Bayesian Network DAG satisfies the Markov condition: each variable is conditionally independent of its non‑descendants given its parents. statistical
    Source sentence
    Following are the 2 assumptions made about the DAG used in BN: (i) Markov condition: Given its parents, each variable X in G is conditionally independent of all its non-descendants.
  • The Bayesian Network DAG satisfies the Minimality condition: edges cannot be removed without losing conditional independencies. statistical
    Source sentence
    Owing to this condition, the joint probability distribution P(X) can be broken down as given in Eq. 6 (where Pa (Xi) are Xi's parents). 𝑃(𝑋𝑖) = ∏𝑋𝑖 𝑛 𝑖=1 (11) (ii) Minimality condition: Since P(X) does not contain a conditional independence; those edges cannot be removed from the DAG without the graph indicating one. 3.2.

Data

No dataset named in the text.

Costs

Not applicable The paper reports no trading or execution result.

Finds 3

  • The authors observe that the application of causal inference in the banking and insurance sectors is still in its infancy, indicating substantial room for further research. theoretical
    Source sentence
    In conclusion, we observed that the application of causal inference in the banking and insurance sectors is still in its infancy, and thus more research is possible to turn it into a viable method.
  • They note a dramatic rise in the development of causal‑inference‑based methodologies, especially in the past five years, to design robust mechanisms for BFSI problems. theoretical
    Source sentence
    Further, especially during the recent past five years, there is an dramatic rise in the development of causal inference-based methodologies, studying the counterfactuals, etc., to design a robust mechanism.
  • Using the proposed approach, advantages such as extracting local information from support regions and deriving a global model from local information were observed. other
    Source sentence
    Using this approach, following advantages were observed (i) extracts the local information by utilizing the support regions, (ii) the global model is derived by using the local information.

Checked by others

No other paper in the archive has been found to support or contradict these findings. Coverage is partial, so this is neither replication nor refutation.

Cited by 2 papers in the archive (2 by independent authors)

Code

No repository by the authors found in the paper.

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.