Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Causality from Bottom to Top: A Survey

Abraham Itzhak Weinberg, Cristiano Premebida, Diego Resende Faria

TL;DR

This survey tracks five decades of causality research and its integration with AI, ML, RL, GAI, and fuzzy logic. It clarifies distinctions between causality and correlation, presents core preconditions, architectures, and evaluation metrics. It catalogs major causal inference paradigms, their applications across domains, and the roles of trustworthiness and explainability. The paper also discusses challenges in big data, scalable causal discovery, and the need for human-centered, transparent causal AI.

Abstract

Causality has become a fundamental approach for explaining the relationships between events, phenomena, and outcomes in various fields of study. It has invaded various fields and applications, such as medicine, healthcare, economics, finance, fraud detection, cybersecurity, education, public policy, recommender systems, anomaly detection, robotics, control, sociology, marketing, and advertising. In this paper, we survey its development over the past five decades, shedding light on the differences between causality and other approaches, as well as the preconditions for using it. Furthermore, the paper illustrates how causality interacts with new approaches such as Artificial Intelligence (AI), Generative AI (GAI), Machine and Deep Learning, Reinforcement Learning (RL), and Fuzzy Logic. We study the impact of causality on various fields, its contribution, and its interaction with state-of-the-art approaches. Additionally, the paper exemplifies the trustworthiness and explainability of causality models. We offer several ways to evaluate causality models and discuss future directions.

Causality from Bottom to Top: A Survey

TL;DR

This survey tracks five decades of causality research and its integration with AI, ML, RL, GAI, and fuzzy logic. It clarifies distinctions between causality and correlation, presents core preconditions, architectures, and evaluation metrics. It catalogs major causal inference paradigms, their applications across domains, and the roles of trustworthiness and explainability. The paper also discusses challenges in big data, scalable causal discovery, and the need for human-centered, transparent causal AI.

Abstract

Causality has become a fundamental approach for explaining the relationships between events, phenomena, and outcomes in various fields of study. It has invaded various fields and applications, such as medicine, healthcare, economics, finance, fraud detection, cybersecurity, education, public policy, recommender systems, anomaly detection, robotics, control, sociology, marketing, and advertising. In this paper, we survey its development over the past five decades, shedding light on the differences between causality and other approaches, as well as the preconditions for using it. Furthermore, the paper illustrates how causality interacts with new approaches such as Artificial Intelligence (AI), Generative AI (GAI), Machine and Deep Learning, Reinforcement Learning (RL), and Fuzzy Logic. We study the impact of causality on various fields, its contribution, and its interaction with state-of-the-art approaches. Additionally, the paper exemplifies the trustworthiness and explainability of causality models. We offer several ways to evaluate causality models and discuss future directions.
Paper Structure (15 sections, 3 figures, 1 table)

This paper contains 15 sections, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Causality Characteristics and Uniqueness
  3. Causality Types, Relationships and Inference
  4. Causality Applications and Usages
  5. Preconditions and Architecture for Implementing Causality on Datasets
  6. Causality Evaluation and Metrics
  7. Causality Trustworthiness
  8. Causality and Explainable AI (XAI)
  9. Causality and Machine Learning (ML), AI, Genetic Algorithms (GA), and Generative AI (GAI) Approaches
  10. Causality and Bigdata
  11. Causality and Reinforcement Learning (RL)
  12. Integration between Causality, Machine and Deep Learning, and Genetic Algorithms
  13. Causality and Generative AI (GAI)
  14. Causality and Fuzzy Logic
  15. Conclusions and Future Directions

Figures (3)

  • Figure 1: Causality timeline with the key milestones over the last 50 years.
  • Figure 2: Main characteristics, as recognized by the relevant literature, that makes Causality distinguishable of other AI domains.
  • Figure 3: Causality Taxonomy based on seven representative categories: mechanism, direction, necessity, relationship, evidence, causes, and temporality.