76,030 Hits in 2.5 sec

Discovering Reliable Causal Rules [article]

Kailash Budhathoki, Mario Boley, Jilles Vreeken
2020 arXiv   pre-print
Moreover, to discover reliable causal rules from a sample, we propose a conservative and consistent estimator of the causal effect, and derive an efficient and exact algorithm that maximises the estimator  ...  Extensive experiments on a variety of real-world datasets show that the proposed algorithm is efficient and discovers meaningful rules.  ...  Discovering Rules Now that we have a reliable and consistent estimator of the causal effect, we turn to discovering rules that maximize this estimator.  ... 
arXiv:2009.02728v2 fatcat:55tf7htnfzgg3ogxvz5lbvfbmy

A Comparison of Association Rule Discovery and Bayesian Network Causal Inference Algorithms to Discover Relationships in Discrete Data [chapter]

Jeff Bowes, Eric Neufeld, Jim E. Greer, John Cooke
2000 Lecture Notes in Computer Science  
This work compares the effectiveness of causal inference algorithms with association rule induction for discovering patterns in discrete data.  ...  However, causal inference algorithms discover more concise relationships between variables, namely, relations of direct cause.  ...  As well, allocation of rules as the "head" or "body" of an association rule is also not reliable as an indicator of causal direction. confidence (B → H) = support(B ∪ H) / support(B).  ... 
doi:10.1007/3-540-45486-1_27 fatcat:licw7sezqvfavpjhzentnejoyq

Discovery of Causal Rules Using Partial Association

Zhou Jin, Jiuyong Li, Lin Liu, Thuc Duy Le, Bingyu Sun, Rujing Wang
2012 2012 IEEE 12th International Conference on Data Mining  
reliability of discovered causal rules.  ...  The results show that our method can effectively discover interesting causal rules in large databases.  ...  These causal rules represent a small set of statistically reliable relationships that are likely to embed cause and effect relationships.  ... 
doi:10.1109/icdm.2012.36 dblp:conf/icdm/JinL0LSW12 fatcat:iajmki3nvfbjzfizn4g7xz3oky

Discovering causal rules in relational databases

Floriana Esposito, Donato Malerba, Vincenza Ripa, Giovanni Semeraro
1997 Applied Artificial Intelligence  
This article explores the combined application of inductive learning algorithms and causal inference techniques to the problem of discovering causal rules among the attributes of a relational database.  ...  When the variables are discrete or have been discretized to test conditional independencies, supervised induction algorithms can be used to learn causal rules, that is, conditional statements in which  ...  y, such that the type of driving license is causally related to the reliability of the driver or Find all rules with support x and confidence y that explain why the driver has a high reliability.  ... 
doi:10.1080/088395197118352 fatcat:tzl77j3gufbyxietl2h7lwiusm

Inferring Implicit Rules by Learning Explicit and Hidden Item Dependency

Shoujin Wang, Longbing Cao
2017 IEEE Transactions on Systems, Man & Cybernetics. Systems  
Explicit relations have been substantially studied by rule mining-based approaches, including association rule mining and causal rule discovery.  ...  IRRMiner is applied to make recommendations and shows that the identified implicit rules can increase recommendation reliability.  ...  Association rule mining has recently been combined with a cohort study to discover causal association rules and has proven to be quite effective [33] .  ... 
doi:10.1109/tsmc.2017.2768547 fatcat:jeht4oslijhwdb4zvtduxqtqxi

Mining Causal Association Rules

Jiuyong Li, Thuc Duy Le, Lin Liu, Jixue Liu, Zhou Jin, Bingyu Sun
2013 2013 IEEE 13th International Conference on Data Mining Workshops  
In this paper we study how to use an efficient association mining approach to discover potential causal rules in observational data.  ...  Discovering causal relationships is the ultimate goal of many scientific explorations.  ...  However, they are reliable relationships since each causal rule is tested by the cohort study in data. Most discovered causal rules (99%) are short and include one or two variables.  ... 
doi:10.1109/icdmw.2013.88 dblp:conf/icdm/LiL0LJS13 fatcat:lyowshorxzcbhepmyuh4n2dpvm

Data Analytics and Mining in Healthcare with Emphasis on Causal Relationship Mining

2019 International journal of recent technology and engineering  
The present models for causality have limitations in terms of scalability and reliability. The present study is targeted to study causal models for causal relationship mining.  ...  This study tried to conclude with some proposals for causal relationship discovery which are efficient, reliable and scalable.  ...  Causal association rules are small in number, powerful, popular, useful, and reliable data relationships because each of the causal rules is tested by the cohort study in data.  ... 
doi:10.35940/ijrte.d6492.118419 fatcat:zkzif7glbvawhmqualnehr7se4

A Review on Algorithms for Constraint-based Causal Discovery [article]

Kui Yu, Jiuyong Li, Lin Liu
2016 arXiv   pre-print
Causal discovery studies the problem of mining causal relationships between variables from data, which is of primary interest in science.  ...  As a conclusion, some open problems in constraint-based causal discovery are outlined for future research.  ...  Instead of discovering the whole causal structure, this approach only studies direct causal relationships around a given target variable.  ... 
arXiv:1611.03977v2 fatcat:ercpfkqssnabfgdc3ndd7bd3tu

Finding Temporal Relations: Causal Bayesian Networks vs. C4.5 [chapter]

Kamran Karimi, Howard J. Hamilton
2000 Lecture Notes in Computer Science  
In this paper we apply TETRAD, a program that uses Bayesian networks to discover causal rules, and C4.5, which creates decision trees, to the problem of discovering relations among a set of variables in  ...  The rules in the domain are known, so we are able to assess the effectiveness of each method. The agent's sensings of its environment and its own actions are saved in data records over time.  ...  TETRAD [9] is a well-known causality miner that uses Bayesian networks [3] to find causal relations. One example of the type of rules discovered by TETRAD is x → y, which means that x causes y.  ... 
doi:10.1007/3-540-39963-1_28 fatcat:6wy7kirutverlbanqipnxuhkcm

Heuristic Mining Revamped: An Interactive, Data-aware, and Conformance-aware Miner

Felix Mannhardt, Massimiliano de Leoni, Hajo A. Reijers
2017 International Conference on Business Process Management  
visualized as described in literature, and (5) existing tools do not give reliable quality diagnostics for discovered models.  ...  It is the first tool that visualizes models using the concise Causal Net (C-Net) notation. We provide a walk-through of the iDHM by applying it to a large event log with hospital billing information.  ...  ., the event payload) are not used for process discovery; (4) discovered Causal Nets (C-Nets) are not visualized as described in literature; and (5) existing tools do not give reliable quality diagnostics  ... 
dblp:conf/bpm/MannhardtLR17 fatcat:3ea4ooyh3jguzaxqdvkkvc4hlu

Evaluation of the SRA Tool Using Data Mining Techniques

Andreas Gregoriades, Alistair G. Sutcliffe, Haralampos Karanikas
2003 International Conference on Advanced Information Systems Engineering  
The System Reliability Analyser (SRA) tool automates the process by iteratively manipulating the BBN model.  ...  Data mining techniques are employed in order to identify whether the initial assumptions embedded in the system reliability model are met by results from scenario-based testing.  ...  In our case we employ association rules in order to identify causal associations in our model.  ... 
dblp:conf/caise/GregoriadesSK03 fatcat:h4qnxtd53jhehmfsyzejhvvu5m

From Observational Studies to Causal Rule Mining

Jiuyong Li, Thuc Duy Le, Lin Liu, Jixue Liu, Zhou Jin, Bingyu Sun, Saisai Ma
2015 ACM Transactions on Intelligent Systems and Technology  
In this paper we propose the concept of causal rules (CRs) and develop an algorithm for mining CRs in large data sets.  ...  Specifically, association rule mining can be used to deal with the high-dimensionality problem while observational studies can be utilised to eliminate non-causal associations.  ...  the idea of cohort studies to obtain reliable causal rules based on the candidates.  ... 
doi:10.1145/2746410 fatcat:n3tlix2rijfihji6hes2ujrjs4

Mining Causal Relationships in Multidimensional Time Series [chapter]

Yasser Mohammad, Toyoaki Nishida
2010 Studies in Computational Intelligence  
The main feature of the proposed system is supporting discovery of causal relations based on automatically discovered recurring patterns in the input time series.  ...  The results show that the combined system can provide causality graphs representing the underlying relations between the human's actions and robot behavior that cannot be recovered using standard causal  ...  There are three categories of Bayesian Causal Network Induction algorithms that utilize different aspects of causality to discover causal rules.  ... 
doi:10.1007/978-3-642-04584-4_14 fatcat:6f4yettaazg6bpw2x3it7opnki

An Overview of Bayesian Network Applications in Uncertain Domains

Khalid Iqbal, Xu-Cheng Yin, Hong-Wei Hao, Qazi Mudassar Ilyas, Hazrat Ali
2015 Journal of clean energy technologies  
rule mining and medical domain analysis.  ...  Thus, the real application of BN can be observed in a broad range of domains such as image processing, decision making, system reliability estimation and PPDM (Privacy Preserving in Data Mining) in association  ...  The purpose of modifying the largest size transaction(s) is to keep the minimum perturbation to avoid generating new rules, ghost rules and lost rules with reliability.  ... 
doi:10.7763/ijcte.2015.v7.996 fatcat:qlhgx3kuevenxlvn3q5uu5lubu

Mining Relationship between Triggering and Consequential Events in a Short Transaction Database [chapter]

Chang-Hung Lee, Philip S. Yu, Ming-Syan Chen
2002 Proceedings of the 2002 SIAM International Conference on Data Mining  
determined by the first phase, i.e., the phase of discovering one-triggering causality rules.  ...  In this paper, we decompose the problem of mining causality rules into two phases, i.e., the phase of discovering one-triggering causality rules and the phase of generating multi-triggering causality rules  ... 
doi:10.1137/1.9781611972726.24 dblp:conf/sdm/LeeYC02 fatcat:jmlolqvdijevpd2jecxtdjm7na
« Previous Showing results 1 — 15 out of 76,030 results