Association Action Rules and Action Paths Triggered by Meta-actions

Tzacheva, Angelina A.; Raś, Zbigniew W.

doi:10.1109/grc.2010.64

Cited by 23 publications

(17 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, we utilize Action Rules produced using distributed Action Rules extraction algorithm: MR-Random Forest [19] and SARGS [20]. We introduce a graph representation for Action Rules that we extracted called Action Graph.…”

Section: Condition(s) → Result(s)mentioning

confidence: 99%

In Search of Actionable Patterns of Lowest Cost - A Scalable Graph Method

Tzacheva¹,

Bagavathi²,

Datta³

2018

IJDMS

View full text Add to dashboard Cite

Action Rules are rule based systems for discovering actionable patterns which are hidden in a large dataset. All recommended patterns from Action Rules incur some form of cost to the users. It is obvious that recommendations are interesting to the users only if the cost that the user pays for the recommended actions is low. In other words, the recommendations should be profitable or valuable to the user when they perform a chain of actions, at the lowest possible cost. In the modern era of big data, organizations are collecting massive amounts of data, growing constantly. Finding low cost actionable patterns for such large data in these domains, is time consuming and requires a scalable approach. In this work, we introduce the notion of Action Graph and propose an algorithm to search the Action Graph for actionable patterns of lowest cost. We apply the proposed algorithm to three datasets in transportation, medical, and business domains. Results show how these domains can benefit from the discovered actionable recommendations of low cost.

show abstract

Section: Condition(s) → Result(s)mentioning

confidence: 99%

In Search of Actionable Patterns of Lowest Cost - A Scalable Graph Method

Tzacheva¹,

Bagavathi²,

Datta³

2018

IJDMS

View full text Add to dashboard Cite

show abstract

“…Tzacheva et al [14] also use the influence matrix for finding action paths which are a sequence of actions. Characteristic for these approaches is that they require background knowledge (the influence matrix) that is not learned from the data, but assumed to be known.…”

Section: Related Workmentioning

confidence: 99%

Causality-based cost-effective action mining

Shamsinejadbabaki

Saraee

Blockeel

2013

IDA

View full text Add to dashboard Cite

In many business contexts, the ultimate goal of knowledge discovery is not the knowledge itself, but putting it to use. Models or patterns found by data mining methods often require further post-processing to bring this about. For instance, in churn prediction, data mining may give a model that predicts which customers are likely to end their contract, but companies are not just interested in knowing who is likely to do so, they want to know what they can do to avoid this. The models or patterns have to be transformed into actionable knowledge. Action mining explicitly addresses this.Currently, many action mining methods rely on a predictive model, obtained through data mining, to estimate the effect of certain actions and finally suggest actions with desirable effects. A major problem with this approach is that predictive models do not necessarily reflect a causal relationship between their inputs and outputs. This makes the existing action mining methods less reliable. In this paper, we introduce ICE-CREAM, a novel approach to action mining that explicitly relies on an automatically obtained best estimate of the causal relationships in the data. Experiments confirm that ICE-CREAM performs much better than the current state of the art in action mining. P. Shamsinejadbabaki et al. / Causality-based cost-effective action miningis not merely interested in predicting which customers it is going to lose, it wants to know what can be done to avoid this.Action Mining (AM) is the process of learning action rules from data. Not much work has been done in this area up till now. Existing work includes Yang et al.'s method for learning actions from decision trees [2,3], and several versions of Ras et al.'s DEAR system for discovering action rules [4][5][6]. In all of these methods, input data is in the form of a set of attribute-value pairs for each object. Furthermore, a certain profit is associated with specific values of one particular attribute, called the target attribute. These methods then try to uncover existing associations between the target attribute and other attributes, and use these associations for finding the most beneficial actions. The main difference between these methods is in the technique by which they find associations. For example, Yang's method uses decision trees, while DEAR 2 uses classification rules.Despite all innovations presented in existing AM methods, they suffer from an important drawback: they implicitly rely on the assumption that the available models (decision trees, association rules) are causal. It is well-known from statistics that association or correlation does not imply causation. Even though the learned models do not merely express the existence of a correlation, but its nature (in the form of a predictive function), they suffer from the same problem. If a function f : X → Y learned from a data set is found to be accurate, this means that, when we observe X = x in a new object, we can accurately predict that Y = f (x); but if we manually change the object's X value to X = x , the...

show abstract

“…Now, we can use the sets A j,k to build the influence matrix [14,9] covering all m ∈ M . Sets of action terms representing meta-actions in M can be built from sets of pairs in P (S).…”

Section: It Should Be Observed That Any Pairmentioning

confidence: 99%

“…Meta-actions were formalized in [9], and used in a pruning process with tree classifiers to discover action rules. In [14] the authors show the cascading effect of meta-actions leading to a desired effects when generating association action rules and action paths. This work is slightly similar in the way we use the cascading effect of meta-action atomic terms to model the correlation with the action rule.…”

Section: Related Workmentioning

confidence: 99%

Mining Meta-Actions for Action Rules Reduction

Touati

Raś

2013

Fundamenta Informaticae

Self Cite

View full text Add to dashboard Cite

Meta-actions effect and selection are the fundamental core for a successful action rule execution. All atomic action terms on the left-hand side of an action rule have to be covered by well chosen meta-actions in order for it to be executed. The choice of meta-actions depends on the antecedent side of action rules; however, it also depends on their list of atomic actions that are outside of the action rule scope, seen as side effects. In this paper, we strive to minimize the side effects by decomposing the left-hand side of an action rule into executable action rules covered by a minimal number of meta-actions and resulting in a cascading effect. This process was tested and compared to original action rules. Experimental results show that side effects are diminished in comparison with the original meta-actions applied while keeping a good execution confidence. ding effect. This process was tested and compared to original action rules. Experimental results show that side effects are diminished in comparison with the original meta-actions applied while keeping a good execution confidence. between the objects' properties values transitions and the desired decision property values transition. This object property correlation results in a cascading effect that ultimately triggers a change in the decision value. Meta-actions are the triggers to those action rules and provide a tool to control their execution. They are represented by an influence matrix containing a set of attribute transitions they trigger. In most previous work, it is assumed that meta-actions are provided and ready to use. In addition, action rules are discovered and then chosen independently of the meta-actions. However, meta-actions are not commonly available in a ready to use format, and therefore they have to be mined and formatted. Action rules and their triggering meta-actions are interrelated and should be discovered together. In addition, meta-actions introduce negative side effects that might be harmful for the objects, and are not taken into consideration in the action rules discovery process. In other words, they provoke changes in objects attribute values that will not only trigger the actions rule targeted but also negative side effects. The negative side effects can damage the objects features outside of the executed action rule scope. Since the discovery process is bounded by the system in use, it is important to integrate the action rules and meta-actions discovery.In this paper we aim at connecting the action rules discovery process and meta action mining to reduce the negative side effects and improve the execution confidence of action rules. For this purpose, we propose a meta-action mining and evaluation process, and an action rules reduction method. The meta-action mining process is done through the study of expert knowledge treatments and their resulting effects. The action rules reduction connects the action rules to their meta-actions for a better action rule selection than the traditional action rule support and confidence se...

show abstract

Association Action Rules and Action Paths Triggered by Meta-actions

Cited by 23 publications

References 11 publications

In Search of Actionable Patterns of Lowest Cost - A Scalable Graph Method

In Search of Actionable Patterns of Lowest Cost - A Scalable Graph Method

Causality-based cost-effective action mining

Mining Meta-Actions for Action Rules Reduction

Contact Info

Product

Resources

About