Constraint-Based Rule Mining in Large, Dense Databases

@article{Bayardo2004ConstraintBasedRM,
  title={Constraint-Based Rule Mining in Large, Dense Databases},
  author={Roberto J. Bayardo and Rakesh Agrawal and Dimitrios Gunopulos},
  journal={Data Mining and Knowledge Discovery},
  year={2004},
  volume={4},
  pages={217-240}
}
Constraint-based rule miners find all rules in a given data-set meeting user-specified constraints such as minimum support and confidence. We describe a new algorithm that directly exploits all user-specified constraints including minimum support, minimum confidence, and a new constraint that ensures every mined rule offers a predictive advantage over any of its simplifications. Our algorithm maintains efficiency even at low supports on data that is dense (e.g. relational tables). Previous… 
Mining Interesting Imperfectly Sporadic Rules
TLDR
This paper introduces an algorithm called MIISR to find a particular type of sporadic rule efficiently: where the support of the antecedent as a whole falls below maximum support, but where items may have quite high support individually.
uCFS2: an enhanced system that mines uncertain data for constrained frequent sets
TLDR
This paper extends a tree-based system to mine uncertain data for frequent sets that satisfy succinct as well as non-succinct constraints by effectively exploiting properties of these constraints.
An Efficient Algorithm for Mining Frequent Itemsets with Single Constraint
TLDR
This paper proposes a unique representation of frequent itemsets restricted on constraint C0 using closed frequent itemset lattice and generators and develops the efficient algorithm to quickly and non-repeatedly generate all frequent itemets contain C0.
Efficient mining for frequent itemsets with multiple convertible constraints
  • Bao-Lisong, Zhen Qin
  • Computer Science
    2005 International Conference on Machine Learning and Cybernetics
  • 2005
TLDR
This paper studies multiple convertible constraints and develops technique which enable them to be readily pushed deep inside a algorithm for frequent itemsets mining.
Reducing Rule Covers with Deterministic Error Bounds
TLDR
This paper proposes a new framework, namely, the generalized closed (or g-closed) itemset framework, and shows that the number of such redundant rules is far more than what was previously estimated.
Likely-Occurring Itemsets for Pattern Mining
TLDR
The notion of likely-occurring itemsets is introduced and a greedy approach to itemset search space discovery is proposed that allows for reducing the number of arbitrary or closed itemsets.
An efficient algorithm for generating association rules by using constrained itemsets mining
  • A. Kaur, V. Aggarwal, S. Shankar
  • Computer Science
    2016 IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT)
  • 2016
TLDR
Proposed algorithm prunes all uninteresting frequent itemsets generated in every level and only considers those items and rules which are of interest based on MST and MCT.
Mining Association Rules Restricted on Constraint
  • Anh N. Tran, Tin C. Truong, H. Le, Hai V. Duong
  • Mathematics, Computer Science
    2012 IEEE RIVF International Conference on Computing & Communication Technologies, Research, Innovation, and Vision for the Future
  • 2012
TLDR
The aim of this paper is to solve the problem of mining association rule restricted on a given constraint itemset which often changes and the theoretical affirmations and experimental results prove that the approach is very efficient and close to user.
Confidence-based Concept Discovery in Multi-Relational Data Mining
TLDR
A new ILP-based con- cept discovery method is described in which user- defined specifications are relaxed and this new method directly works on relational databases.
K-Optimal Rule Discovery
TLDR
This paper presents a scalable algorithm applicable to a wide range of K-optimal rule discovery tasks and demonstrates its efficiency.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 41 REFERENCES
Mining Association Rules with Item Constraints
TLDR
This work considers the problem of integrating constraints that are Boolean expressions over the presence or absence of items into the association discovery algorithm and presents three integrated algorithms for mining association rules with item constraints and discusses their tradeoffs.
Mining the most interesting rules
TLDR
It is argued that by returning a broader set of rules than previous algorithms, these techniques allow for improved insight into the data and support more user-interaction in the optimized rule-mining process.
New Algorithms for Fast Discovery of Association Rules
TLDR
New algorithms for fast association mining, which scan the database only once, are presented, addressing the open question whether all the rules can be efficiently extracted in a single database pass.
Exploratory mining and pruning optimizations of constrained associations rules
TLDR
An architecture that opens up the black-box, and supports constraint-based, human-centered exploratory mining of associations, and introduces and analyzes two properties of constraints that are critical to pruning: anti-monotonicity and succinctness.
Pincer-Search: A New Algorithm for Discovering the Maximum Frequent Set
TLDR
This work presents a new algorithm which combines both the bottom-up and top-down searches, and produces the maximum frequent set, i.e., the set containing all maximal frequent itemsets, which therefore specifies immediately all frequent itemets.
An Efficient Algorithm for Mining Association Rules in Large Databases
TLDR
This paper presents an efficient algorithm for mining association rules that is fundamentally different from known algorithms and not only reduces the I/O overhead significantly but also has lower CPU overhead for most cases.
Brute-Force Mining of High-Confidence Classification Rules
TLDR
An association rule miner enhanced with new pruning strategies to control combinatorial explosion in the number of candidates counted with each database pass effectively and efficiently extracts high confidence classification rules that apply to most if not all of the data in several classification benchmarks.
Abstract-Driven Pattern Discovery in Databases
TLDR
Methods are presented for discovering interesting patterns based on abstracts which are summaries of the data expressed in the language of the user, including relational views and classification hierarchies.
Fast algorithms for mining association rules
TLDR
Two new algorithms for solving thii problem that are fundamentally different from the known algorithms are presented and empirical evaluation shows that these algorithms outperform theknown algorithms by factors ranging from three for small problems to more than an order of magnitude for large problems.
Mining association rules between sets of items in large databases
TLDR
An efficient algorithm is presented that generates all significant association rules between items in the database of customer transactions and incorporates buffer management and novel estimation and pruning techniques.
...
1
2
3
4
5
...