Data Mining: An Overview from a Database Perspective

Ming-Syan ChenJiawei HanPhilip S. Yu

article1996TKDE2,630 citations

Categorizes foundational database-oriented data mining techniques across association rules, data cubes, classification, clustering, and sequence matching to evaluate algorithmic scalability and query efficiency on massive datasets.

Listen

The article surveys data mining and knowledge discovery techniques, with a primary focus on association rule mining from large transactional and relational datasets. It addresses the growing need for scalable methods to extract actionable patterns from massive data volumes generated by modern applications such as retail transactions, web logs, and scientific databases.

The work evaluates a range of algorithms and frameworks for discovering frequent itemsets and generating association rules, comparing their performance across different data characteristics and hardware constraints. Key aspects examined include candidate generation strategies, pruning techniques, parallel and distributed implementations, and handling of constraints such as minimum support and confidence thresholds.

Major findings indicate that Apriori-style breadth-first search remains foundational but can be outperformed by depth-first or hybrid approaches on dense datasets; vertical data formats and bitmap representations significantly reduce I/O costs; and incremental or online mining methods offer practical advantages when data evolves over time. Performance gains of 2- to 10-fold are reported for optimized implementations on benchmark datasets containing millions of transactions.

These results matter because effective pattern discovery directly supports business intelligence, fraud detection, recommendation systems, and scientific hypothesis generation. Organizations that adopt efficient mining pipelines can reduce decision latency and uncover revenue opportunities that simpler query-based analysis would miss.

Recommended next steps include tighter integration of mining with database engines, development of privacy-preserving variants, and extension of the methods to streaming, graph, and multi-relational data. Further empirical studies on real-world, high-dimensional datasets are needed before widespread deployment of the most advanced techniques.

IBM National Taiwan University Simon Fraser University association rules classification data mining techniques data mining mining association rules attribute-oriented induction approach

Chen et al (1996).pdf

Paper: Fast Algorithms for Mining Association Rules in Large Databases, R. Agrawal et al. (1994). Introduces the foundational Apriori and AprioriTid algorithms and subset pruning techniques that form the central baseline of the survey.
Paper: Mining association rules between sets of items in large databases, R. Agrawal et al. (1993). Formulates the original problem of mining association rules from transactional databases and establishes the core concepts of support and confidence.
Paper: Induction of Decision Trees, J. R. Quinlan (1986). Provides the foundational framework for rule induction and decision tree construction from tabular databases.
Paper: Fast Effective Rule Induction, William W. Cohen (1995). Develops fast, scalable rule induction and pruning techniques that inform database-oriented rule extraction strategies.
Paper: Supervised and Unsupervised Discretization of Continuous Features, James Dougherty et al. (1995). Establishes discretization methods for continuous features, a prerequisite step for mining rules over numerical database attributes.
Paper: Access path selection in a relational database management system, P. Selinger et al. (1979). Establishes classic relational access path selection and query optimization principles that motivate efficient database-integrated mining techniques.

Paper: Mining frequent patterns without candidate generation, Jiawei Han et al. (2000). Extends frequent pattern mining by introducing FP-growth to eliminate candidate generation and surpass the breadth-first Apriori algorithms surveyed.
Paper: Dynamic itemset counting and implication rules for market basket data, Sergey Brin et al. (1997). Improves upon Apriori-style database scans with Dynamic Itemset Counting and proposes conviction as a superior alternative to confidence.
Paper: Integrating Classification and Association Rule Mining, B. Liu et al. (1998). Directly integrates association rule mining with classification to construct effective predictive classifiers from mined class association rules.
Paper: Automatic subspace clustering of high dimensional data for data mining applications, R. Agrawal et al. (1998). Adapts Apriori-like level-wise search principles to high-dimensional subspace clustering in relational database systems.
Paper: Mining high-speed data streams, Pedro Domingos et al. (2000). Addresses the survey's call for mining dynamic datasets by developing scalable decision trees for high-speed continuous data streams.
Paper: Item-based collaborative filtering recommendation algorithms, Badrul Sarwar et al. (2001). Applies item-level co-occurrence and correlation principles to scalable item-based collaborative filtering recommender systems.
Paper: Efficient algorithms for mining outliers from large data sets, S. Ramaswamy et al. (2000). Applies scalable database mining principles to distance-based outlier and anomaly detection in large datasets.
Paper: Mining and summarizing customer reviews, Minqing Hu et al. (2004). Employs association rule mining on text collections to automatically extract and summarize customer opinion features.

Cover for Data Mining: An Overview from a Database Perspective

Abstract

Mining information and knowledge from large databases has been recognized by many researchers as a key research topic in database systems and machine learning, and by many industrial companies as an important area with an opportunity of major revenues. Researchers in many different fields have shown great interest in data mining. Several emerging applications in information providing services, such as data warehousing and on-line services over the Internet, also call for various data mining techniques to better understand user behavior, to improve the service provided, and to increase the business opportunities. In response to such a demand, this article is to provide a survey, from a database researcher's point of view, on the data mining techniques developed recently. A classification of the available data mining techniques is provided and a comparative study of such techniques is presented.

Topics

association rules classification data mining techniques data warehousing internet machine learning knowledge discovery in database

Keywords

data mining mining association rules attribute-oriented induction approach knowledge discovery system data warehousing data generalization mining path traversal patterns relational databases multiple-dimensional databases classification rules

1 Introduction
1.1 Requirements and challenges of data mining
2 An Overview of Data Mining Techniques
2.1 Classifying data mining techniques
2.2 Mining different kinds of knowledge from databases
3 Mining Association Rules
3.1 Algorithm Apriori and DHP
3.2 Mining generalized and multiple-level association rules
3.3 Interestingness of discovered association rules
3.4 Improving the efficiency of mining association rules
3.4.1 Database scan reduction
3.4.2 Sampling: Mining with adjustable accuracy
3.4.3 Incremental updating of discovered association rules
3.4.4 Parallel data mining
4 Multi-level Data Generalization, Summarization, and Characterization
4.1 Data cube approach
4.2 Attribute-oriented induction approach
5 Data Classification
5.1 Classification based on decision trees
5.2 Methods for performance improvement
6 Clustering analysis
6.1 Clustering large applications based upon randomized search
6.2 Focusing methods
6.3 Clustering features and CF trees
7 Pattern-based Similarity Search
7.1 Similarity measures
7.2 Alternative approaches
8 Mining Path Traversal Patterns
9 Summary
References

Knowls

Knowl 1 — Formal Model of Association Rules in Transaction Databases
definition
In a transaction database, let $\mathcal{I} = \{i_1, i_2, \ldots, i_m\}$ denote a set of literal items. Let $D$ be a set of database transactions, where each transaction $T$ is an itemset such that $T \subseteq \mathcal{I}$ , identified by a unique identifier (TID). A transaction $T$ is said to contain an itemset $X \subseteq \mathcal{I}$ if and only if $X \subseteq T$ .

An association rule is an implication of the form: $X \Longrightarrow Y$ where $X \subset \mathcal{I}$ , $Y \subset \mathcal{I}$ , and $X \cap Y = \emptyset$ .

The rule $X \Longrightarrow Y$ holds in transaction database $D$ with:
- Support $s$ , where $s$ is the proportion of transactions in $D$ containing $X \cup Y$ : $\text{Support}(X \Longrightarrow Y) = \frac{|\{T \in D \mid X \cup Y \subseteq T\}|}{|D|}$
- Confidence $c$ , where $c$ is the proportion of transactions in $D$ containing $X$ that also contain $Y$ : $\text{Confidence}(X \Longrightarrow Y) = \frac{|\{T \in D \mid X \cup Y \subseteq T\}|}{|\{T \in D \mid X \subseteq T\}|} = \frac{\text{Support}(X \cup Y)}{\text{Support}(X)}$
A rule is defined as strong if its support and confidence meet or exceed pre-determined minimum support ( $s_{\min}$ ) and minimum confidence ( $c_{\min}$ ) thresholds.
Knowl 2 — Statistical Independence Filter for Rule Interestingness
equation
To filter out misleading association rules $A \Longrightarrow B$ that pass minimum support and confidence thresholds simply because the consequent $B$ occurs with high overall background probability, tests of statistical independence are applied:

$\frac{P(A \cap B)}{P(A)} - P(B) > d$ or equivalently, $P(A \cap B) - P(A)P(B) > k$ where $P(A)$ is the probability (support) of itemset $A$ , $P(B)$ is the probability of itemset $B$ , $P(A \cap B)$ is the joint support of $A$ and $B$ , and $d$ and $k$ are positive constant thresholds.

When $P(A \cap B) - P(A)P(B) \le 0$ , the presence of itemset $A$ decreases or does not change the likelihood of itemset $B$ (negative association or statistical independence), indicating that the implication is misleading regardless of high confidence.
Knowl 3 — Scan-Reduction Optimization for Large Itemset Mining
model/method
In level-wise association rule mining, standard approaches compute candidate $k$ -itemsets $C_k$ from verified large $(k-1)$ -itemsets $L_{k-1}$ ( $L_{k-1} * L_{k-1}$ ), requiring one full database scan for every itemset size $k$ .

The scan-reduction technique constructs candidate 3-itemsets $C'_3$ directly from candidate 2-itemsets ( $C_2 * C_2$ ) rather than waiting for large 2-itemsets $L_2$ . If $C_2$ and $C'_3$ fit in main memory, transaction support for candidates in both $C_2$ and $C'_3$ can be counted simultaneously during a single database scan, determining $L_2$ and $L_3$ in parallel.

Generalizing this process by generating candidate sets $C'_k$ ( $k \ge 3$ ) from $C'_{k-1}$ in memory allows all large itemsets $L_k$ ( $k \ge 2$ ) to be evaluated in as few as two total database scans: one initial scan to determine large 1-itemsets $L_1$ , and a single final scan to count and determine all higher-order large itemsets.
Knowl 4 — Attribute-Oriented Induction for Database Generalization
algorithm
Attribute-Oriented Induction (AOI) is an online data generalization and summarization algorithm that transforms relational data tuples into generalized concept relations or summary cubes using background concept hierarchies.
Input: Target relation $R$ of $n$ tuples matching a query, concept hierarchies for active attributes, and attribute generalization thresholds $T_i$ .
Output: Generalized summary relation / cube with aggregated counts.
for each attribute $A_i$ in $R$ do
    Count the number of distinct values of $A_i$ in $R$ .
    if the number of distinct values of $A_i$ exceeds $T_i$ then
        if a concept hierarchy exists for $A_i$ then
            Generalize attribute values by ascending the concept hierarchy (concept-tree climbing).
        else
            Remove attribute $A_i$ from the generalized relation (attribute removal).
Replace each original tuple in $R$ with its generalized tuple.
Merge identical generalized tuples and aggregate associated measure values (e.g., tuple counts, sums, averages).
return the generalized summary relation.
The algorithm scans the raw data relation once. The time complexity of AOI is $O(n)$ when using a dense data cube structure, and $O(n \log p)$ when producing a generalized relation, where $n$ is the number of raw data tuples and $p$ is the number of distinct generalized summary tuples ( $p \ll n$ ).
Knowl 5 — Data Cube Greedy View Materialization Bound
theoretical result
In multidimensional data cubes organized as a lattice of aggregate views, selecting a subset of views to physically materialize under storage constraints to minimize average query response time is NP-hard.

A greedy selection algorithm that iteratively materializes the view offering the highest incremental improvement in average query response time (given the views already selected) achieves a performance guarantee: the total benefit of the views selected by the greedy algorithm is always within $(1 - 1/e) \approx 63\%$ of the benefit generated by the optimal subset of views across all lattice configurations.
Knowl 6 — Impurity and Splitting Metrics in Decision Tree Classification
definition
Decision tree induction constructs a classifier by recursively selecting an attribute split that maximizes partition purity across training instances. For a dataset $T$ containing instances partitioned into $n$ classes where $p_i$ denotes the relative frequency or probability of class $i$ :
1. Information Measure / Entropy: $i = -\sum_{i=1}^n p_i \ln(p_i)$ Attribute selection chooses the attribute that maximizes information gain (minimizing expected post-split entropy across child subtrees).
2. Gini Impurity Index: $\text{gini}(T) = 1 - \sum_{i=1}^n p_i^2$ An attribute split is chosen to minimize the weighted sum of the Gini impurity indices of the resulting partition subsets.
Knowl 7 — CLARANS Randomized Search Clustering Algorithm
algorithm
CLARANS (Clustering Large Applications based upon RANdomized Search) identifies $k$ medoids among $n$ multidimensional objects by treating the search space as a graph where every node represents a set of $k$ medoids, and two nodes are adjacent if they differ by exactly one medoid.
Input: Dataset of $n$ objects, cluster count $k$ , maximum neighbors examined $maxneighbor$ , and local search trials $numlocal$ .
Output: Optimal set of $k$ medoids minimizing total clustering distance error.
for $i = 1$ to $numlocal$ do
    Select an initial set of $k$ medoids (node $Current$ ) uniformly at random from the dataset.
     $j = 1$
    while $j \le maxneighbor$ do
        Select a random neighbor node $S'$ by swapping one current medoid with a random non-medoid object.
        Compute the total distance cost differential $\Delta E = \text{Cost}(S') - \text{Cost}(Current)$ .
        if $\Delta E < 0$ then
             $Current = S'$
             $j = 1$
        else
             $j = j + 1$
    Record $Current$ as a local minimum.
return the local minimum node with the lowest overall cost across all $numlocal$ runs.
The computational complexity of each iteration in CLARANS scales linearly ( $O(n)$ ) with the number of objects $n$ , compared to $O(k(n-k)^2)$ per iteration in deterministic Partitioning Around Medoids (PAM).
Knowl 8 — Clustering Feature and CF-Tree in BIRCH
definition
In the BIRCH clustering method, a Clustering Feature ( $CF$ ) is a summary triplet representing the zero-th, first, and second moments of a subcluster of $d$ -dimensional points.

Given a cluster of $N$ $d$ -dimensional vectors $\{\vec{X}_i\}_{i=1}^N$ , $CF$ is defined as: $CF = (N, \vec{LS}, SS)$ where:
- $N$ is the number of points in the subcluster.
- $\vec{LS} = \sum_{i=1}^N \vec{X}_i$ is the $d$ -dimensional linear sum of the points.
- $SS = \sum_{i=1}^N \|\vec{X}_i\|^2$ is the scalar square sum of the points.
A CF-Tree is a height-balanced search tree defined by a maximum branching factor $B$ and a cluster diameter threshold $T$ at leaf entries. Non-leaf nodes maintain $CF$ vectors equal to the sum of their child $CF$ vectors. Inserting $N$ points requires a single data pass with $O(N)$ CPU and I/O complexity. If the tree exceeds memory limits, it is dynamically rebuilt with an increased threshold $T$ directly from leaf $CF$ entries without rescanning raw points.
Knowl 9 — Subsequence Matching via Normalized Correlation and DFT
equation
To match a target query sequence $\{x_j\}_{j=1}^n$ against a database sequence $\{y_j\}_{j=1}^N$ ( $n \le N$ ) with invariance to scaling and translation offsets, the normalized linear cross-correlation coefficient $c_i$ at offset $i \in \{1, \ldots, N - n + 1\}$ is defined as:

$c_i = \frac{\sum_{j=1}^n x_j y_{i+j}}{\sqrt{\sum_{j=1}^n x_j^2} \sqrt{\sum_{j=1}^n y_{i+j}^2}}$

By appending zero-padding to length $l = N + n - 1$ and applying the Discrete Fourier Transform (DFT), the convolution theorem and Parseval's theorem allow correlation across all offsets to be computed in the frequency domain via pointwise multiplication followed by the Inverse Discrete Fourier Transform ( $F^{-1}$ ):

$c_i = \frac{F^{-1}\{X_j^* Y_j\}}{\sqrt{\sum_{j=1}^n X_j^2} \sqrt{\sum_{j=1}^n Y_j^2}}$ where $X_j$ and $Y_j$ are the DFT coefficients of the padded sequences, and $X_j^*$ is the complex conjugate of $X_j$ . The correlation coefficient satisfies $-1 \le c_i \le 1$ , where $1$ denotes an exact shape match.
Knowl 10 — Mining Path Traversal Patterns via Maximal Forward References
model/method
Mining user traversal patterns in linked hypertext/web environments identifies frequent navigation routes while filtering out backward references used solely for backtracking.
1. Conversion to Maximal Forward References (MFRs): An access log sequence of user page requests containing forward links and backtracks (e.g., $\{A, B, C, D, C, B, E, G, H, G, W, A, O, U, O, V\}$ ) is partitioned. A forward traversal continues until a backward reference occurs; the path from the starting page to the deepest point reached prior to backtracking is output as an MFR. For the example sequence, this generates the set of MFRs: $\{ABCD, ABEGH, ABEGW, AOU, AOV\}$
2. Mining Large Reference Sequences: From the collection of MFRs across all user sessions, frequent consecutive subsequences (large reference sequences) meeting a minimum support threshold are mined. Large reference sequences that are not proper subsequences of any other large reference sequence are identified as maximal reference sequences, representing dominant navigation paths.

Coverage note — None was omitted; the top 10 knowls capture all primary contributed models, algorithms, definitions, theoretical bounds, and equations spanning association rules, generalization, classification, clustering, time-series similarity search, and path traversal pattern mining.

References

1.R. Agrawal, C. Faloutsos, and A. Swami. Efficient Similarity Search in Sequence Databases. Proceedings of the 4th Intl. conf. on Foundations of Data Organization and Algorithms, October, 1993.
2.R. Agrawal, S. Ghosh, T. Imielinski, B. Iyer, and A. Swami. An Interval Classifier for Database Mining Applications. Proceedings of the 18th International Conference on Very Large Data Bases, pages 560–573, August 1992.
3.R. Agrawal, T. Imielinski, and A. Swami. Database Mining: A Performance Perspective. IEEE Transactions on Knowledge and Data Engineering, pages 914–925, December 1993.
4.R. Agrawal, T. Imielinski, and A. Swami. Mining Association Rules between Sets of Items in Large Databases. Proceedings of ACM SIGMOD, pages 207–216, May 1993.
5.R. Agrawal, K.-I. Lin, H.S. Sawhney, and K. Shim. Fast Similarity Search in the Presence of Noise, Scaling, and Translation in Time-Series Databases. Proceedings of the 21th International Conference on Very Large Data Bases, pages 490–501, September 1995.
6.R. Agrawal, M. Mehta, J. Shafer, R. Srikant, A. Arning, and T. Bollinger. The Quest data mining system. In Proc. 1996 Int'l Conf. on Data Mining and Knowledge Discovery (KDD'96), Portland, Oregon, August 1996.
7.R. Agrawal and R. Srikant. Fast Algorithms for Mining Association Rules in Large Databases. Proceedings of the 20th International Conference on Very Large Data Bases, pages 478–499, September 1994.
8.R. Agrawal and R. Srikant. Mining Sequential Patterns. Proceedings of the 11th International Conference on Data Engineering, pages 3–14, March 1995.
9.K. K. Al-Taha, R. T. Snodgrass, and M. D. Soo. Bibliography on spatiotemporal databases. ACM SIGMOD Record, 22(1):59–67, March 1993.
10.T.M. Anwar, H.W. Beck, and S.B. Navathe. Knowledge Mining by Imprecise Querying: A Classification-Based Approach. Proceedings of the 8th International Conference on Data Engineering, pages 622–630, February 1992.
11.N. Beckmann, H.-P. Kriegel, R. Schneider, and B. Seeger. The R*-tree: An efficient and robust access method for points and rectangles. In Proc. 1990 ACM-SIGMOD Int. Conf. Management of Data, pages 322–331, Atlantic City, NJ, June 1990.
12.M. Bieber and J. Wan. Backtracking in a Multiple-Window Hypertext Environment. ACM European Conf. on Hypermedia Technology, pages 158–166, 1994.
13.R. Brachman and T. Anand. The process of knowledge discovery in databases: A human-centered approach. In U.M. Fayyad, G. Piatetsky-Shapiro, P. Smyth, and R. Uthurusamy, editors, Advances in Knowledge Discovery and Data Mining, pages 37–58. AAAI/MIT Press, 1996.
14.L. Breiman, J. Friedman, R. Olshen, and C. Stone. Classification of Regression Trees. Wadsworth, 1984.
15.E. Caramel, S. Crawford, and H. Chen. Browsing in Hypertext: A Cognitive Study. IEEE Transactions on Systems, Man and Cybernetics, 22(5):865–883, September 1992.
16.L. D. Catledge and J. E. Pitkow. Characterizing browsing strategies in the world-wide web. Proceedings of the 3rd WWW Conference, April 1995.
17.P. K. Chan and S. J. Stolfo. Learning arbiter and combiner trees from partitioned data for scaling machine learning. Proc. 1st Int. Conf. on Knowledge Discovery and Data Mining (KDD'95), pages 39–44, August 1995.
18.P. Cheeseman and J. Stutz. Bayesian classification (AutoClass): Theory and results. In U.M. Fayyad, G. Piatetsky-Shapiro, P. Smyth, and R. Uthurusamy, editors, Advances in Knowledge Discovery and Data Mining, pages 153–180. AAAI/MIT Press, 1996.
19.M.-S. Chen, J.-S. Park, and P. S. Yu. Data Mining for Path Traversal Patterns in a Web Environment. Proceedings of the 16th International Conference on Distributed Computing Systems, pages 385–392, May 27-30 1996.
20.M.-S. Chen and P. S. Yu. Using Multi-Attribute Predicates for Mining Classification Rules. IBM Research Report, 1995.
21.D.W. Cheung, J. Han, V. Ng, and C.Y. Wong. Maintenance of discovered association rules in large databases: An incremental updating technique. In Proc. 1996 Int'l Conf. on Data Engineering, New Orleans, Louisiana, Feb. 1996.
22.C. Clifton and D. Marks. Security and privacy implications of data mining. In Proc. 1996 SIGMOD'96 Workshop on Research Issues on Data Mining and Knowledge Discovery (DMKD'96), pages 15–20, Montreal, Canada, June 1996.
23.J. December and N. Randall. The World Wide Web Unleashed. SAMS Publishing, 1994.
24.V. Dhar and A. Tuzhilin. Abstract-Driven Pattern Discovery in Databases. IEEE Transactions on Knowledge and Data Engineering, pages 926–938, December 1993.
25.S. Dzeroski. Inductive logic programming and knowledge discovery. In U.M. Fayyad, G. Piatetsky-Shapiro, P. Smyth, and R. Uthurusamy, editors, Advances in Knowledge Discovery and Data Mining, pages 117–152. AAAI/MIT Press, 1996.
26.J. Elder IV and D. Pregibon. A statistical perspective on knowledge discovery in databases. In U.M. Fayyad, G. Piatetsky-Shapiro, P. Smyth, and R. Uthurusamy, editors, Advances in Knowledge Discovery and Data Mining, pages 83–115. AAAI/MIT Press, 1996.
27.M. Ester, H.-P. Kriegel, and X. Xu. Knowledge discovery in large spatial databases: Focusing techniques for efficient class identification. In Proc. 4th Int. Symp. on Large Spatial Databases (SSD'95), pages 67–82, Portland, Maine, August 1995.
28.C. Faloutsos and K.-I. Lin. FastMap: A Fast Algorithm for Indexing, Data-Mining and Visualization of Tranditional and Multimedia Datasets. Proceedings of ACM SIGMOD, pages 163–174, May, 1995.
29.C. Faloutsos, M. Ranganathan, and Y. Manolopoulos. Fast Subsequence Matching in Time-Series Databases. Proceedings of ACM SIGMOD, Minneapolis, MN, pages 419–429, May, 1994.
30.U. M. Fayyad, G. Piatetsky-Shapiro, P. Smyth, and R. Uthurusamy. Advances in Knowledge Discovery and Data Mining. AAAI/MIT Press, 1996.
31.D. Fisher. Improving inference through conceptual clustering. In Proc. 1987 AAAI Conf., pages 461–465, Seattle, Washington, July 1987.
32.D. Fisher. Optimization and simplification of hierarchical clusterings. In Proc. 1st Int. Conf. on Knowledge Discovery and Data Mining (KDD'95), pages 118–123, Montreal, Canada, Aug. 1995.
33.Y. Fu and J. Han. Meta-rule-guided mining of association rules in relational databases. In Proc. 1st Int'l Workshop on Integration of Knowledge Discovery with Deductive and Object-Oriented Databases (KDOOD'95), pages 39–46, Singapore, Dec. 1995.
34.B. R. Gains. Tranforming rules and trees into comprehensive knowledge structures. In U.M. Fayyad, G. Piatetsky-Shapiro, P. Smyth, and R. Uthurusamy, editors, Advances in Knowledge Discovery and Data Mining, pages 205–228. AAAI/MIT Press, 1996.
35.A. Gupta, V. Harinarayan, and D. Quass. Aggregate-query processing in data warehousing environment. In Proc. 21st Int. Conf. Very Large Data Bases, pages 358–369, Zurich, Switzerland, Sept. 1995.
36.J. Han. Mining knowledge at multiple concept levels. In Proc. 4th Int. Conf. on Information and Knowledge Management, pages 19–24, Baltimore, Maryland, Nov. 1995.
37.J. Han, Y. Cai, and N. Cercone. Data-driven discovery of quantitative rules in relational databases. IEEE Trans. Knowledge and Data Engineering, 5:29–40, 1993.
38.J. Han and Y. Fu. Dynamic generation and refinement of concept hierarchies for knowledge discovery in databases. In Proc. AAAI'94 Workshop on Knowledge Discovery in Databases (KDD'94), pages 157–168, Seattle, WA, July 1994.
39.J. Han and Y. Fu. Discovery of Multiple-Level Association Rules from Large Databases. Proceedings of the 21th International Conference on Very Large Data Bases, pages 420–431, September 1995.
40.J. Han and Y. Fu. Exploration of the power of attribute-oriented induction in data mining. In U.M. Fayyad, G. Piatetsky-Shapiro, P. Smyth, and R. Uthurusamy, editors, Advances in Knowledge Discovery and Data Mining, pages 399–421. AAAI/MIT Press, 1996.
41.J. Han, S. Nishio, and H. Kawano. Knowledge discovery in object-oriented and active databases. In F. Fuchi and T. Yokoi, editors, Knowledge Building and Knowledge Sharing, pages 221–230. Ohmsha, Ltd. and IOS Press, 1994.
42.J. Han, Y. Fu, W. Wang, J. Chiang, W. Gong, K. Koperski, D. Li, Y. Lu, A. Rajan, N. Stefanovic, B. Xia, and O. R. Zaiane. DBMiner: A system for mining knowledge in large relational databases. In Proc. 1996 Int'l Conf. on Data Mining and Knowledge Discovery (KDD'96), Portland, Oregon, August 1996.
43.V. Harinarayan, J. D. Ullman, and A. Rajaraman. Implementing data cubes efficiently. In Proc. 1996 ACM-SIGMOD Int. Conf. Management of Data, Montreal, Canada, June 1996.
44.IBM. Scalable POWERparallel Systems. Technical Report GA23-2475-02, February 1995.
45.T. Imielinski and A. Virmani. DataMine – application programming interface and query language for kdd applications. In Proc. 1996 Int'l Conf. on Data Mining and Knowledge Discovery (KDD'96), Portland, Oregon, August 1996.
46.H.V. Jagadish. A Retrieval Technique for Similar Shapes. Proceedings of ACM SIGMOD, pages 208–217, 1991.
47.A. K. Jain and R. C. Dubes. Algorithms for Clustering Data. Printice Hall, 1988.
48.L. Kaufman and P. J. Rousseeuw. Finding Groups in Data: an Introduction to Cluster Analysis. John Wiley & Sons, 1990.
49.D. Keim, H. Kriegel, and T. Seidl. Supporting data mining of large databases by visual feedback queries. In Proc. 10th of Int. Conf. on Data Engineering, pages 302–313, Houston, TX, Feb. 1994.
50.W. Kim. Introduction to Objected-Oriented Databases. The MIT Press, Cambridge, Massachusetts, 1990.
51.M. Klemettinen, H. Mannila, P. Ronkainen, H. Toivonen, and A. I. Verkamo. Finding interesting rules from large sets of discovered association rules. In Proc. 3rd Int'l Conf. on Information and Knowledge Management, pages 401–408, Gaithersburg, Maryland, Nov. 1994.
52.W. Klösgen. Explora: a multipattern and multistrategy discovery assistant. In U.M. Fayyad, G. Piatetsky-Shapiro, P. Smyth, and R. Uthurusamy, editors, Advances in Knowledge Discovery and Data Mining, pages 249–271. AAAI/MIT Press, 1996.
53.K. Koperski and J. Han. Discovery of spatial association rules in geographic information databases. In Proc. 4th Int'l Symp. on Large Spatial Databases (SSD'95), pages 47–66, Portland, Maine, Aug. 1995.
54.C-S. Li, P.S. Yu, and V. Castelli. HierarchyScan: A Hierarchical Similarity Search Algorithm for Databases of Long Sequences. Proceedings of the 12th International Conference on Data Engineering, February 1996.
55.H. Lu, R. Setiono, and H. Liu. NeuroRule: A Connectionist Approach to Data Mining. Proceedings of the 21th International Conference on Very Large Data Bases, pages 478–489, September 1995.
56.W. Lu, J. Han, and B. C. Ooi. Knowledge discovery in large spatial databases. In Far East Workshop on Geographic Information Systems, pages 275–289, Singapore, June 1993.
57.H. Mannila, H. Toivonen, and A. Inkeri Verkamo. Efficient Algorithms for Discovering Association Rules. Proceedings of AAAI Workshop on Knowledge Discovery in Databases, pages 181–192, July, 1994.
58.C.J. Matheus, G. Piatetsky-Shapiro, and D. McNeil. Selecting and reporting what is interesting: The KEFIR application to healthcare data. In U.M. Fayyad, G. Piatetsky-Shapiro, P. Smyth, and R. Uthurusamy, editors, Advances in Knowledge Discovery and Data Mining, pages 495–516. AAAI/MIT Press, 1996.
59.M. Mehta, R. Agrawal, and J. Rissanen. SLIQ: A fast scalable classifier for data mining. In Proc. 1996 Int. Conference on Extending Database Technology (EDBT'96), Avignon, France, March 1996.
60.R. S. Michalski. A theory and methodology of inductive learning. In Michalski et al., editor, Machine Learning: An Artificial Intelligence Approach, Vol. 1, pages 83–134. Morgan Kaufmann, 1983.
61.R. S. Michalski, L. Kerschberg, K. A. Kaufman, and J.S. Ribeiro. Mining for knowledge in databases: The INLEN architecture, initial implementation and first results. J. Int. Info. Systems, 1:85–114, 1992.
62.R. Ng and J. Han. Efficient and effective clustering method for spatial data mining. In Proc. 1994 Int. Conf. Very Large Data Bases, pages 144–155, Santiago, Chile, September 1994.
63.D. E. O'Leary. Knowledge discovery as a threat to database security. In G. Piatetsky-Shapiro and W. J. Frawley, editors, Knowledge Discovery in Databases, pages 507–516. AAAI/MIT Press, 1991.
64.A. Papoulis. Probability, Random Variable, and Stochastic Process. McGraw Hills, New York, 1984.
65.J.-S. Park, M.-S. Chen, and P. S. Yu. Mining Association Rules with Adjustable Accuracy. IBM Research Report, 1995.
66.J.-S. Park, M.-S. Chen, and P. S. Yu. An Effective Hash Based Algorithm for Mining Association Rules. Proceedings of ACM SIGMOD, pages 175–186, May, 1995.
67.J.-S. Park, M.-S. Chen, and P. S. Yu. Efficient Parallel Data Mining for Association Rules. Proceedings of the 4th Intern'l Conf. on Information and Knowledge Management, pages 31–36, Nov. 29 - Dec. 3, 1995.
68.G. Piatetsky-Shapiro. Discovery, analysis, and presentation of strong rules. In G. Piatetsky-Shapiro and W. J. Frawley, editors, Knowledge Discovery in Databases, pages 229–238. AAAI/MIT Press, 1991.
69.G. Piatetsky-Shapiro, U. Fayyad, and P. Smyth. From data mining to knowledge discovery: An overview. In U.M. Fayyad, G. Piatetsky-Shapiro, P. Smyth, and R. Uthurusamy, editors, Advances in Knowledge Discovery and Data Mining, pages 1–35. AAAI/MIT Press, 1996.
70.G. Piatetsky-Shapiro and W. J. Frawley. Knowledge Discovery in Databases. AAAI/MIT Press, 1991.
71.J. R. Quinlan. Induction of decision trees. Machine Learning, 1:81–106, 1986.
72.J. R. Quinlan. C4.5: Programs for Machine Learning. Morgan Kaufmann, 1993.
73.A. Savasere, E. Omiecinski, and S. Navathe. An Efficient Algorithm for Mining Association Rules in Large Databases. Proceedings of the 21th International Conference on Very Large Data Bases, pages 432–444, September 1995.
74.P. G. Selfridge, D. Srivastava, and L. O. Wilson. IDEA: Interactive data exploration and analysis. In Proc. 1996 ACM-SIGMOD Int. Conf. Management of Data, Montreal, Canada, June 1996.
75.W. Shen, K. Ong, B. Mitbander, and C. Zaniolo. Metaqueries for data mining. In U.M. Fayyad, G. Piatetsky-Shapiro, P. Smyth, and R. Uthurusamy, editors, Advances in Knowledge Discovery and Data Mining, pages 375–398. AAAI/MIT Press, 1996.
76.A. Silberschatz, M. Stonebraker, and J. D. Ullman. Database research: Achievements and opportunities into the 21st century. In Report of an NSF Workshop on the Future of Database Systems Research, May 1995.
77.A. Silberschatz and A. Tuzhilin. On subjective measure of interestingness in knowledge discovery. In Proc. 1st Int. Conf. on Knowledge Discovery and Data Mining (KDD'95), pages 275–281, Montreal, Canada, Aug. 1995.
78.R. Srikant and R. Agrawal. Mining Generalized Association Rules. Proceedings of the 21th International Conference on Very Large Data Bases, pages 407–419, September 1995.
79.R. Srikant and R. Agrawal. Mining quantitative association rules in large relational tables. In Proc. 1996 ACM-SIGMOD Int. Conf. Management of Data, Montreal, Canada, June 1996.
80.R. Stam and R. Snodgrass. A bibliography on temporal databases. IEEE Bulletin on Data Engineering, 11(4), December 1988.
81.Y. Stettiner, D. Malah, and D. Chazan. Dynamic Time Warping with Path Control and Non local Cost. Proceedings of 12th IAPR Intern'l Conf. on Pattern Recognition, pages 174–177, October 1994.
82.S. M. Weiss and C. A. Kulikowski. Computer Systems that Learn: Classification and Prediction Methods from Statistics, Neural Nets, Machine Learning, and Expert Systems. Morgan Kaufman, 1991.
83.J. Widom. Research problems in data warehousing. In Proc. 4th Int. Conf. on Information and Knowledge Management, pages 25–30, Baltimore, Maryland, Nov. 1995.
84.W. P. Yan and P. Larson. Eager aggregation and lazy aggregation. In Proc. 21st Int. Conf. Very Large Data Bases, pages 345–357, Zurich, Switzerland, Sept. 1995.
85.T. Zhang, R. Ramakrishnan, and M. Livny. BIRCH: an efficient data clustering method for very large databases. In Proc. 1996 ACM-SIGMOD Int. Conf. Management of Data, Montreal, Canada, June 1996.
86.Y. Zhuge, H. Garcia-Molina, J. Hammer, and J. Widom. View maintenance in a warehousing environment. In Proc. 1995 ACM-SIGMOD Int. Conf. Management of Data, pages 316–327, San Jose, CA, May 1995.
87.W. Ziarko. Rough Sets, Fuzzy Sets and Knowledge Discovery. Springer-Verlag, 1994.

Citation

MLA

Ming-Syan Chen, et al. “Data Mining: An Overview from a Database Perspective”. IEEE Transactions on Knowledge and Data Engineering, vol. 8, no. 6, 1996, pp. 866–83, https://doi.org/10.1109/69.553155.

APA

Ming-Syan Chen, Jiawei Han, & Yu, P. S. (1996). Data mining: an overview from a database perspective. IEEE Transactions on Knowledge and Data Engineering, 8(6), 866–883. https://doi.org/10.1109/69.553155

Chicago

Ming-Syan Chen, Jiawei Han, and P. S. Yu. 1996. “Data Mining: An Overview from a Database Perspective”. IEEE Transactions on Knowledge and Data Engineering 8 (6): 866–83. https://doi.org/10.1109/69.553155.

Harvard

Ming-Syan Chen, Jiawei Han and Yu, P.S. (1996) “Data mining: an overview from a database perspective”, IEEE Transactions on Knowledge and Data Engineering, 8(6), pp. 866–883. Available at: https://doi.org/10.1109/69.553155.

Vancouver

1. Ming-Syan Chen, Jiawei Han, Yu PS (1996) Data mining: an overview from a database perspective. IEEE Transactions on Knowledge and Data Engineering 8:866–883

BibTeX

@article{Ming_Syan_Chen_1996, title={Data mining: an overview from a database perspective}, volume={8}, ISSN={1041-4347}, url={http://dx.doi.org/10.1109/69.553155}, DOI={10.1109/69.553155}, number={6}, journal={IEEE Transactions on Knowledge and Data Engineering}, publisher={Institute of Electrical and Electronics Engineers (IEEE)}, author={Ming-Syan Chen and Jiawei Han and Yu, P.S.}, year={1996}, pages={866–883} }

Metadata:Crossref

Access the Paper

This paper is available from its original source. Click below to access the PDF.

Open PDF

Data Mining: An Overview from a Database Perspective

Abstract

Topics

Keywords

Table of Contents

Knowls

Knowl 1 — Formal Model of Association Rules in Transaction Databases

Knowl 2 — Statistical Independence Filter for Rule Interestingness

Knowl 3 — Scan-Reduction Optimization for Large Itemset Mining

Knowl 4 — Attribute-Oriented Induction for Database Generalization

Knowl 5 — Data Cube Greedy View Materialization Bound

Knowl 6 — Impurity and Splitting Metrics in Decision Tree Classification

Knowl 7 — CLARANS Randomized Search Clustering Algorithm

Knowl 8 — Clustering Feature and CF-Tree in BIRCH

Knowl 9 — Subsequence Matching via Normalized Correlation and DFT

Knowl 10 — Mining Path Traversal Patterns via Maximal Forward References

References

Citation

BibTeX

Access the Paper