1. 1 DATA MINING Source : Margaret H. Dunham Department of Computer Science and Engineering Southern Methodist University Companion slides for the text by Dr. M.H.Dunham, Data Mining, Introductory and Advanced Topics, Prentice Hall, 2002.

2. 2 Introduction Outline Define data mining Define data mining Data mining vs. databases Data mining vs. databases Basic data mining tasks Basic data mining tasks Data mining development Data mining development Data mining issues Data mining issues Goal: Provide an overview of data mining.

3. 3 Introduction Data is growing at a phenomenal rate Data is growing at a phenomenal rate Users expect more sophisticated information Users expect more sophisticated information How? How? UNCOVER HIDDEN INFORMATION DATA MINING

4. 4 Data Mining Definition Finding hidden information in a database Finding hidden information in a database Fit data to a model Fit data to a model Similar terms Similar terms –Exploratory data analysis –Data driven discovery –Deductive learning

5. 5 Database Processing vs. Data Mining Processing Query Query –Well defined –SQL Query Query –Poorly defined –No precise query language Data Data – Operational data Output Output – Precise – Subset of database Data Data – Not operational data Output Output – Fuzzy – Not a subset of database

6. 6 Query Examples Database Database Data Mining Data Mining – Find all customers who have purchased milk – Find all items which are frequently purchased with milk. (association rules) – Find all credit applicants with last name of Smith. – Identify customers who have purchased more than $10,000 in the last month. – Find all credit applicants who are poor credit risks. (classification) – Identify customers with similar buying habits. (Clustering)

7. 7 Data Mining Models and Tasks

8. 8 Basic Data Mining Tasks Classification maps data into predefined groups or classes Classification maps data into predefined groups or classes –Supervised learning –Pattern recognition –Prediction Regression is used to map a data item to a real valued prediction variable. Regression is used to map a data item to a real valued prediction variable. Clustering groups similar data together into clusters. Clustering groups similar data together into clusters. –Unsupervised learning –Segmentation –Partitioning

9. 9 Basic Data Mining Tasks (cont’d) Summarization maps data into subsets with associated simple descriptions. Summarization maps data into subsets with associated simple descriptions. –Characterization –Generalization Link Analysis uncovers relationships among data. Link Analysis uncovers relationships among data. –Affinity Analysis –Association Rules –Sequential Analysis determines sequential patterns.

10. 10 Ex: Time Series Analysis Example: Stock Market Example: Stock Market Predict future values Predict future values Determine similar patterns over time Determine similar patterns over time Classify behavior Classify behavior

11. 11 Data Mining vs. KDD Knowledge Discovery in Databases (KDD): process of finding useful information and patterns in data. Knowledge Discovery in Databases (KDD): process of finding useful information and patterns in data. Data Mining: Use of algorithms to extract the information and patterns derived by the KDD process. Data Mining: Use of algorithms to extract the information and patterns derived by the KDD process.

12. 12 KDD Process Selection: Obtain data from various sources. Selection: Obtain data from various sources. Preprocessing: Cleanse data. Preprocessing: Cleanse data. Transformation: Convert to common format. Transform to new format. Transformation: Convert to common format. Transform to new format. Data Mining: Obtain desired results. Data Mining: Obtain desired results. Interpretation/Evaluation: Present results to user in meaningful manner. Interpretation/Evaluation: Present results to user in meaningful manner. Modified from [FPSS96C]

13. 13 KDD Process Ex: Web Log Selection: Selection: –Select log data (dates and locations) to use Preprocessing: Preprocessing: – Remove identifying URLs – Remove error logs Transformation: Transformation: –Sessionize (sort and group) Data Mining: Data Mining: –Identify and count patterns –Construct data structure Interpretation/Evaluation: Interpretation/Evaluation: –Identify and display frequently accessed sequences. Potential User Applications: Potential User Applications: –Cache prediction –Personalization

14. 14 Data Mining Development Similarity Measures Hierarchical Clustering IR Systems Imprecise Queries Textual Data Web Search Engines Bayes Theorem Regression Analysis EM Algorithm K-Means Clustering Time Series Analysis Neural Networks Decision Tree Algorithms Algorithm Design Techniques Algorithm Analysis Data Structures Relational Data Model SQL Association Rule Algorithms Data Warehousing Scalability Techniques

15. 15 KDD Issues Human Interaction Human Interaction Overfitting Overfitting Outliers Outliers Interpretation Interpretation Visualization Visualization Large Datasets Large Datasets High Dimensionality High Dimensionality

16. 16 KDD Issues (cont’d) Multimedia Data Multimedia Data Missing Data Missing Data Irrelevant Data Irrelevant Data Noisy Data Noisy Data Changing Data Changing Data Integration Integration Application Application

17. 17 Social Implications of DM Privacy Privacy Profiling Profiling Unauthorized use Unauthorized use

18. 18 Data Mining Metrics Usefulness Usefulness Return on Investment (ROI) Return on Investment (ROI) Accuracy Accuracy Space/Time Space/Time

19. 19 Database Perspective on Data Mining Scalability Scalability Real World Data Real World Data Updates Updates Ease of Use Ease of Use

20. 20 Visualization Techniques Graphical Graphical Geometric Geometric Icon-based Icon-based Pixel-based Pixel-based Hierarchical Hierarchical Hybrid Hybrid

21. 21 Related Concepts Outline Database/OLTP Systems Database/OLTP Systems Fuzzy Sets and Logic Fuzzy Sets and Logic Information Retrieval(Web Search Engines) Information Retrieval(Web Search Engines) Dimensional Modeling Dimensional Modeling Data Warehousing Data Warehousing OLAP/DSS OLAP/DSS Statistics Statistics Machine Learning Machine Learning Pattern Matching Pattern Matching Goal: Examine some areas which are related to data mining.

22. 22 DB & OLTP Systems Schema Schema –(ID,Name,Address,Salary,JobNo) Data Model Data Model –ER –Relational Transaction Transaction Query: Query: SELECT Name FROM T WHERE Salary > 100000 DM: Only imprecise queries

23. 23 Fuzzy Sets and Logic Fuzzy Set: Set membership function is a real valued function with output in the range [0,1]. Fuzzy Set: Set membership function is a real valued function with output in the range [0,1]. f(x): Probability x is in F. f(x): Probability x is in F. 1-f(x): Probability x is not in F. 1-f(x): Probability x is not in F. EX: EX: –T = {x | x is a person and x is tall} –Let f(x) be the probability that x is tall –Here f is the membership function DM: Prediction and classification are fuzzy.

24. 24 Fuzzy Sets

25. 25 Classification/Prediction is Fuzzy Loan Amnt SimpleFuzzy Accept Reject

26. 26 Information Retrieval Information Retrieval (IR): retrieving desired information from textual data. Information Retrieval (IR): retrieving desired information from textual data. Library Science Library Science Digital Libraries Digital Libraries Web Search Engines Web Search Engines Traditionally keyword based Traditionally keyword based Sample query: Sample query: Find all documents about “data mining”. DM: Similarity measures; Mine text/Web data. Mine text/Web data.

27. 27 IR Query Result Measures and Classification IRClassification

28. 28 Dimensional Modeling View data in a hierarchical manner more as business executives might View data in a hierarchical manner more as business executives might Useful in decision support systems and mining Useful in decision support systems and mining Dimension: collection of logically related attributes; axis for modeling data. Dimension: collection of logically related attributes; axis for modeling data. Facts: data stored Facts: data stored Ex: Dimensions – products, locations, date Ex: Dimensions – products, locations, date Facts – quantity, unit price Facts – quantity, unit price DM: May view data as dimensional.

29. 29 Relational View of Data

30. 30 Dimensional Modeling Queries Roll Up: more general dimension Roll Up: more general dimension Drill Down: more specific dimension Drill Down: more specific dimension Dimension (Aggregation) Hierarchy Dimension (Aggregation) Hierarchy SQL uses aggregation SQL uses aggregation Decision Support Systems (DSS): Computer systems and tools to assist managers in making decisions and solving problems. Decision Support Systems (DSS): Computer systems and tools to assist managers in making decisions and solving problems.

31. 31 Cube view of Data

32. 32 Aggregation Hierarchies

33. 33 Data Warehousing “ Subject-oriented, integrated, time-variant, nonvolatile” William Inmon “ Subject-oriented, integrated, time-variant, nonvolatile” William Inmon Operational Data: Data used in day to day needs of company. Operational Data: Data used in day to day needs of company. Informational Data: Supports other functions such as planning and forecasting. Informational Data: Supports other functions such as planning and forecasting. Data mining tools often access data warehouses rather than operational data. Data mining tools often access data warehouses rather than operational data. DM: May access data in warehouse.

34. 34 Operational vs. Informational Operational DataData Warehouse ApplicationOLTPOLAP UsePrecise QueriesAd Hoc TemporalSnapshotHistorical ModificationDynamicStatic OrientationApplicationBusiness DataOperational ValuesIntegrated SizeGigabitsTerabits LevelDetailedSummarized AccessOftenLess Often ResponseFew SecondsMinutes Data SchemaRelationalStar/Snowflake

35. 35 OLAP Online Analytic Processing (OLAP): provides more complex queries than OLTP. Online Analytic Processing (OLAP): provides more complex queries than OLTP. OnLine Transaction Processing (OLTP): traditional database/transaction processing. OnLine Transaction Processing (OLTP): traditional database/transaction processing. Dimensional data; cube view Dimensional data; cube view Visualization of operations: Visualization of operations: –Slice: examine sub-cube. –Dice: rotate cube to look at another dimension. –Roll Up/Drill Down DM: May use OLAP queries.

36. 36 OLAP Operations Single CellMultiple CellsSliceDice Roll Up Drill Down

37. 37Statistics Simple descriptive models Simple descriptive models Statistical inference: generalizing a model created from a sample of the data to the entire dataset. Statistical inference: generalizing a model created from a sample of the data to the entire dataset. Exploratory Data Analysis: Exploratory Data Analysis: –Data can actually drive the creation of the model –Opposite of traditional statistical view. Data mining targeted to business user Data mining targeted to business user DM: Many data mining methods come from statistical techniques.

38. 38 Machine Learning Machine Learning: area of AI that examines how to write programs that can learn. Machine Learning: area of AI that examines how to write programs that can learn. Often used in classification and prediction Often used in classification and prediction Supervised Learning: learns by example. Supervised Learning: learns by example. Unsupervised Learning: learns without knowledge of correct answers. Unsupervised Learning: learns without knowledge of correct answers. Machine learning often deals with small static datasets. Machine learning often deals with small static datasets. DM: Uses many machine learning techniques.

39. 39 Pattern Matching (Recognition) Pattern Matching: finds occurrences of a predefined pattern in the data. Pattern Matching: finds occurrences of a predefined pattern in the data. Applications include speech recognition, information retrieval, time series analysis. Applications include speech recognition, information retrieval, time series analysis. DM: Type of classification.

40. 40 DM vs. Related Topics

41. 41 Data Mining Techniques Outline Statistical Statistical –Point Estimation –Models Based on Summarization –Bayes Theorem –Hypothesis Testing –Regression and Correlation Similarity Measures Similarity Measures Decision Trees Decision Trees Neural Networks Neural Networks –Activation Functions Genetic Algorithms Genetic Algorithms Goal: Provide an overview of basic data mining techniques

42. 42 Point Estimation Point Estimate: estimate a population parameter. Point Estimate: estimate a population parameter. May be made by calculating the parameter for a sample. May be made by calculating the parameter for a sample. May be used to predict value for missing data. May be used to predict value for missing data. Ex: Ex: –R contains 100 employees –99 have salary information –Mean salary of these is $50,000 –Use $50,000 as value of remaining employee’s salary. Is this a good idea?

43. 43 Estimation Error Bias: Difference between expected value and actual value. Bias: Difference between expected value and actual value. Mean Squared Error (MSE): expected value of the squared difference between the estimate and the actual value: Mean Squared Error (MSE): expected value of the squared difference between the estimate and the actual value: Why square? Why square? Root Mean Square Error (RMSE) Root Mean Square Error (RMSE)

44. 44 Expectation-Maximization (EM) Solves estimation with incomplete data. Solves estimation with incomplete data. Obtain initial estimates for parameters. Obtain initial estimates for parameters. Iteratively use estimates for missing data and continue until convergence. Iteratively use estimates for missing data and continue until convergence.

45. 45 EM Example

46. 46 EM Algorithm

47. 47 Bayes Theorem Posterior Probability: P(h 1 |x i ) Posterior Probability: P(h 1 |x i ) Prior Probability: P(h 1 ) Prior Probability: P(h 1 ) Bayes Theorem: Bayes Theorem: Assign probabilities of hypotheses given a data value. Assign probabilities of hypotheses given a data value.

48. 48 Bayes Theorem Example Credit authorizations (hypotheses): h 1 =authorize purchase, h 2 = authorize after further identification, h 3 =do not authorize, h 4 = do not authorize but contact police Credit authorizations (hypotheses): h 1 =authorize purchase, h 2 = authorize after further identification, h 3 =do not authorize, h 4 = do not authorize but contact police Assign twelve data values for all combinations of credit and income: Assign twelve data values for all combinations of credit and income: From training data: P(h 1 ) = 60%; P(h 2 )=20%; P(h 3 )=10%; P(h 4 )=10%. From training data: P(h 1 ) = 60%; P(h 2 )=20%; P(h 3 )=10%; P(h 4 )=10%.

49. 49 Bayes Example(cont’d) Training Data: Training Data:

50. 50 Bayes Example(cont’d) Calculate P(x i |h j ) and P(x i ) Calculate P(x i |h j ) and P(x i ) Ex: P(x 7 |h 1 )=2/6; P(x 4 |h 1 )=1/6; P(x 2 |h 1 )=2/6; P(x 8 |h 1 )=1/6; P(x i |h 1 )=0 for all other x i. Ex: P(x 7 |h 1 )=2/6; P(x 4 |h 1 )=1/6; P(x 2 |h 1 )=2/6; P(x 8 |h 1 )=1/6; P(x i |h 1 )=0 for all other x i. Predict the class for x 4 : Predict the class for x 4 : –Calculate P(h j |x 4 ) for all h j. –Place x 4 in class with largest value. –Ex: P(h 1 |x 4 )=(P(x 4 |h 1 )(P(h 1 ))/P(x 4 ) P(h 1 |x 4 )=(P(x 4 |h 1 )(P(h 1 ))/P(x 4 ) =(1/6)(0.6)/0.1=1. =(1/6)(0.6)/0.1=1. x 4 in class h 1. x 4 in class h 1.

51. 51 Regression Predict future values based on past values Predict future values based on past values Linear Regression assumes linear relationship exists. Linear Regression assumes linear relationship exists. y = c 0 + c 1 x 1 + … + c n x n Find values to best fit the data Find values to best fit the data

52. 52 Linear Regression

53. 53 Correlation Examine the degree to which the values for two variables behave similarly. Examine the degree to which the values for two variables behave similarly. Correlation coefficient r: Correlation coefficient r: 1 = perfect correlation1 = perfect correlation -1 = perfect but opposite correlation-1 = perfect but opposite correlation 0 = no correlation0 = no correlation

54. 54 Similarity Measures Determine similarity between two objects. Determine similarity between two objects. Similarity characteristics: Similarity characteristics: Alternatively, distance measure measure how unlike or dissimilar objects are. Alternatively, distance measure measure how unlike or dissimilar objects are.

55. 55 Similarity Measures

56. 56 Distance Measures Measure dissimilarity between objects Measure dissimilarity between objects

57. 57 Decision Trees Decision Tree (DT): Decision Tree (DT): –Tree where the root and each internal node is labeled with a question. –The arcs represent each possible answer to the associated question. –Each leaf node represents a prediction of a solution to the problem. Popular technique for classification; Leaf node indicates class to which the corresponding tuple belongs. Popular technique for classification; Leaf node indicates class to which the corresponding tuple belongs.

58. 58 Decision Tree Example

59. 59 Decision Trees A Decision Tree Model is a computational model consisting of three parts: A Decision Tree Model is a computational model consisting of three parts: –Decision Tree –Algorithm to create the tree –Algorithm that applies the tree to data Creation of the tree is the most difficult part. Creation of the tree is the most difficult part. Processing is basically a search similar to that in a binary search tree (although DT may not be binary). Processing is basically a search similar to that in a binary search tree (although DT may not be binary).

60. 60 Decision Tree Algorithm

61. 61 DT Advantages/Disadvantages Advantages: Advantages: –Easy to understand. –Easy to generate rules Disadvantages: Disadvantages: –May suffer from overfitting. –Classifies by rectangular partitioning. –Does not easily handle nonnumeric data. –Can be quite large – pruning is necessary.

62. 62 Neural Networks Based on observed functioning of human brain. Based on observed functioning of human brain. (Artificial Neural Networks (ANN) (Artificial Neural Networks (ANN) Our view of neural networks is very simplistic. Our view of neural networks is very simplistic. We view a neural network (NN) from a graphical viewpoint. We view a neural network (NN) from a graphical viewpoint. Alternatively, a NN may be viewed from the perspective of matrices. Alternatively, a NN may be viewed from the perspective of matrices. Used in pattern recognition, speech recognition, computer vision, and classification. Used in pattern recognition, speech recognition, computer vision, and classification.

63. 63 Neural Networks Neural Network (NN) is a directed graph F= with vertices V={1,2,…,n} and arcs A={ |1 with vertices V={1,2,…,n} and arcs A={ |1<=i,j<=n}, with the following restrictions: –V is partitioned into a set of input nodes, V I, hidden nodes, V H, and output nodes, V O. –The vertices are also partitioned into layers –Any arc must have node i in layer h-1 and node j in layer h. –Arc is labeled with a numeric value w ij. –Node i is labeled with a function f i.

64. 64 Neural Network Example

65. 65 NN Node

66. 66 NN Activation Functions Functions associated with nodes in graph. Functions associated with nodes in graph. Output may be in range [-1,1] or [0,1] Output may be in range [-1,1] or [0,1]

67. 67 NN Activation Functions

68. 68 NN Learning Propagate input values through graph. Propagate input values through graph. Compare output to desired output. Compare output to desired output. Adjust weights in graph accordingly. Adjust weights in graph accordingly.

69. 69 Neural Networks A Neural Network Model is a computational model consisting of three parts: A Neural Network Model is a computational model consisting of three parts: –Neural Network graph –Learning algorithm that indicates how learning takes place. –Recall techniques that determine how information is obtained from the network.

70. 70 NN Advantages Learning Learning Can continue learning even after training set has been applied. Can continue learning even after training set has been applied. Easy parallelization Easy parallelization Solves many problems Solves many problems

71. 71 NN Disadvantages Difficult to understand Difficult to understand May suffer from overfitting May suffer from overfitting Structure of graph must be determined a priori. Structure of graph must be determined a priori. Input values must be numeric. Input values must be numeric. Verification difficult. Verification difficult.

72. 72 Genetic Algorithms Optimization search type algorithms. Optimization search type algorithms. Creates an initial feasible solution and iteratively creates new “better” solutions. Creates an initial feasible solution and iteratively creates new “better” solutions. Based on human evolution and survival of the fitness. Based on human evolution and survival of the fitness. Must represent a solution as an individual. Must represent a solution as an individual. Individual: string I=I 1,I 2,…,I n where I j is in given alphabet A. Individual: string I=I 1,I 2,…,I n where I j is in given alphabet A. Each character I j is called a gene. Each character I j is called a gene. Population: set of individuals. Population: set of individuals.

73. 73 Genetic Algorithms A Genetic Algorithm (GA) is a computational model consisting of five parts: A Genetic Algorithm (GA) is a computational model consisting of five parts: –A starting set of individuals, P. –Crossover: technique to combine two parents to create offspring. –Mutation: randomly change an individual. –Fitness: determine the best individuals. –Algorithm which applies the crossover and mutation techniques to P iteratively using the fitness function to determine the best individuals in P to keep.

74. 74 Crossover Examples

75. 75 Genetic Algorithm

76. 76 GA Advantages/Disadvantages Advantages Advantages –Easily parallelized Disadvantages Disadvantages –Difficult to understand and explain to end users. –Abstraction of the problem and method to represent individuals is quite difficult. –Determining fitness function is difficult. –Determining how to perform crossover and mutation is difficult.