Introduksi Data Mining S1 Teknik Informatika Fakultas Teknologi Informasi Universitas Kristen Maranatha 1 DM-MA/S1IF/FTI/UKM/2010
Agenda Pendahuluan Definisi Data Mining Data Mining Steps Data Mining Tasks Data untuk Data Mining Data Mining Dalam Bisnis 2 DM-MA/S1IF/FTI/UKM/2010
Pendahuluan Ukuran DB yang sangat besar : Terabytes -> Petabytes Data collection & data availability : Database system, web, e-commerce, remote sensing, news, bioinformatics, etc. Komputer semakin powerful => Data Mining 3 DM-MA/S1IF/FTI/UKM/2010
Mining Large Data Sets - Motivation There is often information hidden in the data that is not readily evident Human analysts may take weeks to discover useful information Much of the data is never analyzed at all 4,000,000 3,500,000 3,000,000 2,500,000 2,000,000 1,500,000 The Data Gap Total new disk (TB) since 1995 1,000,000 500,000 0 Number of analysts 1995 1996 1997 1998 1999 4 DM-MA/S1IF/FTI/UKM/2010 From: R. Grossman, C. Kamath, V. Kumar, Data Mining for Scientific and Engineering Applications
Definisi Data Mining (1/3) Data mining is an interdisciplinary field bringing together techniques from machine learning, pattern recognition, statistics, databases, and visualization to address the issue of information extraction from large data bases Evangelos Simoudis in Cabena et al. Data mining is the extraction of implicit, previously unknown, and potentially useful information from data Witten & Frank 5 DM-MA/S1IF/FTI/UKM/2010
Definisi Data Mining (2/3) Data mining is the exploration and analysis, by automatic or semiautomatic means, of large quantities of data in order to discover meaningful patterns and rules Berry & Linoff Data mining is a term usually applied to techniques that can be used to find underlying structure and relationships in large amounts of data Kennedy et al. 6 DM-MA/S1IF/FTI/UKM/2010
Definisi Data Mining (3/3) Simply put, data mining is used to discover patterns and relationships in your data in order to help you make better business decisions Herb Edelstein, Two Crows 7 DM-MA/S1IF/FTI/UKM/2010
DM-MA/S1IF/FTI/UKM/2010 8
Data Mining Analytical Steps Describe the data Atribut statistik (mean & standar deviasi) hubungan antar variabel Build predictive model Test the model Verify the model 9 DM-MA/S1IF/FTI/UKM/2010
Data mining & data warehouse Biasanya, data yang akan ditambang diambil dari data warehouse, kemudian masuk ke data mining database atau data mart 10 DM-MA/S1IF/FTI/UKM/2010
Data Mining Tasks Prediction Methods Use some variables to predict unknown or future values of other variables. Description Methods Find human-interpretable patterns that describe the data. 11 DM-MA/S1IF/FTI/UKM/2010 From [Fayyad, et.al.] Advances in Knowledge Discovery and Data Mining, 1996
Data Mining Tasks Classification [predictive] Segmentation/Clustering [descriptive] Association [descriptive] Forecasting [predictive] Text Mining 12 DM-MA/S1IF/FTI/UKM/2010
Classification What type of membership card should I offer? Which customers will respond to my mailing? Is this transaction fraudulent? Will I lose this customer? Will this product be defective? Why is my system failing? Which patients health will degrade? 13 DM-MA/S1IF/FTI/UKM/2010
Classification Given a collection of records (training set ) Each record contains a set of attributes, one of the attributes is the class. Find a model for class attribute as a function of the values of other attributes. Goal: previously unseen records should be assigned a class as accurately as possible. A test set is used to determine the accuracy of the model. Usually, the given data set is divided into training and test sets, with training set used to build the model and test set used to validate it. 14 DM-MA/S1IF/FTI/UKM/2010
10 10 Classification Example Tid Refund Marital Status Taxable Income Cheat Refund Marital Status Taxable Income Cheat 1 Yes Single 125K No 2 No Married 100K No 3 No Single 70K No 4 Yes Married 120K No 5 No Divorced 95K Yes 6 No Married 60K No 7 Yes Divorced 220K No 8 No Single 85K Yes No Single 75K? Yes Married 50K? No Married 150K? Yes Divorced 90K? No Single 40K? No Married 80K? Test Set 9 No Married 75K No 10 No Single 90K Yes Training Set Learn Classifier Model 15 DM-MA/S1IF/FTI/UKM/2010
Classification: Application Direct Marketing Goal: Reduce cost of mailing by targeting a set of consumers likely to buy a new cell-phone product. Approach: Use the data for a similar product introduced before. We know which customers decided to buy and which decided otherwise. This {buy, don t buy} decision forms the class attribute. Collect various demographic, lifestyle, and companyinteraction related information about all such customers. Type of business, where they stay, how much they earn, etc. Use this information as input attributes to learn a classifier model. 16 DM-MA/S1IF/FTI/UKM/2010 From [Berry & Linoff] Data Mining Techniques, 1997
Segmentation/Clustering Describe my customers How can I differentiate my customers? How can I organize my data in a manner that make sense? Is this record an outlier? 17 DM-MA/S1IF/FTI/UKM/2010
Clustering Definition Given a set of data points, each having a set of attributes, and a similarity measure among them, find clusters such that Data points in one cluster are more similar to one another. Data points in separate clusters are less similar to one another. Similarity Measures: Euclidean Distance if attributes are continuous. Other Problem-specific Measures. 18 DM-MA/S1IF/FTI/UKM/2010
Illustrating Clustering Euclidean Distance Based Clustering in 3-D space. Intracluster distances are minimized Intercluster distances are maximized 19 DM-MA/S1IF/FTI/UKM/2010
Clustering: Application Document Clustering: Goal: To find groups of documents that are similar to each other based on the important terms appearing in them. Approach: To identify frequently occurring terms in each document. Form a similarity measure based on the frequencies of different terms. Use it to cluster. Gain: Information Retrieval can utilize the clusters to relate a new document or search term to clustered documents. 20 DM-MA/S1IF/FTI/UKM/2010
Illustrating Document Clustering Clustering Points: 3204 Articles of Los Angeles Times. Similarity Measure: How many words are common in these documents (after some word filtering). Category Total Correctly Articles Placed Financial 555 364 Foreign 341 260 National 273 36 Metro 943 746 Sports 738 573 Entertainment 354 278 21 DM-MA/S1IF/FTI/UKM/2010
Association Rule Discovery Given a set of records each of which contain some number of items from a given collection; Produce dependency rules which will predict occurrence of an item based on occurrences of other items. TID Items 1 Bread, Coke, Milk 2 Beer, Bread 3 Beer, Coke, Diaper, Milk 4 Beer, Bread, Diaper, Milk 5 Coke, Diaper, Milk Rules Discovered: {Milk} --> {Coke} {Diaper, Milk} --> {Beer} 22 DM-MA/S1IF/FTI/UKM/2010
Association Rule Discovery: Application Marketing and Sales Promotion: Let the rule discovered be {Bagels, } --> {Potato Chips} Potato Chips as consequent => Can be used to determine what should be done to boost its sales. Bagels in the antecedent => Can be used to see which products would be affected if the store discontinues selling bagels. Bagels in antecedent and Potato chips in consequent => Can be used to see what products should be sold with Bagels to promote sale of Potato chips! 23 DM-MA/S1IF/FTI/UKM/2010
Forecasting What are projected revenues for all products? What are inventory levels next month? 24 DM-MA/S1IF/FTI/UKM/2010
Regression Predict a value of a given continuous valued variable based on the values of other variables, assuming a linear or nonlinear model of dependency. Greatly studied in statistics, neural network fields. Examples: Predicting sales amounts of new product based on advetising expenditure. Predicting wind velocities as a function of temperature, humidity, air pressure, etc. Time series prediction of stock market indices. 25 DM-MA/S1IF/FTI/UKM/2010
Text Mining Analysis of unstructured data Finds key terms and phrases in text Conversion to structured data Feed into other algorithms Classification Segmentation Association How do I handle call center data? How can I classify mail? What can I do with web feedback? 26 DM-MA/S1IF/FTI/UKM/2010
Advanced Data Exploration Descriptive Analysis Learning more about data through visualizations Typical business questions : Why do people churn? What are the relationships between products? What are the differences between high profit and low profit customers? 27 DM-MA/S1IF/FTI/UKM/2010
Data untuk Data Mining Pada prinsipnya, di segala macam information repository, bisa dilakukan data mining. Relational DB Data warehouse Transactional DB Advanced DB system Flat files WWW 28 DM-MA/S1IF/FTI/UKM/2010
Data Mining dalam Bisnis Market segmentation Mengidentifikasi karakteristik umum customer yang membeli barang yang sama Customer churn Memprediksi customer mana yang kira-kira dapat pindah ke perusahaan kompetitor Fraud detection Mengidentifikasi transaksi mana yang kira-kira berpotensi menjadi fraud 29 DM-MA/S1IF/FTI/UKM/2010
Data Mining dalam Bisnis Direct marketing Mengidentifikasi prospect yang harus dimasukkan dalam mailing list agar tercapai response rate yang lebih tinggi. Interactive marketing Memprediksi hal yang paling disukai ketika seseorang mengunjungi sebuah web site Market basket analysis Memahami produk mana yang diakses bersamaan (dlm 1 keranjang); mis. Popok dan bir 30 DM-MA/S1IF/FTI/UKM/2010
Data Mining dalam Bisnis Automated prediction of trends and behaviors: Data mining mengotomasi proses penemuan predictive information pada large database. Target marketing Memprediksikan kebangkrutan Mengidentifikasi segment yang mungkin merespon ke event tertentu 31 DM-MA/S1IF/FTI/UKM/2010
Data Mining dalam Bisnis Automated discovery of previously unknown patterns: Data mining tools mencari di database dan mengidentifikasi pola yang sebelumya tersembunyi. Mengidentifikasi produk yang tidak berelasi tapi yang seringkali dibeli bersamaan. Popok dan bir Mendeteksi fraud dalam transaksi kartu kredit 32 DM-MA/S1IF/FTI/UKM/2010