DM
Download as PPTX, PDF•0 likes•58 views
This document provides an overview of data mining and machine learning techniques. It discusses how machine learning can be used to extract patterns and insights from large amounts of data. Examples are provided of applications in domains like credit lending, oil spill detection, load forecasting, and machine fault diagnosis. The document also covers key concepts in data mining like the generalization process, bias, and some ethical considerations around using these techniques.
DM
- 1. Data Mining Practical Machine Learning Tools and Techniques Slides for Chapter 1, What’s it all about? of Data Mining by I. H. Witten, E. Frank, M. A. Hall, and C. J. Pal
- 2. 2 Chapter 1: What’s it all about? •Data mining and machine learning •Simple examples: the weather problem and others •Fielded applications •The data mining process •Machine learning and statistics •Generalization as search •Data mining and ethics
- 3. 3 Information is crucial •Example 1: in vitro fertilization • Given: embryos described by 60 features • Problem: selection of embryos that will survive • Data: historical records of embryos and outcome •Example 2: cow culling • Given: cows described by 700 features • Problem: selection of cows that should be culled • Data: historical records and farmers’ decisions
- 4. 4 From data to information •Society produces huge amounts of data • Sources: business, science, medicine, economics, geography, environment, sports, … •This data is a potentially valuable resource •Raw data is useless: need techniques to automatically extract information from it • Data: recorded facts • Information: patterns underlying the data • We are concerned with machine learning techniques for automatically finding patterns in data • Patterns that are found may be represented as structural descriptions or as black-box models
- 5. 5 Structural descriptions • Example: if-then rules …………… HardNormalYesMyopePresbyopic NoneReducedNoHypermetropePre-presbyopic SoftNormalNoHypermetropeYoung NoneReducedNoMyopeYoung Recommended lenses Tear production rate AstigmatismSpectacle prescription Age If tear production rate = reduced then recommendation = none Otherwise, if age = young and astigmatic = no then recommendation = soft
- 6. 6 Machine learning •Definitions of “learning” from dictionary: To get knowledge of by study, experience, or being taught To become aware by information or from observation To commit to memory To be informed of, ascertain; to receive instruction Difficult to measure Trivial for computers Things learn when they change their behavior in a way that makes them perform better in the future. • Operational definition: Does a slipper learn? • Does learning imply intention?
- 7. 7 Data mining •Finding patterns in data that provide insight or enable fast and accurate decision making •Strong, accurate patterns are needed to make decisions • Problem 1: most patterns are not interesting • Problem 2: patterns may be inexact (or spurious) • Problem 3: data may be garbled or missing • Machine learning techniques identify patterns in data and provide many tools for data mining • Of primary interest are machine learning techniques that provide structural descriptions
- 8. 8 The weather problem • Conditions for playing a certain game …………… YesFalseNormalMildRainy YesFalseHighHotOvercast NoTrueHighHotSunny NoFalseHighHotSunny PlayWindyHumidityTemperatureOutlook If outlook = sunny and humidity = high then play = no If outlook = rainy and windy = true then play = no If outlook = overcast then play = yes If humidity = normal then play = yes If none of the above then play = yes
- 9. 9 Classification vs. association rules •Classification rule: predicts value of a given attribute (the classification of an example) •Association rule: predicts value of arbitrary attribute (or combination) If outlook = sunny and humidity = high then play = no If temperature = cool then humidity = normal If humidity = normal and windy = false then play = yes If outlook = sunny and play = no then humidity = high If windy = false and play = no then outlook = sunny and humidity = high
- 10. 10 Weather data with mixed attributes • Some attributes have numeric values …………… YesFalse8075Rainy YesFalse8683Overcast NoTrue9080Sunny NoFalse8585Sunny PlayWindyHumidityTemperatureOutlook If outlook = sunny and humidity > 83 then play = no If outlook = rainy and windy = true then play = no If outlook = overcast then play = yes If humidity < 85 then play = yes If none of the above then play = yes
- 11. 11 The contact lenses data NoneReducedYesHypermetropePre-presbyopic NoneNormalYesHypermetropePre-presbyopic NoneReducedNoMyopePresbyopic NoneNormalNoMyopePresbyopic NoneReducedYesMyopePresbyopic HardNormalYesMyopePresbyopic NoneReducedNoHypermetropePresbyopic SoftNormalNoHypermetropePresbyopic NoneReducedYesHypermetropePresbyopic NoneNormalYesHypermetropePresbyopic SoftNormalNoHypermetropePre-presbyopic NoneReducedNoHypermetropePre-presbyopic HardNormalYesMyopePre-presbyopic NoneReducedYesMyopePre-presbyopic SoftNormalNoMyopePre-presbyopic NoneReducedNoMyopePre-presbyopic hardNormalYesHypermetropeYoung NoneReducedYesHypermetropeYoung SoftNormalNoHypermetropeYoung NoneReducedNoHypermetropeYoung HardNormalYesMyopeYoung NoneReducedYesMyopeYoung SoftNormalNoMyopeYoung NoneReducedNoMyopeYoung Recommended lenses Tear production rateAstigmatismSpectacle prescriptionAge
- 12. 12 A complete and correct rule set If tear production rate = reduced then recommendation = none If age = young and astigmatic = no and tear production rate = normal then recommendation = soft If age = pre-presbyopic and astigmatic = no and tear production rate = normal then recommendation = soft If age = presbyopic and spectacle prescription = myope and astigmatic = no then recommendation = none If spectacle prescription = hypermetrope and astigmatic = no and tear production rate = normal then recommendation = soft If spectacle prescription = myope and astigmatic = yes and tear production rate = normal then recommendation = hard If age young and astigmatic = yes and tear production rate = normal then recommendation = hard If age = pre-presbyopic and spectacle prescription = hypermetrope and astigmatic = yes then recommendation = none If age = presbyopic and spectacle prescription = hypermetrope and astigmatic = yes then recommendation = none
- 13. 13 A decision tree for this problem
- 14. 14 Classifying iris flowers … … … Iris virginica1.95.12.75.8102 101 52 51 2 1 Iris virginica2.56.03.36.3 Iris versicolor1.54.53.26.4 Iris versicolor1.44.73.27.0 Iris setosa0.21.43.04.9 Iris setosa0.21.43.55.1 TypePetal widthPetal lengthSepal widthSepal length If petal length < 2.45 then Iris setosa If sepal width < 2.10 then Iris versicolor ...
- 15. 15 • Example: 209 different computer configurations • Linear regression function Predicting CPU performance 0 0 32 128 CHMAX 0 0 8 16 CHMIN Channels PerformanceCache (Kb) Main memory (Kb) Cycle time (ns) 45040001000480209 67328000512480208 … 26932320008000292 19825660002561251 PRPCACHMMAXMMINMYCT PRP = -55.9 + 0.0489 MYCT + 0.0153 MMIN + 0.0056 MMAX + 0.6410 CACH - 0.2700 CHMIN + 1.480 CHMAX
- 16. 16 Data from labor negotiations goodgoodgoodbad{good,bad}Acceptability of contract halffull?none{none,half,full}Health plan contribution yes??no{yes,no}Bereavement assistance fullfull?none{none,half,full}Dental plan contribution yes??no{yes,no}Long-term disability assistance avggengenavg{below-avg,avg,gen}Vacation 12121511(Number of days)Statutory holidays ???yes{yes,no}Education allowance Shift-work supplement Standby pay Pension Working hours per week Cost of living adjustment Wage increase third year Wage increase second year Wage increase first year Duration Attribute 44%5%?Percentage ??13%?Percentage ???none{none,ret-allw, empl-cntr} 40383528(Number of hours) none?tcfnone{none,tcf,tc} ????Percentage 4.04.4%5%?Percentage 4.54.3%4%2%Percentage 2321(Number of years) 40…321Type
- 17. 17 Decision trees for the labor data
- 18. 18 Soybean classification Diaporthe stem canker19Diagnosis Normal3ConditionRoot … Yes2Stem lodging Abnormal2ConditionStem … ?3Leaf spot size Abnormal2ConditionLeaf ?5Fruit spots Normal4Condition of fruit pods Fruit … Absent2Mold growth Normal2ConditionSeed … Above normal3Precipitation July7Time of occurrenceEnvironment Sample valueNumber of values Attribute
- 19. 19 The role of domain knowledge But in this domain, “leaf condition is normal” implies “leaf malformation is absent”! If leaf condition is normal and stem condition is abnormal and stem cankers is below soil line and canker lesion color is brown then diagnosis is rhizoctonia root rot If leaf malformation is absent and stem condition is abnormal and stem cankers is below soil line and canker lesion color is brown then diagnosis is rhizoctonia root rot
- 20. 20 Fielded applications •The result of learning—or the learning method itself—is deployed in practical applications • Processing loan applications • Screening images for oil slicks • Electricity supply forecasting • Diagnosis of machine faults • Marketing and sales • Separating crude oil and natural gas • Reducing banding in rotogravure printing • Finding appropriate technicians for telephone faults • Scientific applications: biology, astronomy, chemistry • Automatic selection of TV programs • Monitoring intensive care patients
- 21. 21 Processing loan applications (American Express) •Given: questionnaire with financial and personal information •Question: should money be lent? •Simple statistical method covers 90% of cases •Borderline cases referred to loan officers •But: 50% of accepted borderline cases defaulted! •Solution: reject all borderline cases? • No! Borderline cases are most active customers
- 22. 22 Enter machine learning •1000 training examples of borderline cases •20 attributes: • age • years with current employer • years at current address • years with the bank • other credit cards possessed,… •Learned rules: correct on 70% of cases • human experts only 50% •Rules could be used to explain decisions to customers
- 23. 23 Screening images •Given: radar satellite images of coastal waters •Problem: detect oil slicks in those images •Oil slicks appear as dark regions with changing size and shape •Not easy: lookalike dark regions can be caused by weather conditions (e.g. high wind) •Expensive process requiring highly trained personnel
- 24. 24 Enter machine learning •Extract dark regions from normalized image •Attributes: • size of region • shape, area • intensity • sharpness and jaggedness of boundaries • proximity of other regions • info about background •Constraints: • Few training examples—oil slicks are rare! • Unbalanced data: most dark regions aren’t slicks • Regions from same image form a batch • Requirement: adjustable false-alarm rate
- 25. 25 Load forecasting •Electricity supply companies need forecast of future demand for power •Forecasts of min/max load for each hour => significant savings •Given: manually constructed load model that assumes “normal” climatic conditions •Problem: adjust for weather conditions •Static model consist of: • base load for the year • load periodicity over the year • effect of holidays
- 26. 26 Enter machine learning •Prediction corrected using “most similar” days •Attributes: • temperature • humidity • wind speed • cloud cover readings • plus difference between actual load and predicted load •Average difference among three “most similar” days added to static model •Linear regression coefficients form attribute weights in similarity function
- 27. 27 Diagnosis of machine faults •Diagnosis: classical domain of expert systems •Given: Fourier analysis of vibrations measured at various points of a device’s mounting •Question: which fault is present? •Preventative maintenance of electromechanical motors and generators •Information very noisy •So far: diagnosis by expert/hand-crafted rules
- 28. 28 Enter machine learning •Available: 600 faults with expert’s diagnosis •~300 unsatisfactory, rest used for training •Attributes augmented by intermediate concepts that embodied causal domain knowledge •Expert not satisfied with initial rules because they did not relate to his domain knowledge •Further background knowledge resulted in more complex rules that were satisfactory •Learned rules outperformed hand-crafted ones
- 29. 29 Marketing and sales I •Companies precisely record massive amounts of marketing and sales data •Applications: • Customer loyalty: identifying customers that are likely to defect by detecting changes in their behavior (e.g. banks/phone companies) • Special offers: identifying profitable customers (e.g. reliable owners of credit cards that need extra money during the holiday season)
- 30. 30 Marketing and sales II •Market basket analysis • Association techniques find groups of items that tend to occur together in a transaction (used to analyze checkout data) •Historical analysis of purchasing patterns •Identifying prospective customers • Focusing promotional mailouts (targeted campaigns are cheaper than mass-marketed ones)
- 31. 31 The data mining process
- 32. 32 Machine learning and statistics •Historical difference (grossly oversimplified): • Statistics: testing hypotheses • Machine learning: finding the right hypothesis •But: huge overlap • Decision trees (C4.5 and CART) • Nearest-neighbor methods •Today: perspectives have converged • Most machine learning algorithms employ statistical techniques
- 33. 33 Generalization as search •Inductive learning: find a concept description that fits the data •Example: rule sets as description language • Enormous, but finite, search space •Simple solution: • enumerate the concept space • eliminate descriptions that do not fit examples • surviving descriptions contain target concept
- 34. 34 Enumerating the concept space •Search space for weather problem • 4 x 4 x 3 x 3 x 2 = 288 possible combinations • With 14 rules => 2.7x1034 possible rule sets •Other practical problems: • More than one description may survive • No description may survive • Language is unable to describe target concept • or data contains noise • Another view of generalization as search: hill-climbing in description space according to pre-specified matching criterion • Many practical algorithms use heuristic search that cannot guarantee to find the optimum solution
- 35. 35 Bias •Important decisions in learning systems: • Concept description language • Order in which the space is searched • Way that overfitting to the particular training data is avoided •These form the “bias” of the search: • Language bias • Search bias • Overfitting-avoidance bias
- 36. 36 Language bias •Important question: • is language universal or does it restrict what can be learned? •Universal language can express arbitrary subsets of examples •If language includes logical or (“disjunction”), it is universal •Example: rule sets •Domain knowledge can be used to exclude some concept descriptions a priori from the search
- 37. 37 Search bias •Search heuristic • “Greedy” search: performing the best single step • “Beam search”: keeping several alternatives • … •Direction of search • General-to-specific • E.g. specializing a rule by adding conditions • Specific-to-general • E.g. generalizing an individual instance into a rule
- 38. 38 Overfitting-avoidance bias •Can be seen as a form of search bias •Modified evaluation criterion • E.g., balancing simplicity and number of errors •Modified search strategy • E.g., pruning (simplifying a description) • Pre-pruning: stops at a simple description before search proceeds to an overly complex one • Post-pruning: generates a complex description first and simplifies it afterwards
- 39. 39 Data mining and ethics I •Ethical issues arise in practical applications •Anonymizing data is difficult •85% of Americans can be identified from just zip code, birth date and sex •Data mining often used to discriminate • E.g., loan applications: using some information (e.g., sex, religion, race) is unethical •Ethical situation depends on application • E.g., same information ok in medical application •Attributes may contain problematic information • E.g., area code may correlate with race
- 40. 40 Data mining and ethics II •Important questions: • Who is permitted access to the data? • For what purpose was the data collected? • What kind of conclusions can be legitimately drawn from it? •Caveats must be attached to results •Purely statistical arguments are never sufficient! •Are resources put to good use?