Project.

Slides:



Advertisements
Similar presentations
World of work How is science used in the world of work? Science in the world of work.
Advertisements

Discrimination amongst k populations. We want to determine if an observation vector comes from one of the k populations For this purpose we need to partition.
Brief introduction on Logistic Regression
R Squared. r = r = -.79 y = x y = x if x = 15, y = ? y = (15) y = if x = 6, y = ? y = (6)
Pattern Recognition and Machine Learning
Chapter 5 – Evaluating Classification & Predictive Performance
Chapter 4 – Evaluating Classification & Predictive Performance © Galit Shmueli and Peter Bruce 2008 Data Mining for Business Intelligence Shmueli, Patel.
 Econometrics and Programming approaches › Historically these approaches have been at odds, but recent advances have started to close this gap  Advantages.
Machine Learning CMPT 726 Simon Fraser University
Mathematical Modeling. What is Mathematical Modeling? Mathematical model – an equation, graph, or algorithm that fits some real data set reasonably well.
Boosting Main idea: train classifiers (e.g. decision trees) in a sequence. a new classifier should focus on those cases which were incorrectly classified.
1 Linear Classification Problem Two approaches: -Fisher’s Linear Discriminant Analysis -Logistic regression model.
Optimization in Business Economics Life Sciences
ADJUSTED EXPONENTIAL SMOOTHING FORECASTING METHOD Prepared by Dan Milewski November 29, 2005.
Number Systems Part 2 Numerical Overflow Right and Left Shifts Storage Methods Subtraction Ranges.
1 Evaluating Model Performance Lantz Ch 10 Wk 5, Part 2 Right – Graphing is often used to evaluate results from different variations of an algorithm. Depending.
Performance measurement. Must be careful what performance metric we use For example, say we have a NN classifier with 1 output unit, and we code ‘1 =
Business and Economic Applications. Summary of Business Terms and Formulas  x is the number of units produced (or sold)  p is the price per unit  R.
Empirical Research Methods in Computer Science Lecture 7 November 30, 2005 Noah Smith.
Remainder Estimation Theorem
Regression Lines. Today’s Aim: To learn the method for calculating the most accurate Line of Best Fit for a set of data.
Valuing environment as production input. Production function The Cobb-Douglas function: q: output x: variable input E: environmental quality.
F. Provost and T. Fawcett. Confusion Matrix 2Bitirgen - CS678.
Goal of Learning Algorithms  The early learning algorithms were designed to find such an accurate fit to the data.  A classifier is said to be consistent.
10.5 Systems of Linear Inequalities and Applications 11.1 Interval Notation and Linear Inequalities.
PRODUCTION & PRODUCT PLANNING. What is Production Planning? Planning is a process for accomplishing purpose. Production planning is one of the planning.
Least Cost Rule When the last dollar spent on each resource yields the same marginal product.
Chapter 5 – Evaluating Predictive Performance Data Mining for Business Analytics Shmueli, Patel & Bruce.
D/RS 1013 Discriminant Analysis. Discriminant Analysis Overview n multivariate extension of the one-way ANOVA n looks at differences between 2 or more.
This whole paper is about...
Machine Learning: Ensemble Methods
Chapter 12 – Discriminant Analysis
Bayesian inference, Naïve Bayes model
Angelo Dalisay Raymond Ye Yang Zheng
Large Margin classifiers
Nature of Roots of a Quadratic Equation
Determining the optimal solution to a real-world engineering problem
The Prediction Calculator Tool
Data Mining Lecture 11.
Overview of Supervised Learning
In-Class Exercise: Discrete Distributions
Support Vector Machines
السيولة والربحية أدوات الرقابة المالية الوظيفة المالية
CS539: Project 3 Zach Pardos.
SIRS and STARS: Now What?
Big Data Analytics: Evaluating Classification Performance April, 2016 R. Bohn Some overheads from Galit Shmueli and Peter Bruce 2010.
R Squared.
10:00.
The Least-Squares Line Introduction
CHAPTER Perfect Competition 8.
Machine Learning Week 3.
Lecture 6: Introduction to Machine Learning
Loss.
SCIENCE SKILLS.
Getting the most out of your editing time
Profit-Maximizing Level for Mini-Z
Mathematical Sciences
Income Report for Mini-Z
Ensembles An ensemble is a set of classifiers whose combined results give the final decision. test feature vector classifier 1 classifier 2 classifier.
FdSc Module 107 Systems Analysis
R = R Squared
Explain how you plan to accomplish your goals? (Write in CDC form)
Mathematics Objectives: Today we will determine whether a shape has been divided into equal or unequal parts and identify halves, thirds, and fourths.
2015 Question 3 Intent of Question
Decision Trees Jeff Storey.
Types of Errors And Error Analysis.
Damage Scoring Flowchart
For More Details:
Diagnostic performance of dentist clinical impression.
Unions.
Presentation transcript:

Project

Overview Project details Open class to begin project work Fitness function Equal error costs Unequal error costs Open class to begin project work

Project details Objective (or fitness function)?

Equal Error Costs If type 1 and type 2 error costs are the same we can simply minimize misclassification rates (on hold out set)

These two models have the same misclassification rate: Unequal Error Costs In many real life scenarios the costs of type 1 and type 2 error costs are not the same… These two models have the same misclassification rate: Which one do you prefer?

Example Type 2 error Type 1 error MODEL A MODEL B Example Type 2 error expected cost of incorrectly classifying someone with cancer (actual YES) as not having cancer (predict NO) is $10000   expected cost of incorrectly classifying someone without cancer (actual NO) as having cancer (predict YES) is $500 Type 1 error

Example Instead of minimizing misclassification rate... MODEL A MODEL B Example Type 2 error cost = 10000 Type 1 error cost = 500 Revenue for correctly identifying cancer exists = 4000 Revenue for correctly identifying cancer doesn’t exist = 100 Instead of minimizing misclassification rate...  let’s maximize expected profit revenue correctly predict 1 revenue correctly predict 0 #correct predict 1 #correct predict 0 cost of type 1 error cost of type 2 error x + x - #type 1 errors #type 2 errors x - x

Example Instead of minimizing misclassification rate... MODEL A MODEL B Example Type 2 error cost = 10000 Type 1 error cost = 500 Revenue for correctly identifying cancer exists = 4000 Revenue for correctly identifying cancer doesn’t exist = 100 Instead of minimizing misclassification rate...  let’s maximize expected profit Model A: revenue correctly predict 1 revenue correctly predict 0 4000 #correct predict 1 5 100 #correct predict 0 5 cost of type 1 error cost of type 2 error 1 x + x - 500 #type 1 errors 9 10000 #type 2 errors x - x = 6000

Example Instead of minimizing misclassification rate... MODEL A MODEL B Example Type 2 error cost = 10000 Type 1 error cost = 500 Revenue for correctly identifying cancer exists = 4000 Revenue for correctly identifying cancer doesn’t exist = 100 Instead of minimizing misclassification rate...  let’s maximize expected profit Model A: revenue correctly predict 1 revenue correctly predict 0 4000 #correct predict 1 5 100 #correct predict 0 5 cost of type 1 error cost of type 2 error x + x - 500 #type 1 errors 9 10000 #type 2 errors 1 x - x = 6000 Model B: revenue correctly predict 0 4000 #correct predict 1 5 cost of type 1 error 5 100 #correct predict 0 cost of type 2 error x + - 500 #type 1 errors 1 x 10000 #type 2 errors 9 x - x = -70000

Project Work