《商务智能：数据分析的管理视角 Business Intelligence, Analytics, and Data Science：A Managerial Perspective》教学资源（PPT课件，原书第4版）06 Prescriptive Analytics：Optimization and Simulation

Business Intelligence, Analytics, and Data Science: A Managerial Perspective Fourth Edition BUSINESS INTELLIGENCE ANALYTICS Chapter 6 AND DATA SCIENCE Prescriptive Analytics A Managerial Optimization and Simulation Ramesh Sharda Dursun Delen Efraim Turban PEarson Pearson Copyright 2018, 2014, 2011 Pearson Education, Inc. All Rights Reserved

Business Intelligence, Analytics, and Data Science: A Managerial Perspective Fourth Edition Chapter 6 Prescriptive Analytics: Optimization and Simulation Copyright © 2018, 2014, 2011 Pearson Education, Inc. All Rights Reserved Slides in this presentation contain hyperlinks. JAWS users should be able to get a list of links by using INSERT+F7

Learning Objectives (1 of2 6. 1 Understand the applications of prescriptive analytics techniques in combination with reporting and predictive analytics 6.2 Understand the basic concepts of analytical decision modeling 6.3 Understand the concepts of analytical models for selected decision problems, including linear programming and simulation models for decision support 6. 4 Describe how spreadsheets can be used for analytical modeling and solutions Pearson Copyright C 2018, 2014, 2011 Pearson Education, Inc. All Rights Reserved

Copyright © 2018, 2014, 2011 Pearson Education, Inc. All Rights Reserved Learning Objectives (1 of 2) 6.1 Understand the applications of prescriptive analytics techniques in combination with reporting and predictive analytics 6.2 Understand the basic concepts of analytical decision modeling 6.3 Understand the concepts of analytical models for selected decision problems, including linear programming and simulation models for decision support 6.4 Describe how spreadsheets can be used for analytical modeling and solutions

Learning Objectives (2 of 2) 6.5 Explain the basic concepts of optimization and when to use them 6.6 Describe how to structure a linear programming model 6.7 Explain what is meant by sensitivity analysis, what-if analysis, and goal seeking 6. 8 Understand the concepts and applications of different types of simulation 6.9 Understand potential applications of discrete event simulation Pearson Copyright C 2018, 2014, 2011 Pearson Education, Inc. All Rights Reserved

Copyright © 2018, 2014, 2011 Pearson Education, Inc. All Rights Reserved Learning Objectives (2 of 2) 6.5 Explain the basic concepts of optimization and when to use them 6.6 Describe how to structure a linear programming model 6.7 Explain what is meant by sensitivity analysis, what-if analysis, and goal seeking 6.8 Understand the concepts and applications of different types of simulation 6.9 Understand potential applications of discrete event simulation

Opening Vignette School District of Philadelphia Uses Prescriptive Analytics to Find Optimal Solution for Awarding Bus Route Contracts Discussion Questions 1. What decision was being made in this vignette? 2. What data(descriptive and or predictive )might one need to make the best allocations in this scenario? 3. What other costs or constraints might you have to consider in awarding contracts for such routes? 4. Which other situations might be appropriate for applications of such models Pearson Copyright C 2018, 2014, 2011 Pearson Education, Inc. All Rights Reserved

Copyright © 2018, 2014, 2011 Pearson Education, Inc. All Rights Reserved Opening Vignette School District of Philadelphia Uses Prescriptive Analytics to Find Optimal Solution for Awarding Bus Route Contracts Discussion Questions 1. What decision was being made in this vignette? 2. What data (descriptive and or predictive) might one need to make the best allocations in this scenario? 3. What other costs or constraints might you have to consider in awarding contracts for such routes? 4. Which other situations might be appropriate for applications of such models?

Model-Based Decision Making Prescriptive analytics -making decision using some kind of analytical model Descriptive and predictive analytics creates the foundation (i.e, choice alternatives) for prescriptive analytics (i.e, making best possible decision) Descriptive and Predictive leads to Prescriptive Descriptive, Predictive -> Prescriptive ° EXample Profit maximization based on optimal spending on promotions and product/service pricing Pearson Copyright C 2018, 2014, 2011 Pearson Education, Inc. All Rights Reserved

Copyright © 2018, 2014, 2011 Pearson Education, Inc. All Rights Reserved Model-Based Decision Making • Prescriptive analytics – making decision using some kind of analytical model – Descriptive and predictive analytics creates the foundation (i.e., choice alternatives) for prescriptive analytics (i.e., making best possible decision) • Descriptive and Predictive leads to Prescriptive – Descriptive, Predictive → Prescriptive • Example – Profit maximization based on optimal spending on promotions and product/service pricing

rescriptive Analytics Model Examples INFORMS publications such as Interfaces, ORMS Today, and Analytics Magazine, include real-world cases illustrating successful analytics applications Modeling is a key element to prescriptive analytics Mathematical modeling TurboRouter -DSS for ship routing In just a few weeks, company saved $1-2M EXample: Which customers should receive certain promotional offers to maximize overall response(while staying within a pre-specified budget) Pearson Copyright C 2018, 2014, 2011 Pearson Education, Inc. All Rights Reserved

Copyright © 2018, 2014, 2011 Pearson Education, Inc. All Rights Reserved Prescriptive Analytics Model Examples • INFORMS publications such as Interfaces, ORMS Today, and Analytics Magazine, include real-world cases illustrating successful analytics applications. • Modeling is a key element to prescriptive analytics – Mathematical modeling • TurboRouter – DSS for ship routing – In just a few weeks, company saved $1-2M • Example: which customers should receive certain promotional offers to maximize overall response (while staying within a pre-specified budget)

Application Case 6.1 Optimal transport for ExxonMobil downstream through a Decision Support System(Dss) Questions for Discussion 1. List three ways in which manual scheduling of ships could result in more operational costs as compared to the tool developed 2. In what other ways can Exxon Mobil leverage the decision support tool developed to expand and optimize their other business operations? 3. What are some strategic decisions that could be made by decision makers using the tool developed? Pearson Copyright C 2018, 2014, 2011 Pearson Education, Inc. All Rights Reserved

Copyright © 2018, 2014, 2011 Pearson Education, Inc. All Rights Reserved Application Case 6.1 Optimal Transport for ExxonMobil Downstream through a Decision Support System (DSS) Questions for Discussion 1. List three ways in which manual scheduling of ships could result in more operational costs as compared to the tool developed. 2. In what other ways can ExxonMobil leverage the decision support tool developed to expand and optimize their other business operations? 3. What are some strategic decisions that could be made by decision makers using the tool developed?

Major Modeling Issues (1 of 2) Problem identification and environmental analysis(information collection) Variable identification Influence diagrams, cognitive maps Forecasting(predictive analytics) More information leads to better forecast/prediction Multiple models: A decision system can include several models, each of which representing a different part of the decision-making problem Static versus dynamic models See categories of models in the next slide Pearson Copyright C 2018, 2014, 2011 Pearson Education, Inc. All Rights Reserved

Copyright © 2018, 2014, 2011 Pearson Education, Inc. All Rights Reserved Major Modeling Issues (1 of 2) • Problem identification and environmental analysis (information collection) • Variable identification – Influence diagrams, cognitive maps • Forecasting (predictive analytics) – More information leads to better forecast/prediction • Multiple models: A decision system can include several models, each of which representing a different part of the decision-making problem – Static versus dynamic models – See categories of models in the next slide

Major Modeling Issues (2 of 2) Model Management Models (like data)must be managed to maintain their integrity and applicability Model-based management systems(MBMS) Knowledge-Based Modeling( KBM) DSS usually uses quantitative models Expert systems use qualitative, KB models Current trends in modeling Cloud-based modeling tools(efficient and cost effective Transparent models(multidimensional/visual models Model of models e.g., Influence Diagrams(to build and solve models) Pearson Copyright C 2018, 2014, 2011 Pearson Education, Inc. All Rights Reserved

Copyright © 2018, 2014, 2011 Pearson Education, Inc. All Rights Reserved Major Modeling Issues (2 of 2) • Model Management – Models (like data) must be managed to maintain their integrity and applicability – Model-based management systems (MBMS) • Knowledge-Based Modeling (KBM) – DSS usually uses quantitative models – Expert systems use qualitative, KB models • Current trends in modeling – Cloud-based modeling tools (efficient and cost effective) – Transparent models (multidimensional/visual models) – Model of models ▪ e.g., Influence Diagrams (to build and solve models) – …

Categories of Models Table 6. 1 Categories of Models Category Process and objective Representative Techniques Optimization of problems with few Find the best solution from a small Decision tables. decision trees native number of alternatives analytic hierarchy process Optimization via algorithm Find the best solution from a large Linear and other mathematical number of alternatives, using a step-by- programming models, network step improvement process models Optimization via an analytic Find the best solution in one step, using Some inventory models formula a formula Simulation Find a good enough solution or the best Several types of simulation among the alternatives checked, using experimentation Heuristics Find a good enough solution, using Heuristic programming, expert ules Predictive models Predict the future for a given Forecasting models, Markov scenarIo analysIs Other models Solve a what-if case, using a Financial modeling, waiting lines formula Pearson Copyright C 2018, 2014, 2011 Pearson Education, Inc. All Rights Reserved

Copyright © 2018, 2014, 2011 Pearson Education, Inc. All Rights Reserved Categories of Models Table 6.1 Categories of Models Category Process and Objective Representative Techniques Optimization of problems with few alternatives Find the best solution from a small number of alternatives Decision tables, decision trees, analytic hierarchy process Optimization via algorithm Find the best solution from a large number of alternatives, using a step-by￾step improvement process Linear and other mathematical programming models, network models Optimization via an analytic formula Find the best solution in one step, using a formula Some inventory models Simulation Find a good enough solution or the best among the alternatives checked, using experimentation Several types of simulation Heuristics Find a good enough solution, using rules Heuristic programming, expert systems Predictive models Predict the future for a given scenario Forecasting models, Markov analysis Other models Solve a what-if case, using a formula Financial modeling, waiting lines